COVID-19
Regístrese
metricas
covid
Radiología (English Edition)
Buscar en
Radiología (English Edition)
Toda la web
Inicio Radiología (English Edition) Development of severity and mortality prediction models for covid-19 patients at...
Journal Information
Back to article

Statistics

Follow this link to access the full text of the article

Original articles
Development of severity and mortality prediction models for covid-19 patients at emergency department including the chest x-ray
Elaboración de modelos predictivos de la gravedad y la mortalidad en pacientes con COVID-19 que acuden al servicio de urgencias, incluida la radiografía torácica
P. Calvillo-Batllésa,
Corresponding author
calvillo_mar@gva.es

Corresponding author.
, L. Cerdá-Alberichb, C. Fonfría-Esparciaa, A. Carreres-Ortegaa, C.F. Muñoz-Núñeza, L. Trilles-Olasoa, L. Martí-Bonmatía,b
a Servicio de Radiología, Hospital Universitario y Politécnico La Fe, Valencia, Spain
b Grupo de Investigación Biomédica en Imagen (GIBI230), Instituto de Investigación Sanitaria La Fe, Valencia, Spain
Read
1477
Times
was read the article
56
Total PDF
1421
Total HTML
Share statistics
 array:24 [
  "pii" => "S2173510722000222"
  "issn" => "21735107"
  "doi" => "10.1016/j.rxeng.2021.09.004"
  "estado" => "S300"
  "fechaPublicacion" => "2022-05-01"
  "aid" => "1340"
  "copyright" => "SERAM"
  "copyrightAnyo" => "2021"
  "documento" => "article"
  "crossmark" => 1
  "subdocumento" => "fla"
  "cita" => "Radiologia. 2022;64:214-27"
  "abierto" => array:3 [
    "ES" => false
    "ES2" => false
    "LATM" => false
  ]
  "gratuito" => false
  "lecturas" => array:1 [
    "total" => 0
  ]
  "Traduccion" => array:1 [
    "es" => array:19 [
      "pii" => "S0033833821001806"
      "issn" => "00338338"
      "doi" => "10.1016/j.rx.2021.09.011"
      "estado" => "S300"
      "fechaPublicacion" => "2022-05-01"
      "aid" => "1340"
      "copyright" => "SERAM"
      "documento" => "article"
      "crossmark" => 1
      "subdocumento" => "fla"
      "cita" => "Radiologia. 2022;64:214-27"
      "abierto" => array:3 [
        "ES" => false
        "ES2" => false
        "LATM" => false
      ]
      "gratuito" => false
      "lecturas" => array:1 [
        "total" => 0
      ]
      "es" => array:13 [
        "idiomaDefecto" => true
        "cabecera" => "<span class="elsevierStyleTextfn">Original</span>"
        "titulo" => "Elaboraci&#243;n de modelos predictivos de la gravedad y la mortalidad en pacientes con COVID-19 que acuden al servicio de urgencias&#44; incluida la radiograf&#237;a tor&#225;cica"
        "tienePdf" => "es"
        "tieneTextoCompleto" => "es"
        "tieneResumen" => array:2 [
          0 => "es"
          1 => "en"
        ]
        "paginas" => array:1 [
          0 => array:2 [
            "paginaInicial" => "214"
            "paginaFinal" => "227"
          ]
        ]
        "titulosAlternativos" => array:1 [
          "en" => array:1 [
            "titulo" => "Development of severity and mortality prediction models for covid-19 patients at emergency department including the chest <span class="elsevierStyleSmallCaps">x</span>-ray"
          ]
        ]
        "contieneResumen" => array:2 [
          "es" => true
          "en" => true
        ]
        "contieneTextoCompleto" => array:1 [
          "es" => true
        ]
        "contienePdf" => array:1 [
          "es" => true
        ]
        "resumenGrafico" => array:2 [
          "original" => 0
          "multimedia" => array:7 [
            "identificador" => "fig0030"
            "etiqueta" => "Figura 6"
            "tipo" => "MULTIMEDIAFIGURA"
            "mostrarFloat" => true
            "mostrarDisplay" => false
            "figura" => array:1 [
              0 => array:4 [
                "imagen" => "gr6.jpeg"
                "Alto" => 1530
                "Ancho" => 2917
                "Tamanyo" => 416486
              ]
            ]
            "descripcion" => array:1 [
              "es" => "<p id="spar0075" class="elsevierStyleSimplePara elsevierViewall">Las curvas ROC &#40;arriba&#41; y CPS &#40;abajo&#41; de la validaci&#243;n interna realizada con un conjunto de datos nuevo para los modelos predictivos de mortalidad hospitalaria &#40;SVM&#58; m&#225;quinas de vectores de soporte &#91;<span class="elsevierStyleItalic">Support Vector Machine</span>&#44; azul&#93;&#59; RF&#58; bosque aleatorio &#91;<span class="elsevierStyleItalic">Random Forest</span>&#44; verde&#93;&#59; GB&#58; potenciaci&#243;n del gradiente &#91;<span class="elsevierStyleItalic">Gradient Boosting</span>&#44; naranja&#93;&#41; elaborados con tres combinaciones distintas de par&#225;metros &#40;A&#58; par&#225;metros epidemiol&#243;gicos y radiol&#243;gicos&#59; B&#58; par&#225;metros epidemiol&#243;gicos&#44; radiol&#243;gicos&#44; cl&#237;nicos y anal&#237;ticos&#59; C&#58; par&#225;metros epidemiol&#243;gicos&#44; radiol&#243;gicos&#44; cl&#237;nicos&#44; anal&#237;ticos y basados en la RNC&#41;&#46; Se muestran los valores del AUC correspondientes&#46;</p>"
            ]
          ]
        ]
        "autores" => array:1 [
          0 => array:2 [
            "autoresLista" => "P&#46; Calvillo-Batll&#233;s, L&#46; Cerd&#225;-Alberich, C&#46; Fonfr&#237;a-Esparcia, A&#46; Carreres-Ortega, C&#46;F&#46; Mu&#241;oz-N&#250;&#241;ez, L&#46; Trilles-Olaso, L&#46; Mart&#237;-Bonmat&#237;"
            "autores" => array:7 [
              0 => array:2 [
                "nombre" => "P&#46;"
                "apellidos" => "Calvillo-Batll&#233;s"
              ]
              1 => array:2 [
                "nombre" => "L&#46;"
                "apellidos" => "Cerd&#225;-Alberich"
              ]
              2 => array:2 [
                "nombre" => "C&#46;"
                "apellidos" => "Fonfr&#237;a-Esparcia"
              ]
              3 => array:2 [
                "nombre" => "A&#46;"
                "apellidos" => "Carreres-Ortega"
              ]
              4 => array:2 [
                "nombre" => "C&#46;F&#46;"
                "apellidos" => "Mu&#241;oz-N&#250;&#241;ez"
              ]
              5 => array:2 [
                "nombre" => "L&#46;"
                "apellidos" => "Trilles-Olaso"
              ]
              6 => array:2 [
                "nombre" => "L&#46;"
                "apellidos" => "Mart&#237;-Bonmat&#237;"
              ]
            ]
          ]
        ]
      ]
      "idiomaDefecto" => "es"
      "Traduccion" => array:1 [
        "en" => array:9 [
          "pii" => "S2173510722000222"
          "doi" => "10.1016/j.rxeng.2021.09.004"
          "estado" => "S300"
          "subdocumento" => ""
          "abierto" => array:3 [
            "ES" => false
            "ES2" => false
            "LATM" => false
          ]
          "gratuito" => false
          "lecturas" => array:1 [
            "total" => 0
          ]
          "idiomaDefecto" => "en"
          "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2173510722000222?idApp=UINPBA00004N"
        ]
      ]
      "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0033833821001806?idApp=UINPBA00004N"
      "url" => "/00338338/0000006400000003/v1_202205110735/S0033833821001806/v1_202205110735/es/main.assets"
    ]
  ]
  "itemSiguiente" => array:19 [
    "pii" => "S2173510722000660"
    "issn" => "21735107"
    "doi" => "10.1016/j.rxeng.2022.03.005"
    "estado" => "S300"
    "fechaPublicacion" => "2022-05-01"
    "aid" => "1380"
    "copyright" => "SERAM"
    "documento" => "article"
    "crossmark" => 1
    "subdocumento" => "fla"
    "cita" => "Radiologia. 2022;64:228-36"
    "abierto" => array:3 [
      "ES" => false
      "ES2" => false
      "LATM" => false
    ]
    "gratuito" => false
    "lecturas" => array:1 [
      "total" => 0
    ]
    "en" => array:13 [
      "idiomaDefecto" => true
      "cabecera" => "<span class="elsevierStyleTextfn">Update in Radiology</span>"
      "titulo" => "Artificial Intelligence in Radiology&#58; an introduction to the most important concepts"
      "tienePdf" => "en"
      "tieneTextoCompleto" => "en"
      "tieneResumen" => array:2 [
        0 => "en"
        1 => "es"
      ]
      "paginas" => array:1 [
        0 => array:2 [
          "paginaInicial" => "228"
          "paginaFinal" => "236"
        ]
      ]
      "titulosAlternativos" => array:1 [
        "es" => array:1 [
          "titulo" => "Inteligencia artificial en Radiolog&#237;a&#58; introducci&#243;n a los conceptos m&#225;s importantes"
        ]
      ]
      "contieneResumen" => array:2 [
        "en" => true
        "es" => true
      ]
      "contieneTextoCompleto" => array:1 [
        "en" => true
      ]
      "contienePdf" => array:1 [
        "en" => true
      ]
      "resumenGrafico" => array:2 [
        "original" => 0
        "multimedia" => array:8 [
          "identificador" => "fig0030"
          "etiqueta" => "Figure 6"
          "tipo" => "MULTIMEDIAFIGURA"
          "mostrarFloat" => true
          "mostrarDisplay" => false
          "figura" => array:1 [
            0 => array:4 [
              "imagen" => "gr6.jpeg"
              "Alto" => 736
              "Ancho" => 2925
              "Tamanyo" => 167113
            ]
          ]
          "detalles" => array:1 [
            0 => array:3 [
              "identificador" => "at0030"
              "detalle" => "Figure "
              "rol" => "short"
            ]
          ]
          "descripcion" => array:1 [
            "en" => "<p id="spar0035" class="elsevierStyleSimplePara elsevierViewall"><span class="elsevierStyleItalic">Filters</span> and <span class="elsevierStyleItalic">pooling</span>&#58; A <span class="elsevierStyleItalic">filter</span> is a matrix that scans the image and performs a multiplication operation element by element and then an addition operation to yield a value &#40;convolution&#41;&#46; High values are obtained when the <span class="elsevierStyleItalic">filter</span> is applied to a feature similar to the filter&#59; low values are obtained when it is applied to a feature that is different from it&#46; In a <span class="elsevierStyleItalic">filter</span> that detects vertical edges&#44; high values mean that a vertical edge has been detected&#46; Is this not reminiscent of the cells of the primary visual cortex&#63; The <span class="elsevierStyleItalic">pooling</span> layer&#44; average with a size of 2 &#215; 2 in this example&#44; determines the mean of the values in the range&#44; thus reducing the dimensionality of the feature map&#46;</p>"
          ]
        ]
      ]
      "autores" => array:1 [
        0 => array:2 [
          "autoresLista" => "A&#46; P&#233;rez del Barrio, P&#46; Men&#233;ndez Fern&#225;ndez-Miranda, P&#46; Sanz Bell&#243;n, L&#46; Lloret Iglesias, D&#46; Rodr&#237;guez Gonz&#225;lez"
          "autores" => array:5 [
            0 => array:2 [
              "nombre" => "A&#46;"
              "apellidos" => "P&#233;rez del Barrio"
            ]
            1 => array:2 [
              "nombre" => "P&#46;"
              "apellidos" => "Men&#233;ndez Fern&#225;ndez-Miranda"
            ]
            2 => array:2 [
              "nombre" => "P&#46;"
              "apellidos" => "Sanz Bell&#243;n"
            ]
            3 => array:2 [
              "nombre" => "L&#46;"
              "apellidos" => "Lloret Iglesias"
            ]
            4 => array:2 [
              "nombre" => "D&#46;"
              "apellidos" => "Rodr&#237;guez Gonz&#225;lez"
            ]
          ]
        ]
      ]
    ]
    "idiomaDefecto" => "en"
    "Traduccion" => array:1 [
      "es" => array:9 [
        "pii" => "S0033833822000972"
        "doi" => "10.1016/j.rx.2022.03.003"
        "estado" => "S300"
        "subdocumento" => ""
        "abierto" => array:3 [
          "ES" => false
          "ES2" => false
          "LATM" => false
        ]
        "gratuito" => false
        "lecturas" => array:1 [
          "total" => 0
        ]
        "idiomaDefecto" => "es"
        "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0033833822000972?idApp=UINPBA00004N"
      ]
    ]
    "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2173510722000660?idApp=UINPBA00004N"
    "url" => "/21735107/0000006400000003/v1_202206060554/S2173510722000660/v1_202206060554/en/main.assets"
  ]
  "itemAnterior" => array:19 [
    "pii" => "S2173510721000471"
    "issn" => "21735107"
    "doi" => "10.1016/j.rxeng.2020.07.008"
    "estado" => "S300"
    "fechaPublicacion" => "2022-05-01"
    "aid" => "1213"
    "copyright" => "SERAM"
    "documento" => "article"
    "crossmark" => 1
    "subdocumento" => "fla"
    "cita" => "Radiologia. 2022;64:206-13"
    "abierto" => array:3 [
      "ES" => false
      "ES2" => false
      "LATM" => false
    ]
    "gratuito" => false
    "lecturas" => array:1 [
      "total" => 0
    ]
    "en" => array:13 [
      "idiomaDefecto" => true
      "cabecera" => "<span class="elsevierStyleTextfn">Original articles</span>"
      "titulo" => "Ultralow-dose CT of the petrous bone using iterative reconstruction technique&#44; tin filter and high resolution detectors allows an adequate assessment of the petrous bone structures"
      "tienePdf" => "en"
      "tieneTextoCompleto" => "en"
      "tieneResumen" => array:2 [
        0 => "en"
        1 => "es"
      ]
      "paginas" => array:1 [
        0 => array:2 [
          "paginaInicial" => "206"
          "paginaFinal" => "213"
        ]
      ]
      "titulosAlternativos" => array:1 [
        "es" => array:1 [
          "titulo" => "La tomograf&#237;a computarizada de pe&#241;ascos con dosis ultrabaja&#44; utilizando filtro de esta&#241;o&#44; detectores de alta resoluci&#243;n y reconstrucci&#243;n iterativa&#44; permite una adecuada valoraci&#243;n de las estructuras del pe&#241;asco"
        ]
      ]
      "contieneResumen" => array:2 [
        "en" => true
        "es" => true
      ]
      "contieneTextoCompleto" => array:1 [
        "en" => true
      ]
      "contienePdf" => array:1 [
        "en" => true
      ]
      "resumenGrafico" => array:2 [
        "original" => 0
        "multimedia" => array:8 [
          "identificador" => "fig0005"
          "etiqueta" => "Figure 1"
          "tipo" => "MULTIMEDIAFIGURA"
          "mostrarFloat" => true
          "mostrarDisplay" => false
          "figura" => array:1 [
            0 => array:4 [
              "imagen" => "gr1.jpeg"
              "Alto" => 2376
              "Ancho" => 2667
              "Tamanyo" => 433062
            ]
          ]
          "detalles" => array:1 [
            0 => array:3 [
              "identificador" => "at0005"
              "detalle" => "Figure "
              "rol" => "short"
            ]
          ]
          "descripcion" => array:1 [
            "en" => "<p id="spar0005" class="elsevierStyleSimplePara elsevierViewall">Computed tomography &#40;CT&#41; of petrous bones acquired in the 32 and 16-channel scanner&#44; respectively&#44; in the axial plane&#44; in the area of the tympanic cavity at the level of the malleus &#40;blue arrow&#41; and incus &#40;yellow arrow&#41; in the images on the left&#44; and the stapes &#40;red arrow&#41; and cochlea &#40;green arrow&#41; in the right-hand images&#46; The 32-MDCT obtains images with adequate quality for the diagnosis&#44; with less noise&#44; using a radiation dose 10 times lower than the 16-MDCT&#46;</p>"
          ]
        ]
      ]
      "autores" => array:1 [
        0 => array:2 [
          "autoresLista" => "M&#46; Novoa Ferro, E&#46; Santos Armentia, N&#46; Silva Priegue, C&#46; Jurado Basildo, C&#46;A&#46; Sep&#250;lveda Villegas, C&#46; Delgado S&#225;nchez-Graci&#225;n"
          "autores" => array:6 [
            0 => array:2 [
              "nombre" => "M&#46;"
              "apellidos" => "Novoa Ferro"
            ]
            1 => array:2 [
              "nombre" => "E&#46;"
              "apellidos" => "Santos Armentia"
            ]
            2 => array:2 [
              "nombre" => "N&#46;"
              "apellidos" => "Silva Priegue"
            ]
            3 => array:2 [
              "nombre" => "C&#46;"
              "apellidos" => "Jurado Basildo"
            ]
            4 => array:2 [
              "nombre" => "C&#46;A&#46;"
              "apellidos" => "Sep&#250;lveda Villegas"
            ]
            5 => array:2 [
              "nombre" => "C&#46;"
              "apellidos" => "Delgado S&#225;nchez-Graci&#225;n"
            ]
          ]
        ]
      ]
    ]
    "idiomaDefecto" => "en"
    "Traduccion" => array:1 [
      "es" => array:9 [
        "pii" => "S0033833820300941"
        "doi" => "10.1016/j.rx.2020.07.001"
        "estado" => "S300"
        "subdocumento" => ""
        "abierto" => array:3 [
          "ES" => false
          "ES2" => false
          "LATM" => false
        ]
        "gratuito" => false
        "lecturas" => array:1 [
          "total" => 0
        ]
        "idiomaDefecto" => "es"
        "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0033833820300941?idApp=UINPBA00004N"
      ]
    ]
    "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2173510721000471?idApp=UINPBA00004N"
    "url" => "/21735107/0000006400000003/v1_202206060554/S2173510721000471/v1_202206060554/en/main.assets"
  ]
  "en" => array:22 [
    "idiomaDefecto" => true
    "cabecera" => "<span class="elsevierStyleTextfn">Original articles</span>"
    "titulo" => "Development of severity and mortality prediction models for covid-19 patients at emergency department including the chest x-ray"
    "tieneTextoCompleto" => true
    "paginas" => array:1 [
      0 => array:2 [
        "paginaInicial" => "214"
        "paginaFinal" => "227"
      ]
    ]
    "autores" => array:1 [
      0 => array:4 [
        "autoresLista" => "P&#46; Calvillo-Batll&#233;s, L&#46; Cerd&#225;-Alberich, C&#46; Fonfr&#237;a-Esparcia, A&#46; Carreres-Ortega, C&#46;F&#46; Mu&#241;oz-N&#250;&#241;ez, L&#46; Trilles-Olaso, L&#46; Mart&#237;-Bonmat&#237;"
        "autores" => array:7 [
          0 => array:4 [
            "nombre" => "P&#46;"
            "apellidos" => "Calvillo-Batll&#233;s"
            "email" => array:1 [
              0 => "calvillo_mar@gva.es"
            ]
            "referencia" => array:2 [
              0 => array:2 [
                "etiqueta" => "<span class="elsevierStyleSup">a</span>"
                "identificador" => "aff0005"
              ]
              1 => array:2 [
                "etiqueta" => "<span class="elsevierStyleSup">&#42;</span>"
                "identificador" => "cor0005"
              ]
            ]
          ]
          1 => array:3 [
            "nombre" => "L&#46;"
            "apellidos" => "Cerd&#225;-Alberich"
            "referencia" => array:1 [
              0 => array:2 [
                "etiqueta" => "<span class="elsevierStyleSup">b</span>"
                "identificador" => "aff0010"
              ]
            ]
          ]
          2 => array:3 [
            "nombre" => "C&#46;"
            "apellidos" => "Fonfr&#237;a-Esparcia"
            "referencia" => array:1 [
              0 => array:2 [
                "etiqueta" => "<span class="elsevierStyleSup">a</span>"
                "identificador" => "aff0005"
              ]
            ]
          ]
          3 => array:3 [
            "nombre" => "A&#46;"
            "apellidos" => "Carreres-Ortega"
            "referencia" => array:1 [
              0 => array:2 [
                "etiqueta" => "<span class="elsevierStyleSup">a</span>"
                "identificador" => "aff0005"
              ]
            ]
          ]
          4 => array:3 [
            "nombre" => "C&#46;F&#46;"
            "apellidos" => "Mu&#241;oz-N&#250;&#241;ez"
            "referencia" => array:1 [
              0 => array:2 [
                "etiqueta" => "<span class="elsevierStyleSup">a</span>"
                "identificador" => "aff0005"
              ]
            ]
          ]
          5 => array:3 [
            "nombre" => "L&#46;"
            "apellidos" => "Trilles-Olaso"
            "referencia" => array:1 [
              0 => array:2 [
                "etiqueta" => "<span class="elsevierStyleSup">a</span>"
                "identificador" => "aff0005"
              ]
            ]
          ]
          6 => array:3 [
            "nombre" => "L&#46;"
            "apellidos" => "Mart&#237;-Bonmat&#237;"
            "referencia" => array:2 [
              0 => array:2 [
                "etiqueta" => "<span class="elsevierStyleSup">a</span>"
                "identificador" => "aff0005"
              ]
              1 => array:2 [
                "etiqueta" => "<span class="elsevierStyleSup">b</span>"
                "identificador" => "aff0010"
              ]
            ]
          ]
        ]
        "afiliaciones" => array:2 [
          0 => array:3 [
            "entidad" => "Servicio de Radiolog&#237;a&#44; Hospital Universitario y Polit&#233;cnico La Fe&#44; Valencia&#44; Spain"
            "etiqueta" => "a"
            "identificador" => "aff0005"
          ]
          1 => array:3 [
            "entidad" => "Grupo de Investigaci&#243;n Biom&#233;dica en Imagen &#40;GIBI2<span class="elsevierStyleSup">30</span>&#41;&#44; Instituto de Investigaci&#243;n Sanitaria La Fe&#44; Valencia&#44; Spain"
            "etiqueta" => "b"
            "identificador" => "aff0010"
          ]
        ]
        "correspondencia" => array:1 [
          0 => array:3 [
            "identificador" => "cor0005"
            "etiqueta" => "&#8270;"
            "correspondencia" => "Corresponding author&#46;"
          ]
        ]
      ]
    ]
    "titulosAlternativos" => array:1 [
      "es" => array:1 [
        "titulo" => "Elaboraci&#243;n de modelos predictivos de la gravedad y la mortalidad en pacientes con COVID-19 que acuden al servicio de urgencias&#44; incluida la radiograf&#237;a tor&#225;cica"
      ]
    ]
    "resumenGrafico" => array:2 [
      "original" => 0
      "multimedia" => array:8 [
        "identificador" => "fig0025"
        "etiqueta" => "Figure 5"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr5.jpeg"
            "Alto" => 1760
            "Ancho" => 3333
            "Tamanyo" => 678183
          ]
        ]
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0025"
            "detalle" => "Figure "
            "rol" => "short"
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0025" class="elsevierStyleSimplePara elsevierViewall">The ROC &#40;up&#41; and the PRC &#40;down&#41; curves of the internal validation performed with an unseen dataset for the severity predictive models built with three different combinations of parameters&#46; &#40;A&#58; epidemiological and radiological parameters&#44; B&#58; epidemiological&#44; radiological&#44; clinical and laboratory parameters&#44; C&#58; epidemiological&#44; radiological&#44; clinical&#44; laboratory and CNN-based parameters&#41;&#46; The curves per severity level are obtained with a one-vs-all classification methodology&#58; home discharge or hospitalization &#8804; 3 days &#40;level&#47;class 0&#44; in light blue&#41;&#44; need for hospital stay &#62;3 days &#40;level&#47;class 1&#44; in orange&#41;&#44; need for ICU stay or death due to COVID-19 &#40;level&#47;class 2&#44; in blue&#41;&#46; The dashed lines represent the micro-average &#40;magenta&#41; and macro-average &#40;dark blue&#41; curve statistics which take into account the single level contributions&#46; The corresponding values of AUC are shown&#46; Precision&#8239;&#61;&#8239;true positive &#47; &#40;true positive&#8239;&#43;&#8239;false positive&#41;&#46; Recall &#40;sensitivity&#41;&#8239;&#61;&#8239;true positive &#47; &#40;true positive&#8239;&#43;&#8239;false negative&#41;&#46;</p>"
        ]
      ]
    ]
    "textoCompleto" => "<span class="elsevierStyleSections"><span id="sec0005" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0065">Introduction</span><p id="par0005" class="elsevierStylePara elsevierViewall">The COVID-19 pandemic is posing a large challenge for health systems&#44; forcing a balance to be found between resource management and safe decision-making with a lower than needed scientific evidence&#46; Clinical presentation of the disease varies from mild symptoms to a bilateral bronchopneumonia with hypoxemia&#46; An Acute Respiratory Distress Syndrome or the involvement of other vital organs may complicate the clinical course and compromise the life of the patient&#46; Uncertainties make necessary the development of specific disease models in order to identify patients by prognosis and severity&#44; requiring hospital or even intensive care&#46; Thoracic imaging has served as a diagnostic tool in emergency department &#40;ED&#41; as it may reveal suggestive COVID-19 patterns of lung involvement&#46;<a class="elsevierStyleCrossRefs" href="#bib0005"><span class="elsevierStyleSup">1&#8211;5</span></a> However&#44; studies on the utility of the chest X-ray &#40;CXR&#41; for predicting health outcomes are limited<a class="elsevierStyleCrossRefs" href="#bib0030"><span class="elsevierStyleSup">6&#8211;9</span></a> and the prognostic studies have mainly been based on chest CT&#46;<a class="elsevierStyleCrossRefs" href="#bib0050"><span class="elsevierStyleSup">10&#8211;12</span></a></p><p id="par0010" class="elsevierStylePara elsevierViewall">Considering the higher use of CXR&#44; its larger availability and safer use to control the spread of the virus when compared with CT&#44; we aimed to develop two multivariable prediction models for severity and mortality estimations in COVID-19 taking into consideration the radiological&#44; demographic&#44; clinical and laboratory variables registered on the emergency evaluation&#46;</p></span><span id="sec0010" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0070">Material and methods</span><p id="par0015" class="elsevierStylePara elsevierViewall">The institutional review board approved this retrospective study&#46; This research did not receive any specific grant from funding agencies in the public&#44; commercial&#44; or not-for-profit sectors&#46;</p><p id="par0020" class="elsevierStylePara elsevierViewall">It followed the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis&#58; the TRIPOD statement&#46;<a class="elsevierStyleCrossRef" href="#bib0065"><span class="elsevierStyleSup">13</span></a> The risk of bias and applicability was assessed with the Prediction model Risk of Bias Assessment Tool &#40;PROBAST&#41;&#46;<a class="elsevierStyleCrossRef" href="#bib0070"><span class="elsevierStyleSup">14</span></a></p><span id="sec0015" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0075">Patients</span><p id="par0025" class="elsevierStylePara elsevierViewall">All consecutive symptomatic adult patients visiting the ED of our university hospital between 24 February and 24 April 2020 were included if CXR was performed and Severe Acute Respiratory Syndrome - Coronavirus 2 &#40;SARS-CoV-2&#41; RNA was detected in nasopharyngeal swab or sputum&#47;bronchoalveolar lavage&#46; Patients with simultaneous final diagnosis other than COVID-19 were excluded&#46; Emergency physicians triaged these patients&#46; Oligosymptomatic patients with normal CXR and laboratory parameters&#44; oxygen saturation &#62;95&#37;&#44; absence of chronic diseases and &#60;65 years old were discharged at home&#46; Patients admitted at the hospital were treated with standard of care drugs in force at the time and they were discharged if afebrile for at least 3 days with respiratory symptoms and laboratory parameters improvement &#40;Flowchart of the study in <a class="elsevierStyleCrossRef" href="#fig0005">Fig&#46; 1</a>&#41;&#46;</p><elsevierMultimedia ident="fig0005"></elsevierMultimedia></span><span id="sec0020" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0080">Chest X-ray review</span><p id="par0030" class="elsevierStylePara elsevierViewall">Initial CXR readings on admission were distributed among five radiologists with an average of 11 years of experience in thoracic imaging&#44; blinded to the rest of parameters and outcome&#46; The following items were described &#40;<a class="elsevierStyleCrossRef" href="#fig0010">Fig&#46; 2</a>&#41;&#58;<ul class="elsevierStyleList" id="lis0005"><li class="elsevierStyleListItem" id="lsti0005"><span class="elsevierStyleLabel">&#8226;</span><p id="par0035" class="elsevierStylePara elsevierViewall">Absence &#40;level 0&#41; or presence and density of opacities&#58; only low-density &#40;level 1&#41; or consolidation &#40;&#43;&#47;- low density&#41; &#40;level 2&#41;&#46; Lung opacities were considered &#8220;low-density&#8221; if the attenuation did not conceal the underlying vessels and &#8220;consolidation&#8221; if the opacification of the parenchyma obscured the underlying vessels&#46;</p></li><li class="elsevierStyleListItem" id="lsti0010"><span class="elsevierStyleLabel">&#8226;</span><p id="par0040" class="elsevierStylePara elsevierViewall">Distribution of opacities&#58; peripheral &#40;in the outer third of the lungs&#41; &#47; central &#40;in the inner two thirds of the lungs&#41; prevalence &#47; both without clear prevalence&#59; unilateral &#47; bilateral&#59; upper &#40;suprahillar&#41; &#47; medium &#40;hilar&#41; &#47; lower fields &#40;infrahilar&#41;&#46; For determining the distribution and extent of involvement each lung was divided in upper&#44; medium and inferior field&#44; with a maximum of six fields&#46; The affected lobes were not recorded since a high percentage of the radiographs were portable &#40;27&#46;7&#37;&#41;&#46;</p></li><li class="elsevierStyleListItem" id="lsti0015"><span class="elsevierStyleLabel">&#8226;</span><p id="par0045" class="elsevierStylePara elsevierViewall">Extension degree and score of lung involvement&#58; the extent was graded as mild &#40;if size opacity was less than 1 field&#41;&#59; moderate &#40;1-2 fields involved&#41;&#59; extensive &#40;3-4 fields involved&#41; and very extensive &#40;5-6 fields involved&#41;&#46; A numerical value was assigned to each field depending on the percentage with increased attenuation&#58; 0 &#40;0&#37;&#41;&#44; 1 &#40;&#8804;50&#37;&#41;&#44; and 2 &#40;&#62;50&#37;&#41;&#46; A total score of the lung involvement extent &#40;ExtScoreCXR&#41; was reached by adding up the six field scores&#44; obtaining a value from 0 to 12&#46; The ExtScoreCXR was created by the authors after considering it by consensus a simple&#44; fast&#44; reproducible and optimal method of semi-quantification of the lung involvement extent&#46; The extent score from the division into lung fields has also been used by other authors in patients with COVID-19&#46;<a class="elsevierStyleCrossRefs" href="#bib0030"><span class="elsevierStyleSup">6&#8211;8&#44;15</span></a></p></li><li class="elsevierStyleListItem" id="lsti0020"><span class="elsevierStyleLabel">&#8226;</span><p id="par0050" class="elsevierStylePara elsevierViewall">The imaging variables were agreed upon by the radiologists from the X-ray of the first 80 cases detected&#46; House-made repository software was used to record all the variables in a structured shared database&#44; with description and imaging reminders aiming to reduce variability between readers and mandatory fill-in fields to optimize data collection&#46;</p></li></ul></p><elsevierMultimedia ident="fig0010"></elsevierMultimedia></span><span id="sec0025" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0085">Demographics&#44; clinical and laboratory variables collected on the first visit to ED</span><p id="par0055" class="elsevierStylePara elsevierViewall">Demographics&#44; institutionalization&#44; comorbidities&#44; clinical manifestations&#44; peripheral oxygen saturation &#40;SatO2&#41;&#44; laboratory data -C reactive protein &#40;CRP&#41;&#44; lactate dehydrogenase &#40;LDH&#41;&#44; lymphocyte count&#44; platelet count&#44; and D-dimer- were recorded&#46; We calculated SatO2&#47;FiO2 to avoid data loss from patients with SatO2 obtained under oxygen therapy&#46; FiO2 is the fraction of inspired oxygen and changes depending on the oxygen flow rate delivered to each patient&#59; for room air it is 0&#46;21&#46;</p></span><span id="sec0030" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0090">Computational Imaging &#40;Artificial Intelligence Data&#41;</span><p id="par0060" class="elsevierStylePara elsevierViewall">Probability indices of lung abnormal findings were extracted from CXR by a Convolutional neural network &#40;CNN&#41;-based diagnostic tool&#44; QUIBIM Precision CXR v2&#46;0&#46;0 &#40;QUIBIM S&#46;L&#41; with CE mark class IIa&#46; The algorithm includes an ensemble of deep learning models that estimate the probability of different thoracic findings and the probability of abnormality in CXR&#46; A value of 0 would mean no probability of belonging to that pathological finding and a value of 1 would mean total certainty of belonging to that pathological group&#46; <span class="elsevierStyleItalic">See supplementary material about the CNN-tool on Appendix 1</span>&#46; Indices for &#8220;consolidation&#8221;&#44; &#8220;lung opacity&#8221; and &#8220;abnormal CXR&#8221; were incorporated into the final model to assess whether they improved its predictive accuracy</p></span><span id="sec0035" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0095">Outcome variables</span><p id="par0065" class="elsevierStylePara elsevierViewall">Three severity levels were defined&#58; home discharge or hospitalization &#8804; 3 days &#40;level 0&#41;&#44; hospital stay &#62;3 days &#40;level 1&#41;&#44; need for intensive care unit &#40;ICU&#41; stay or death due to COVID-19 &#40;level 2&#41;&#46; Both days of hospitalization and days to death were registered&#46; The median of follow-up was 91 days &#40;range 64-124 days&#41;&#46;</p></span><span id="sec0040" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0100">Univariable analysis</span><p id="par0070" class="elsevierStylePara elsevierViewall">Correlations between the lung involvement extension on CXR &#40;degrees and score&#41; and the days with symptoms&#44; the SatO2&#47;FiO2 and the variable outcomes were investigated&#46; Spearman&#44; Kendall&#44; Rank or Point biserial tests were used depending on the type of the studied variables&#46; For interpreting the strength of a relationship based on its r-value &#40;using the absolute value of the r-value to make all values positive&#41; we applied the following rule of thumb&#58; r &#60; 0&#46;1 none&#44; 0&#46;1&#8239;&#60;&#8239;r&#8239;&#60;&#8239;0&#46;3 weak&#44; 0&#46;3&#8239;&#60;&#8239;r&#8239;&#60;&#8239;0&#46;5 moderate&#44; 0&#46;5&#8239;&#60;&#8239;r&#8239;&#60;&#8239;0&#46;8 strong and r &#62; 0&#46;8 very strong&#46;</p></span><span id="sec0045" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0105">Prognostic predictive models</span><p id="par0075" class="elsevierStylePara elsevierViewall">Different prognostic predictive models were developed using three types of classifiers or ensemble methods &#40;Gradient Boosting&#44; Random Forest and Support Vector Machine&#41; and applying a stratified cross-validation with the 80&#37; of the population&#46; These classifiers have been chosen because they are intrinsically suited to solve classification problems with two or more classes&#46; For instance&#44; Support Vector Machine is a linear model that scales relatively well to high dimensional data and is less prone to over-fitting&#46; Both Random Forest and Gradient Boosting are ensemble models that consist in training multiple weak learners and merge their results to build a &#8220;strong learner&#8221;&#46; They differ on two key points&#58; the way the training sets for each base model are defined and the order in which the weak learners are trained&#46; In particular&#44; Random forest creates random train samples from the full training set based on a random selection of both observations and features &#40;bootstrapping&#41;&#46; A weak learner is trained in parallel on each of the derived training sets&#46; In the case of Gradient Boosting&#44; the method consists in fitting several weak learners sequentially&#44; where&#44; at each iteration&#44; more weight is added to the observations with the worst prediction from the previous iteration&#46; Since each weak learner is built upon the results from the preceding one&#44; the computation cannot be parallelized and the computation can be longer&#46;</p><p id="par0080" class="elsevierStylePara elsevierViewall">An internal validation was performed with an unseen dataset corresponding to the remaining 20&#37; to assess model generalizability and robustness&#46;</p><p id="par0085" class="elsevierStylePara elsevierViewall">The model hyperparameters were obtained by performing a grid search strategy&#44; a method for hyperparameters optimization that methodically builds and evaluates a model for each combination of algorithm parameters specified in a grid&#46;</p><p id="par0090" class="elsevierStylePara elsevierViewall">In order to avoid redundant information&#44; prevent the models from becoming unstable in the presence of strong feature dependencies and to improve their interpretability&#44; features with high correlation &#40;&#62;80&#37;&#41; were identified with a Spearman&#8217;s rank-order correlation matrix &#40;<a class="elsevierStyleCrossRef" href="#fig0015">Fig&#46; 3</a>&#41;&#46; From each pair of high correlated features&#44; the one with the larger p-value in the univariate statistical test was excluded from the models&#46; Following this criterion&#44; the extent degrees and the distribution of the opacities in the medium lung field were discarded&#46;</p><elsevierMultimedia ident="fig0015"></elsevierMultimedia><p id="par0095" class="elsevierStylePara elsevierViewall">Three models were developed with different predictive variables&#44; the first one containing the epidemiological &#40;age&#44; sex&#44; institutionalization and comorbidities&#41; and all the above mentioned radiological features&#46; The clinical &#40;symptoms and SatO2&#47;FiO2&#41; and all the above mentioned laboratory parameters were incorporated into the first model to build the second model&#44; and finally the CNN-derived based data were incorporated into the second model to build the third model&#46; A partial under-sampling methodology followed by a synthetic minority over-sampling technique &#40;SMOTE&#41; was used to address the data imbalance problem&#44; very common in Machine Learning environments&#46;<a class="elsevierStyleCrossRef" href="#bib0080"><span class="elsevierStyleSup">16</span></a> Features were standardized accordingly&#46;</p><p id="par0100" class="elsevierStylePara elsevierViewall">As a method for dimensionality reduction and to evaluate the impact of each feature&#44; the variable importance was calculated&#46; This importance is a measure of by how much removing a variable decreases accuracy&#44; and vice versa &#8212; by how much including a variable increases accuracy&#46; The default method to compute variable importance is the mean decrease in impurity &#40;or gini importance&#41; mechanism&#58; At each split in each tree&#44; the improvement in the split-criterion is the importance measure attributed to the splitting variable&#44; and is accumulated over all the trees in the forest separately for each variable&#46; Note that this measure is quite like the R&#94;2 in regression on the training set&#46; If a variable has very little predictive power&#44; removing it may lead to an increase in accuracy due to random noise&#46;</p><p id="par0105" class="elsevierStylePara elsevierViewall">Sensitivity&#44; specificity&#44; PPV&#44; NPV&#44; AUC-ROC and precision-recall curves &#40;AUC-PRC&#41; were obtained for each model&#46; The Youden index was used for the optimal threshold selection of the classification model&#44; by maximizing the highest sensibility and NPV for critically ill &#40;or dead&#41; patients and the highest specificity and PPV for the mild severity &#40;or alive&#41; ones&#46; The optimal thresholds were defined on the training data set&#46; A weighted micro-average statistical approach is used to obtain the values per severity level after threshold optimization of the classification model with the Youden index&#46; A macro-average will compute the metric independently for each class and then take the average &#40;hence treating all classes equally&#41;&#44; whereas a micro-average will aggregate the contributions of all classes to compute the average metric&#44; which is particularly useful when the dataset varies in size&#46; In order to test for a potential overestimation of the diagnostic model performance&#44; the metrics were obtained by evaluating the same thresholds on the internal validation data set&#46; DeLong&#39;s test for two correlated ROC curves<a class="elsevierStyleCrossRef" href="#bib0085"><span class="elsevierStyleSup">17</span></a> was used to compare the performance of the models&#46;</p><p id="par0110" class="elsevierStylePara elsevierViewall">The following Python and Machine Learning libraries were used to perform the data visualization and statistical analysis in the study&#58; Pandas&#44; Numpy&#44; SciPy&#44; Matplotlib and Scikit Learn&#46;</p></span></span><span id="sec0050" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0110">Results</span><span id="sec0055" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0115">Patients</span><p id="par0115" class="elsevierStylePara elsevierViewall">From 445 registered patients&#44; 5 were excluded &#40;1 acute appendicitis&#44; 1 cholangitis&#44; 1 diverticulitis&#44; 1 ictus stoke and 1 cardiac failure&#41;&#46; A total final population of 440 was enrolled in the study&#46;</p></span><span id="sec0060" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0120">Demographics&#44; comorbidities</span><p id="par0120" class="elsevierStylePara elsevierViewall">The median age was 64 years &#40;range 17-100&#41; and 55&#46;9&#37; were male&#46; 79&#37; suffered &#8805;1 comorbidities&#59; the most frequent were hypertension&#44; dyslipidaemia and diabetes &#40;<a class="elsevierStyleCrossRef" href="#tbl0005">Table 1</a>&#41;&#46;</p><elsevierMultimedia ident="tbl0005"></elsevierMultimedia></span><span id="sec0065" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0125">Clinical and laboratory variables&#44; SatO2&#47;FiO2</span><p id="par0125" class="elsevierStylePara elsevierViewall">Upon their arrival to ED the average of days with symptoms was 6&#46;8 &#40;range 0-30&#41; and the most common symptoms were by this order fever and cough&#46; The average oxygen saturation was 93&#46;7&#37; &#40;range 55-100&#37;&#41;&#46; There was loss of &#8805;1 laboratory parameters in 67 patients because they had not been performed &#40;<a class="elsevierStyleCrossRef" href="#tbl0010">Table 2</a>&#41;&#46;</p><elsevierMultimedia ident="tbl0010"></elsevierMultimedia></span><span id="sec0070" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0130">Outcome variables</span><p id="par0130" class="elsevierStylePara elsevierViewall">13&#46;6&#37; patients were discharged at home or hospitalized &#8804; 3 days&#59; 64&#37; patients were hospitalized &#40;4-54 days&#44; average 17 days&#41;&#59; 6&#46;6&#37; required intensive care &#40;2-65 days&#44; average 18 days in ICU&#41; and 15&#46;7&#37; died &#40;0-51 days after admission&#44; average 10 days&#41;&#46;</p></span><span id="sec0075" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0135">Chest X-ray review</span><p id="par0135" class="elsevierStylePara elsevierViewall">The median time between CXR and Real-Time reverse transcription Polymerase Chain Reaction &#40;RT-PCR&#41; was 1 day &#40;range 0-30&#41;&#46; 65&#46;9&#37; of patients with pending RT-PCR result showed suggestive COVID-19 lung involvement on CXR&#44; anticipating the definitive diagnosis&#46; The ExtScoreCXR was 3&#46;3 &#43;&#47;- 3&#46;07 &#40;average &#43;&#47;- SD&#41; &#40;<a class="elsevierStyleCrossRef" href="#tbl0015">Table 3</a>&#41;&#46;</p><elsevierMultimedia ident="tbl0015"></elsevierMultimedia><p id="par0140" class="elsevierStylePara elsevierViewall">From 76 patients initially discharged at home 24&#37; were admitted in a second visit to ED&#46; The first CXR of these patients was normal in 7 and showed very slight or difficult to interpret opacities in 11&#59; in the second visit all presented progression of the lung involvement&#46;</p></span><span id="sec0080" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0140">Computational Imaging &#40;Artificial Intelligence Data&#41;</span><p id="par0145" class="elsevierStylePara elsevierViewall">Probability indices - average &#43;&#47;- standard deviation &#40;range&#41;- for &#8220;consolidation&#8221;&#44; &#8220;lung opacity&#8221; and &#8220;abnormal CXR&#8221; obtained from CXR of the population studied were 0&#44;39 &#43;&#47;-0&#44;19 &#40;0-0&#44;84&#41;&#59; 0&#44;47 &#43;&#47;-0&#44;25 &#40;0-0&#44;98&#41; and 0&#44;98 &#43;&#47;-0&#44;13 &#40;0-1&#41; respectively&#46;</p></span><span id="sec0085" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0145">Univariable analysis&#46; Lung involvement extension in CXR</span><p id="par0150" class="elsevierStylePara elsevierViewall">The lung involvement extent -degrees and score- showed poor correlation with days of symptoms duration &#40;r&#8239;&#61;&#8239;0&#46;198 and r&#8239;&#61;&#8239;0&#46;176&#44; respectively&#44; p-value&#60;0&#46;001&#41;&#44; strong negative correlation with SatO2&#47;FiO2 &#40;r&#61;-0&#46;53 and r&#61;-0&#46;57&#44; respectively&#44; p-value&#60;0&#46;001&#41;&#44; strong-moderate correlation with the severity level &#40;r&#8239;&#61;&#8239;0&#46;536 and r&#8239;&#61;&#8239;0&#46;491&#44; respectively&#44; p-value&#60;0&#46;001&#41;&#44; poor correlation with days of hospitalization &#40;r&#8239;&#61;&#8239;0&#46;240 and r&#8239;&#61;&#8239;0&#46;246&#44; respectively&#44; p-value&#60;0&#46;001&#41;&#44; no significant correlation with ICU stay days&#44; and poor-moderate correlation with mortality &#40;r&#8239;&#61;&#8239;0&#46;277 and r&#8239;&#61;&#8239;0&#46;310&#44; respectively&#44; p-value &#60;0&#46;001&#41;&#46;</p></span><span id="sec0090" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0150">Prognostic prediction models</span><p id="par0155" class="elsevierStylePara elsevierViewall">The SatO2&#47;FiO2 &#40;33&#37;&#41;&#44; the CNN-based index for lung consolidation &#40;13&#37;&#41;&#44; the LDH &#40;12&#37;&#41;&#44; the ExtScoreCXR &#40;9&#37;&#41;&#44; the age &#40;9&#37;&#41;&#44; the lymphocyte count &#40;9&#37;&#41;&#44; the CRP &#40;7&#37;&#41;&#44; the CNN-based index for lung opacities &#40;3&#37;&#41;&#44; the D-dimer level &#40;3&#37;&#41;&#44; and the platelets count &#40;2&#37;&#41; were&#44; in this order&#44; the most important predictors of severity level outcome for the most severe group of patients &#40;<a class="elsevierStyleCrossRef" href="#fig0020">Fig&#46; 4</a>&#41;&#46; The values in parenthesis correspond to the variable importance in the developed model&#46;</p><elsevierMultimedia ident="fig0020"></elsevierMultimedia><p id="par0160" class="elsevierStylePara elsevierViewall">The ROC and the PRC curves of the internal validation performed with an unseen dataset for the severity level prognostic predictive models built with three different combinations of features are shown in <a class="elsevierStyleCrossRef" href="#fig0025">Fig&#46; 5</a>&#46; The curves per severity level are obtained after applying a one-vs-all classification methodology&#46; An improvement of the AUC-ROC and AUC-PRC is observed for both the most and least critically ill patients&#44; as more features are included in the model&#46; In particular&#44; the larger effect is obtained when adding the clinical and laboratory parameters &#40;micro-average AUC-ROC&#8239;&#61;&#8239;0&#46;94&#44; micro-average AUC-PRC&#8239;&#61;&#8239;0&#46;88&#41;&#46; The addition of the CNN-based indices increases the AUC-PRC value of the patients belonging to the extreme severity levels but has the opposite effect on the mid-severity level ones&#44; resulting in a worsening of the predictive metrics &#40;micro-average AUC-ROC&#8239;&#61;&#8239;0&#46;91&#44; micro-average AUC-PRC&#8239;&#61;&#8239;0&#46;82&#41; &#40;<a class="elsevierStyleCrossRef" href="#tbl0020">Table 4</a>&#41;&#46;</p><elsevierMultimedia ident="fig0025"></elsevierMultimedia><elsevierMultimedia ident="tbl0020"></elsevierMultimedia><p id="par0165" class="elsevierStylePara elsevierViewall">Regarding the clinical outcome of mortality&#44; the best model is achieved with a Gradient Boosting classifier with the inclusion of the selected epidemiological&#44; radiological&#44; clinical&#44; and laboratory parameters and the CNN-based indices &#40;AUC-ROC&#8239;&#61;&#8239;0&#46;97&#44; AUC-PRC&#8239;&#61;&#8239;0&#46;83&#41;&#46; The age &#40;54&#37;&#41;&#44; the SatO2&#47;FiO2 &#40;14&#37;&#41;&#44; the lymphocyte count &#40;10&#37;&#41;&#44; the LDH &#40;8&#37;&#41;&#44; the CNN-based index for lung consolidation on CXR &#40;7&#37;&#41;&#44; the platelets count &#40;4&#37;&#41; and the D-dimer level &#40;3&#37;&#41; were&#44; in this order&#44; the most weighted predictors of in-hospital mortality &#40;<a class="elsevierStyleCrossRef" href="#fig0020">Fig&#46; 4</a>&#41;&#46; A decrease in these metrics is observed when the CNN-based indices are removed from the model &#40;AUC-ROC&#8239;&#61;&#8239;0&#46;97&#44; AUC-PRC&#8239;&#61;&#8239;0&#46;78&#41; but an improvement on the PPV and specificity of the model is achieved by means of threshold optimization with the Youden index &#40;<a class="elsevierStyleCrossRef" href="#tbl0020">Table 4</a>&#41;&#46; In this case&#44; the age &#40;43&#37;&#41;&#44; the SatO2&#47;FiO2 &#40;20&#37;&#41;&#44; the CRP &#40;15&#37;&#41;&#44; the LDH &#40;7&#37;&#41;&#44; the ExtScoreCXR &#40;6&#37;&#41;&#44; the lymphocyte count &#40;6&#37;&#41; and the D-dimer level &#40;3&#37;&#41; were&#44; in this order&#44; the most weighted predictors&#46; There were no statistically significant differences in terms of the AUC-ROC between the models with and without CNN-based indices &#40;p-value&#8239;&#61;&#8239;0&#46;315&#41;&#44; suggesting that the addition of the AI parameters does not offer a significant additional improvement on the model performance&#46; <a class="elsevierStyleCrossRef" href="#fig0030">Fig&#46; 6</a> shows the ROC and the PRC curves of the internal validation performed with an unseen dataset for a selection of three classification mortality models built with three different combinations of features&#46;</p><elsevierMultimedia ident="fig0030"></elsevierMultimedia></span></span><span id="sec0095" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0155">Discussion</span><p id="par0170" class="elsevierStylePara elsevierViewall">In this study&#44; the presence and extent of lung involvement on the initial CXR of COVID-19 patients has a prognostic value&#46; In the univariable analysis the ExtScoreCXR showed moderate correlation with the severity level and mortality&#44; and in the first developed multivariable models based on age&#44; gender and radiological features&#44; the ExtScoreCXR was the strongest predictor of severity and the second predictor of in-hospital mortality after age&#46; However&#44; the addition of other parameters usually registered at admission significantly improved the predictive accuracy of the models&#46; These results demonstrate the greatest usefulness of CXR score as a prognostic tool in COVID-19 when considered together in a model with the SatO2&#47;FiO2&#44; the age&#44; the LDH&#44; the lymphocyte count&#44; the CRP&#44; the D-dimer level and the platelets&#46; The distribution and the density of opacities were not strong enough to remain predictors in the definitive models and the indices of CNN-based diagnostic tool did not improve significantly the predictive metrics&#44; probably because the extension was not quantified&#46; On the other hand&#44; despite a careful analysis of the imaging&#44; overlapping of structures&#44; slight or indeterminate opacities and normal CXR are not uncommon &#40;31&#46;8&#37; in our series&#41;&#46; Therefore the integration of the ExtScoreCXR into a prognostic model attempts the safe decision-making&#44; avoiding discharge at home of patients requiring hospital care and unnecessary hospitalizations or CT overuse&#46;</p><p id="par0175" class="elsevierStylePara elsevierViewall">We also confirmed the strong negative correlation between lung involvement extent and SatO2&#47;FiO2&#46; It supports the widely accepted indication of CT pulmonary angiography in case of oxygen desaturation or dyspnea and normal or mild lung involvement on CXR&#44;<a class="elsevierStyleCrossRef" href="#bib0090"><span class="elsevierStyleSup">18</span></a> looking for extended slight lung opacities not visible on CXR or pulmonary thrombosis&#47;embolism&#46;<a class="elsevierStyleCrossRef" href="#bib0095"><span class="elsevierStyleSup">19</span></a> In concordance with this&#44; in both developed prognostic models the SatO2&#47;FiO2 showed to be a strong predictor&#46;</p><p id="par0180" class="elsevierStylePara elsevierViewall">In the literature&#44; COVID-19 CXR opacification rating scores in ED were predictive of risk for hospital admission and intubation in patients aged 21-50<a class="elsevierStyleCrossRef" href="#bib0030"><span class="elsevierStyleSup">6</span></a> and of time to intubation&#44; independent of comorbidities&#46;<a class="elsevierStyleCrossRef" href="#bib0040"><span class="elsevierStyleSup">8</span></a> The extent of lung involvement was also associated to worse outcomes in severe acute respiratory syndrome&#46;<a class="elsevierStyleCrossRefs" href="#bib0100"><span class="elsevierStyleSup">20&#44;21</span></a></p><p id="par0185" class="elsevierStylePara elsevierViewall">The most reported predictors of severe prognosis in patients with COVID-19 included age&#44; sex&#44; features derived from CT&#44; CRP&#44; LDH&#44; and lymphocyte count<a class="elsevierStyleCrossRefs" href="#bib0055"><span class="elsevierStyleSup">11&#44;22</span></a> and the most published predictors of mortality are older age<a class="elsevierStyleCrossRefs" href="#bib0115"><span class="elsevierStyleSup">23&#8211;25</span></a> and D-dimer level&#46;<a class="elsevierStyleCrossRefs" href="#bib0110"><span class="elsevierStyleSup">22&#44;23</span></a> These predictors coincide with most of those we have observed in the multivariable analysis and included in the predictive models&#46;</p><p id="par0190" class="elsevierStylePara elsevierViewall">Days with symptoms&#44; clinical presentation&#44; institutionalization&#44; comorbidities and the rest of CXR features did not show enough predictive power &#40;variable importance &#60;1&#37;&#41; to be included in the models&#46; The number of days with symptoms on arrival of patients to ED was not related to the lung involvement extension&#46; In other series neither a significant difference was identified between the severe and non-severe patients&#44; regarding the median days from symptom onset to hospital admission&#46;<a class="elsevierStyleCrossRef" href="#bib0130"><span class="elsevierStyleSup">26</span></a> Tobacco&#44; comorbidities as obesity&#44; hypertension&#44; diabetes&#44; cardiovascular disease&#44; respiratory diseases&#44; cancer history and the presence of fever&#44; dyspnea&#44; haemoptysis and unconsciousness&#44; were also associated to a worse prognosis in some publications&#44;<a class="elsevierStyleCrossRefs" href="#bib0125"><span class="elsevierStyleSup">25&#44;27&#8211;29</span></a> but not in our study&#46; There is probably a data collection bias from the medical records&#44; especially obesity may be underreported&#46; But apparently&#44; the comorbidities and symptoms have a lower relative predictor weight with respect to the definitive variables of the models&#46; The larger impact of the SatO2&#47;FiO2&#44; the ExtScoreCXR and the laboratory parameters raises the need of performing these tests to all COVID-19 patients with respiratory symptoms or persistent systemic symptoms&#46; This prognostic approach could early identify patients who would benefit from more specific treatment or hospitalization&#46;</p><p id="par0195" class="elsevierStylePara elsevierViewall">The National Early Warning Score 2 &#40;NEWS2&#41;&#44; based on vital signs&#44; is the most used score in ED&#46; Its predictive accuracy in COVID-19 patients is higher than other clinical risk scores&#46;<a class="elsevierStyleCrossRefs" href="#bib0150"><span class="elsevierStyleSup">30&#44;31</span></a> Nevertheless&#44; the models developed in this study exceed this accuracy with an AUC-ROC&#8239;&#61;&#8239;0&#46;94 and an AUC-ROC&#8239;&#61;&#8239;0&#46;97 for severity and mortality respectively&#44; as expected because the addition of other relevant variables&#46; A specific COVID-19 risk score was developed to predict clinical illness at admission with ten variables including the CXR abnormality as predictor&#44; but without extent assessment&#59; it showed an AUC-ROC of 0&#46;88&#46;<a class="elsevierStyleCrossRef" href="#bib0145"><span class="elsevierStyleSup">29</span></a> Another multivariable model including CXR at admission was constructed to predict critical illness in hospitalized COVID-19 patients&#46;<a class="elsevierStyleCrossRef" href="#bib0035"><span class="elsevierStyleSup">7</span></a> The predictors that remained in the model were male gender&#44; obstructive lung disease&#44; symptom duration &#62; 7 days&#44; neutrophil count&#44; CPR&#44; LDH&#44; distribution of lung disease and CXR score&#44; with an AUC-ROC&#8239;&#61;&#8239;0&#46;77&#46; The CPR&#44; the LDH and the lung involvement extension on CXR are also included in our final model but there are no further coincidences in the rest of predictors&#46; This is probably explained by the different model development methodologies including a different feature selection strategy&#44; as they used a univariable statistical test and we based our selection on the correlation between parameters and with respect to the clinical outcome&#46; Other discrepancies include the data pre-processing steps&#44; as we included a combination of some over- and under-sampling techniques as well as data standardization&#59; and the consideration of different model architectures&#44; as they employed a multivariable logistic regression&#44; which relies on transformations for non-linear features&#46; In order to overcome this issue&#44; we tested three different model architectures&#58; Support Vector Machine&#44; Random Forest and Gradient Boosting&#44; which can handle non-linear features as well as their interactions&#44; and perform well in a large feature space&#46;</p><p id="par0200" class="elsevierStylePara elsevierViewall">As potential sources of bias&#44; the severity level is a decision-based clinical outcome&#44; unlike mortality&#46; In order to reduce this bias we grouped at level 0 not only home discharge from the ED but also hospitalization &#8804; 3 days&#46; In addition&#44; the follow-up of at least 2 months included patients who returned to the hospital&#46; In these cases all the variables collected were also those obtained from the first visit to the ED but the event considered as outcome was the most severe&#46; In fact&#44; the proportion of the most severe patients &#40;22&#37;&#41; was within the range published in longer series &#40;15-36&#37;&#41;&#46;<a class="elsevierStyleCrossRefs" href="#bib0160"><span class="elsevierStyleSup">32&#44;33</span></a></p><p id="par0205" class="elsevierStylePara elsevierViewall">Regarding the proposed method to quantify the extent of lung involvement &#40;ExtScoreCXR&#41;&#44; we have not analyzed interobserver agreement&#46; On the other hand&#44; a good interobserver agreement was demonstrated with the use of Brixia&#44; a more complex score designed for COVID-19 patients&#44;<a class="elsevierStyleCrossRef" href="#bib0045"><span class="elsevierStyleSup">9</span></a> and coincidentally we have used the same score as other authors&#44; who have recently published its good correlation with Brixia score&#46;<a class="elsevierStyleCrossRef" href="#bib0075"><span class="elsevierStyleSup">15</span></a></p><p id="par0210" class="elsevierStylePara elsevierViewall">The internal validation was performed with 88 cases&#46; However&#44; it has been reported that a minimum sample size of 100 is recommended in order to achieve a robust validation&#46;<a class="elsevierStyleCrossRef" href="#bib0170"><span class="elsevierStyleSup">34</span></a> An external validation with cases from other hospitals is desirable to assess the generalizability and the potential use of the developed models in daily clinical practice&#46;</p><p id="par0215" class="elsevierStylePara elsevierViewall">In conclusion&#44; the developed multivariable prognosis prediction models showed a high predictive accuracy that could allow triage of symptomatic COVID-19 patients at ED to improve the decision-making&#46; The application to estimate the severity level and the in-hospital mortality is available on <a href="http://upv.datahub.egi.eu:30054/hulafecovid19models">http&#58;&#47;&#47;upv&#46;datahub&#46;egi&#46;eu&#58;30054&#47;hulafecovid19models</a>&#46; It should be validated at different ED for both COVID-19 and other viral infections with similar behaviour&#46;</p></span><span id="sec0100" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0160">Authors contributions</span><p id="par0220" class="elsevierStylePara elsevierViewall"><ul class="elsevierStyleList" id="lis0010"><li class="elsevierStyleListItem" id="lsti0025"><span class="elsevierStyleLabel">1</span><p id="par0225" class="elsevierStylePara elsevierViewall">Guarantor of integrity of the entire study&#58; L&#46;M&#46;B&#46;</p></li><li class="elsevierStyleListItem" id="lsti0030"><span class="elsevierStyleLabel">2</span><p id="par0230" class="elsevierStylePara elsevierViewall">Study concepts and design&#58; P&#46;C&#46;B&#46;&#44; L&#46;M&#46;B&#46;&#44; L&#46;C&#46;A&#46;</p></li><li class="elsevierStyleListItem" id="lsti0035"><span class="elsevierStyleLabel">3</span><p id="par0235" class="elsevierStylePara elsevierViewall">Literature research&#58; P&#46;C&#46;B&#46;&#44; L&#46;M&#46;B&#46;</p></li><li class="elsevierStyleListItem" id="lsti0040"><span class="elsevierStyleLabel">4</span><p id="par0240" class="elsevierStylePara elsevierViewall">Clinical studies&#58; P&#46;C&#46;B&#46;&#44; C&#46;F&#46;E&#46;&#44; A&#46;C&#46;O&#46;&#44; C&#46;F&#46; M&#46;N&#46;&#44; L&#46;T&#46;O&#46;</p></li><li class="elsevierStyleListItem" id="lsti0045"><span class="elsevierStyleLabel">5</span><p id="par0245" class="elsevierStylePara elsevierViewall">Data analysis&#58; L&#46;C&#46;A&#46;</p></li><li class="elsevierStyleListItem" id="lsti0050"><span class="elsevierStyleLabel">6</span><p id="par0250" class="elsevierStylePara elsevierViewall">Statistical analysis&#58; L&#46;C&#46;A&#46;</p></li><li class="elsevierStyleListItem" id="lsti0041"><span class="elsevierStyleLabel">7</span><p id="par0241" class="elsevierStylePara elsevierViewall">Bibliographic search&#58; P&#46;C&#46;B&#46;&#44; L&#46;C&#46;A&#46;</p></li><li class="elsevierStyleListItem" id="lsti0055"><span class="elsevierStyleLabel">8</span><p id="par0255" class="elsevierStylePara elsevierViewall">Manuscript preparation&#58; Pilar Calvillo-Batll&#233;s&#44; Leonor Cerd&#225;-Alberich</p></li><li class="elsevierStyleListItem" id="lsti0060"><span class="elsevierStyleLabel">9</span><p id="par0260" class="elsevierStylePara elsevierViewall">Manuscript editing Pilar Calvillo-Batll&#233;s&#44; Leonor Cerd&#225;-Alberich&#44; Luis Mart&#237;-Bonmat&#237;&#46;</p></li><li class="elsevierStyleListItem" id="lsti0065"><span class="elsevierStyleLabel">10</span><p id="par0265" class="elsevierStylePara elsevierViewall">Review and approval of the final version&#58; all authors&#46;</p></li></ul></p></span><span id="sec0105" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0165">Conflicts of interest</span><p id="par0270" class="elsevierStylePara elsevierViewall">The authors declare that they have no conflicts of interest&#46;</p></span></span>"
    "textoCompletoSecciones" => array:1 [
      "secciones" => array:12 [
        0 => array:3 [
          "identificador" => "xres1726696"
          "titulo" => "Abstract"
          "secciones" => array:4 [
            0 => array:2 [
              "identificador" => "abst0005"
              "titulo" => "Objectives"
            ]
            1 => array:2 [
              "identificador" => "abst0010"
              "titulo" => "Methods"
            ]
            2 => array:2 [
              "identificador" => "abst0015"
              "titulo" => "Results"
            ]
            3 => array:2 [
              "identificador" => "abst0020"
              "titulo" => "Conclusion"
            ]
          ]
        ]
        1 => array:2 [
          "identificador" => "xpalclavsec1524915"
          "titulo" => "Keywords"
        ]
        2 => array:3 [
          "identificador" => "xres1726695"
          "titulo" => "Resumen"
          "secciones" => array:4 [
            0 => array:2 [
              "identificador" => "abst0025"
              "titulo" => "Objetivos"
            ]
            1 => array:2 [
              "identificador" => "abst0030"
              "titulo" => "M&#233;todos"
            ]
            2 => array:2 [
              "identificador" => "abst0035"
              "titulo" => "Resultados"
            ]
            3 => array:2 [
              "identificador" => "abst0040"
              "titulo" => "Conclusi&#243;n"
            ]
          ]
        ]
        3 => array:2 [
          "identificador" => "xpalclavsec1524914"
          "titulo" => "Palabras clave"
        ]
        4 => array:2 [
          "identificador" => "sec0005"
          "titulo" => "Introduction"
        ]
        5 => array:3 [
          "identificador" => "sec0010"
          "titulo" => "Material and methods"
          "secciones" => array:7 [
            0 => array:2 [
              "identificador" => "sec0015"
              "titulo" => "Patients"
            ]
            1 => array:2 [
              "identificador" => "sec0020"
              "titulo" => "Chest X-ray review"
            ]
            2 => array:2 [
              "identificador" => "sec0025"
              "titulo" => "Demographics&#44; clinical and laboratory variables collected on the first visit to ED"
            ]
            3 => array:2 [
              "identificador" => "sec0030"
              "titulo" => "Computational Imaging &#40;Artificial Intelligence Data&#41;"
            ]
            4 => array:2 [
              "identificador" => "sec0035"
              "titulo" => "Outcome variables"
            ]
            5 => array:2 [
              "identificador" => "sec0040"
              "titulo" => "Univariable analysis"
            ]
            6 => array:2 [
              "identificador" => "sec0045"
              "titulo" => "Prognostic predictive models"
            ]
          ]
        ]
        6 => array:3 [
          "identificador" => "sec0050"
          "titulo" => "Results"
          "secciones" => array:8 [
            0 => array:2 [
              "identificador" => "sec0055"
              "titulo" => "Patients"
            ]
            1 => array:2 [
              "identificador" => "sec0060"
              "titulo" => "Demographics&#44; comorbidities"
            ]
            2 => array:2 [
              "identificador" => "sec0065"
              "titulo" => "Clinical and laboratory variables&#44; SatO2&#47;FiO2"
            ]
            3 => array:2 [
              "identificador" => "sec0070"
              "titulo" => "Outcome variables"
            ]
            4 => array:2 [
              "identificador" => "sec0075"
              "titulo" => "Chest X-ray review"
            ]
            5 => array:2 [
              "identificador" => "sec0080"
              "titulo" => "Computational Imaging &#40;Artificial Intelligence Data&#41;"
            ]
            6 => array:2 [
              "identificador" => "sec0085"
              "titulo" => "Univariable analysis&#46; Lung involvement extension in CXR"
            ]
            7 => array:2 [
              "identificador" => "sec0090"
              "titulo" => "Prognostic prediction models"
            ]
          ]
        ]
        7 => array:2 [
          "identificador" => "sec0095"
          "titulo" => "Discussion"
        ]
        8 => array:2 [
          "identificador" => "sec0100"
          "titulo" => "Authors contributions"
        ]
        9 => array:2 [
          "identificador" => "sec0105"
          "titulo" => "Conflicts of interest"
        ]
        10 => array:2 [
          "identificador" => "xack609173"
          "titulo" => "Acknowledgments"
        ]
        11 => array:1 [
          "titulo" => "References"
        ]
      ]
    ]
    "pdfFichero" => "main.pdf"
    "tienePdf" => true
    "fechaRecibido" => "2021-03-27"
    "fechaAceptado" => "2021-09-15"
    "PalabrasClave" => array:2 [
      "en" => array:1 [
        0 => array:4 [
          "clase" => "keyword"
          "titulo" => "Keywords"
          "identificador" => "xpalclavsec1524915"
          "palabras" => array:6 [
            0 => "COVID-19"
            1 => "Chest X-Ray"
            2 => "Prognosis"
            3 => "Mortality"
            4 => "Predictive models"
            5 => "Artificial intelligence"
          ]
        ]
      ]
      "es" => array:1 [
        0 => array:4 [
          "clase" => "keyword"
          "titulo" => "Palabras clave"
          "identificador" => "xpalclavsec1524914"
          "palabras" => array:6 [
            0 => "COVID-19"
            1 => "Radiograf&#237;a tor&#225;cica"
            2 => "Pron&#243;stico"
            3 => "Mortalidad"
            4 => "Modelos predictivos"
            5 => "Inteligencia artificial"
          ]
        ]
      ]
    ]
    "tieneResumen" => true
    "resumen" => array:2 [
      "en" => array:3 [
        "titulo" => "Abstract"
        "resumen" => "<span id="abst0005" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0010">Objectives</span><p id="spar0055" class="elsevierStyleSimplePara elsevierViewall">To develop prognosis prediction models for COVID-19 patients attending an emergency department &#40;ED&#41; based on initial chest X-ray &#40;CXR&#41;&#44; demographics&#44; clinical and laboratory parameters&#46;</p></span> <span id="abst0010" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0015">Methods</span><p id="spar0060" class="elsevierStyleSimplePara elsevierViewall">All symptomatic confirmed COVID-19 patients admitted to our hospital ED between February 24th and April 24th 2020 were recruited&#46; CXR features&#44; clinical and laboratory variables and CXR abnormality indices extracted by a convolutional neural network &#40;CNN&#41; diagnostic tool were considered potential predictors on this first visit&#46; The most serious individual outcome defined the three severity level&#58; 0&#41; home discharge or hospitalization &#8804; 3 days&#44; 1&#41; hospital stay &#62;3 days and 2&#41; intensive care requirement or death&#46; Severity and in-hospital mortality multivariable prediction models were developed and internally validated&#46; The Youden index was used for the optimal threshold selection of the classification model&#46;</p></span> <span id="abst0015" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0020">Results</span><p id="spar0065" class="elsevierStyleSimplePara elsevierViewall">A total of 440 patients were enrolled &#40;median 64 years&#59; 55&#46;9&#37; male&#41;&#59; 13&#46;6&#37; patients were discharged&#44; 64&#37; hospitalized&#44; 6&#46;6&#37; required intensive care and 15&#46;7&#37; died&#46; The severity prediction model included oxygen saturation&#47;inspired oxygen fraction &#40;SatO2&#47;FiO2&#41;&#44; age&#44; C-reactive protein &#40;CRP&#41;&#44; lymphocyte count&#44; extent score of lung involvement on CXR &#40;ExtScoreCXR&#41;&#44; lactate dehydrogenase &#40;LDH&#41;&#44; D-dimer level and platelets count&#44; with AUC-ROC &#61; 0&#46;94 and AUC-PRC &#61; 0&#46;88&#46; The mortality prediction model included age&#44; SatO2&#47;FiO2&#44; CRP&#44; LDH&#44; CXR extent score&#44; lymphocyte count and D-dimer level&#44; with AUC-ROC &#61; 0&#46;97 and AUC-PRC &#61; 0&#46;78&#46; The addition of CXR CNN-based indices did not improve significantly the predictive metrics&#46;</p></span> <span id="abst0020" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0025">Conclusion</span><p id="spar0070" class="elsevierStyleSimplePara elsevierViewall">The developed and internally validated severity and mortality prediction models could be useful as triage tools in ED for patients with COVID-19 or other virus infections with similar behaviour&#46;</p></span>"
        "secciones" => array:4 [
          0 => array:2 [
            "identificador" => "abst0005"
            "titulo" => "Objectives"
          ]
          1 => array:2 [
            "identificador" => "abst0010"
            "titulo" => "Methods"
          ]
          2 => array:2 [
            "identificador" => "abst0015"
            "titulo" => "Results"
          ]
          3 => array:2 [
            "identificador" => "abst0020"
            "titulo" => "Conclusion"
          ]
        ]
      ]
      "es" => array:3 [
        "titulo" => "Resumen"
        "resumen" => "<span id="abst0025" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0035">Objetivos</span><p id="spar0075" class="elsevierStyleSimplePara elsevierViewall">Desarrollar modelos de predicci&#243;n de pron&#243;stico para pacientes con COVID-19 que acuden a urgencias&#44; basados en la radiograf&#237;a de t&#243;rax inicial &#40;RXT&#41;&#44; par&#225;metros demogr&#225;ficos&#44; cl&#237;nicos y de laboratorio&#46;</p></span> <span id="abst0030" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0040">M&#233;todos</span><p id="spar0080" class="elsevierStyleSimplePara elsevierViewall">Se reclutaron todos los pacientes sintom&#225;ticos con COVID-19 confirmada&#44; que ingresaron en urgencias de nuestro hospital entre el 24 de febrero y el 24 de abril de 2020&#46; Los par&#225;metros de la RXT&#44; las variables cl&#237;nicas y de laboratorio y los &#237;ndices de hallazgos en RXT extra&#237;dos por una herramienta diagn&#243;stica de inteligencia artificial en esta primera visita se consideraron potenciales predictores&#46; El desenlace individual m&#225;s grave defini&#243; los tres niveles de gravedad&#58; 0&#41; alta domiciliaria u hospitalizaci&#243;n de 3 d&#237;as o inferior&#44; 1&#41; hospitalizaci&#243;n m&#225;s de 3 d&#237;as y 2&#41; necesidad de cuidados intensivos o muerte&#46; Se desarrollaron y validaron internamente modelos de predicci&#243;n multivariable de gravedad y mortalidad hospitalaria&#46; El &#237;ndice de Youden se utiliz&#243; para la selecci&#243;n del umbral &#243;ptimo del modelo de clasificaci&#243;n&#46;</p></span> <span id="abst0035" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0045">Resultados</span><p id="spar0085" class="elsevierStyleSimplePara elsevierViewall">Se registraron 440 pacientes &#40;mediana de 64 a&#241;os&#59; 55&#44;9&#37; hombres&#41;&#59; el 13&#44;6&#37; de los pacientes fueron dados de alta&#44; el 64&#37; hospitalizo m&#225;s de 3 d&#237;as&#44; el 6&#44;6&#37; requiri&#243; cuidados intensivos y un 15&#44;7&#37; falleci&#243;&#46; El modelo de predicci&#243;n de gravedad incluy&#243; saturaci&#243;n de ox&#237;geno&#47;fracci&#243;n de ox&#237;geno inspirado &#40;SatO<span class="elsevierStyleInf">2</span>&#47;FiO<span class="elsevierStyleInf">2</span>&#41;&#44; edad&#44; prote&#237;na C reactiva &#40;PCR&#41;&#44; linfocitos&#44; puntuaci&#243;n de la extensi&#243;n de la afectaci&#243;n pulmonar en la RXT &#40;ExtScoreRXT&#41;&#44; lactato deshidrogenasa &#40;LDH&#41;&#44; d&#237;mero D y plaquetas&#44; con AUC-ROC &#61; 0&#44;94 y AUC-PRC &#61; 0&#44;88&#46; El modelo de predicci&#243;n de mortalidad incluy&#243; edad&#44; SatO<span class="elsevierStyleInf">2</span>&#47;FiO<span class="elsevierStyleInf">2</span>&#44; PCR&#44; LDH&#44; ExtScoreRXT&#44; linfocitos y d&#237;mero D&#44; con AUC-ROC &#61; 0&#44;97 y AUC-PRC &#61; 0&#44;78&#46; La adici&#243;n de &#237;ndices radiol&#243;gicos obtenidos por inteligencia artificial no mejor&#243; significativamente las m&#233;tricas predictivas&#46;</p></span> <span id="abst0040" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0050">Conclusi&#243;n</span><p id="spar0090" class="elsevierStyleSimplePara elsevierViewall">Los modelos de predicci&#243;n de pron&#243;stico desarrollados podr&#237;an ser &#250;tiles para clasificar en urgencias a los pacientes con COVID-19 u otras infecciones v&#237;ricas con comportamiento similar&#46;</p></span>"
        "secciones" => array:4 [
          0 => array:2 [
            "identificador" => "abst0025"
            "titulo" => "Objetivos"
          ]
          1 => array:2 [
            "identificador" => "abst0030"
            "titulo" => "M&#233;todos"
          ]
          2 => array:2 [
            "identificador" => "abst0035"
            "titulo" => "Resultados"
          ]
          3 => array:2 [
            "identificador" => "abst0040"
            "titulo" => "Conclusi&#243;n"
          ]
        ]
      ]
    ]
    "NotaPie" => array:1 [
      0 => array:2 [
        "etiqueta" => "&#9734;"
        "nota" => "<p class="elsevierStyleNotepara" id="npar0005">Please cite this article as&#58; Calvillo-Batll&#233;s P&#44; Cerd&#225;-Alberich L&#44; Fonfr&#237;a-Esparcia C&#44; Carreres-Ortega A&#44; Mu&#241;oz-N&#250;&#241;ez CF&#44; Trilles-Olaso L&#44; et al&#46; Elaboraci&#243;n de modelos predictivos de la gravedad y la mortalidad en pacientes con COVID-19 que acuden al servicio de urgencias&#44; incluida la radiograf&#237;a tor&#225;cica&#46; Radiolog&#237;a&#46; 2022&#59;64&#58;214&#8211;227&#46;</p>"
      ]
    ]
    "apendice" => array:1 [
      0 => array:1 [
        "seccion" => array:1 [
          0 => array:4 [
            "apendice" => "<p id="par0285" class="elsevierStylePara elsevierViewall">The following is Supplementary data to this article&#58;<elsevierMultimedia ident="upi0005"></elsevierMultimedia></p>"
            "etiqueta" => "Appendix A"
            "titulo" => "Supplementary data"
            "identificador" => "sec0115"
          ]
        ]
      ]
    ]
    "multimedia" => array:11 [
      0 => array:8 [
        "identificador" => "fig0005"
        "etiqueta" => "Figure 1"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr1.jpeg"
            "Alto" => 2364
            "Ancho" => 3340
            "Tamanyo" => 420352
          ]
        ]
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0005"
            "detalle" => "Figure "
            "rol" => "short"
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0005" class="elsevierStyleSimplePara elsevierViewall">Flowchart of the study&#46;</p>"
        ]
      ]
      1 => array:8 [
        "identificador" => "fig0010"
        "etiqueta" => "Figure 2"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr2.jpeg"
            "Alto" => 2050
            "Ancho" => 3340
            "Tamanyo" => 600514
          ]
        ]
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0010"
            "detalle" => "Figure "
            "rol" => "short"
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0010" class="elsevierStyleSimplePara elsevierViewall">Chest X-ray features&#46; Up&#58; examples of distribution&#44; density of opacities and extent score&#46; Down &#40;the same CXR&#41;&#58; Division of lung fields&#46; Upper fields &#40;suprahillar area&#41; limited by the line that passes under the aortic arch&#59; medium fields &#40;hilar area&#41; and inferior fields &#40;infrahilar area&#41; separated by the line that divides the rest of the lungs into two halves &#40;frequently this line crosses the bifurcation of the right inferior lobar artery&#41;&#46; <span class="elsevierStyleBold">A1</span>&#58; Unilateral central and peripheral low-density opacities &#40;arrow&#41;&#44; without predominance&#46; <span class="elsevierStyleBold">A2&#58;</span> Medium and lower right fields involved &#8804; 50&#37;&#59; ExtScoreCXR&#8239;&#61;&#8239;2&#46; <span class="elsevierStyleBold">B1</span>&#58; Central right low-density opacity &#40;arrow&#41; and peripheral left consolidation &#40;larger arrows&#41;&#46; Peripheral predominance&#46; <span class="elsevierStyleBold">B2</span>&#58; Medium right and left fields with &#8804;50&#37; of involvement and upper left field with &#62;50&#37; of involvement&#59; ExtScoreCXR&#8239;&#61;&#8239;4&#46; <span class="elsevierStyleBold">C1</span>&#58; Bilateral low-density opacities &#40;arrows&#41; and consolidations &#40;larger arrows&#41; without predominance&#46; <span class="elsevierStyleBold">C2</span>&#58; Upper fields and lower left field with &#8804;50&#37;&#44; medium fields and right lower right field with &#62;50&#37; of involvement&#59; ExtScoreCXR&#8239;&#61;&#8239;9&#46;</p>"
        ]
      ]
      2 => array:8 [
        "identificador" => "fig0015"
        "etiqueta" => "Figure 3"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr3.jpeg"
            "Alto" => 2588
            "Ancho" => 2917
            "Tamanyo" => 403033
          ]
        ]
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0015"
            "detalle" => "Figure "
            "rol" => "short"
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0015" class="elsevierStyleSimplePara elsevierViewall">Spearman&#8217;s rank-order correlation matrix for the epidemiological and radiological features&#46;</p>"
        ]
      ]
      3 => array:8 [
        "identificador" => "fig0020"
        "etiqueta" => "Figure 4"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr4.jpeg"
            "Alto" => 3108
            "Ancho" => 2924
            "Tamanyo" => 393003
          ]
        ]
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0020"
            "detalle" => "Figure "
            "rol" => "short"
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0020" class="elsevierStyleSimplePara elsevierViewall">Importance of model predictors obtained for the <span class="elsevierStyleUnderline">severity level</span> &#40;up&#41;&#58; oxygen saturation&#47;inspired oxygen fraction &#40;SatO2&#47;FiO2&#41; &#40;33&#37;&#41;&#44; convolutional neural network &#40;CNN&#41;-based index for lung consolidation on chest X-ray &#40;CXR&#41; &#40;13&#37;&#41;&#44; lactate dehydrogenase &#40;LDH&#41; &#40;12&#37;&#41;&#44; extent score of lung involvement on CXR &#40;ExtScoreCXR&#41; &#40;9&#37;&#41;&#44; age &#40;9&#37;&#41;&#44; lymphocyte count &#40;9&#37;&#41;&#44; C-reactive protein &#40;CRP&#41; &#40;7&#37;&#41;&#44; CNN-based index for lung opacities on CXR &#40;3&#37;&#41;&#44; D-dimer level &#40;3&#37;&#41; and platelets count &#40;2&#37;&#41;&#59; and <span class="elsevierStyleUnderline">mortality</span> &#40;down&#41;&#58; age &#40;54&#37;&#41;&#44; SatO2&#47;FiO2 &#40;14&#37;&#41;&#44; the lymphocyte count &#40;10&#37;&#41;&#44; LDH &#40;8&#37;&#41;&#44; CNN-based index for lung consolidation on CXR &#40;7&#37;&#41;&#44; platelets count &#40;4&#37;&#41; and D-dimer level &#40;3&#37;&#41;&#46; Those with an importance of less than 0&#46;01 are excluded from the model&#46;</p>"
        ]
      ]
      4 => array:8 [
        "identificador" => "fig0025"
        "etiqueta" => "Figure 5"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr5.jpeg"
            "Alto" => 1760
            "Ancho" => 3333
            "Tamanyo" => 678183
          ]
        ]
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0025"
            "detalle" => "Figure "
            "rol" => "short"
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0025" class="elsevierStyleSimplePara elsevierViewall">The ROC &#40;up&#41; and the PRC &#40;down&#41; curves of the internal validation performed with an unseen dataset for the severity predictive models built with three different combinations of parameters&#46; &#40;A&#58; epidemiological and radiological parameters&#44; B&#58; epidemiological&#44; radiological&#44; clinical and laboratory parameters&#44; C&#58; epidemiological&#44; radiological&#44; clinical&#44; laboratory and CNN-based parameters&#41;&#46; The curves per severity level are obtained with a one-vs-all classification methodology&#58; home discharge or hospitalization &#8804; 3 days &#40;level&#47;class 0&#44; in light blue&#41;&#44; need for hospital stay &#62;3 days &#40;level&#47;class 1&#44; in orange&#41;&#44; need for ICU stay or death due to COVID-19 &#40;level&#47;class 2&#44; in blue&#41;&#46; The dashed lines represent the micro-average &#40;magenta&#41; and macro-average &#40;dark blue&#41; curve statistics which take into account the single level contributions&#46; The corresponding values of AUC are shown&#46; Precision&#8239;&#61;&#8239;true positive &#47; &#40;true positive&#8239;&#43;&#8239;false positive&#41;&#46; Recall &#40;sensitivity&#41;&#8239;&#61;&#8239;true positive &#47; &#40;true positive&#8239;&#43;&#8239;false negative&#41;&#46;</p>"
        ]
      ]
      5 => array:8 [
        "identificador" => "fig0030"
        "etiqueta" => "Figure 6"
        "tipo" => "MULTIMEDIAFIGURA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "figura" => array:1 [
          0 => array:4 [
            "imagen" => "gr6.jpeg"
            "Alto" => 1753
            "Ancho" => 3340
            "Tamanyo" => 500608
          ]
        ]
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0030"
            "detalle" => "Figure "
            "rol" => "short"
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0030" class="elsevierStyleSimplePara elsevierViewall">The ROC &#40;up&#41; and the PRC &#40;down&#41; curves of the internal validation performed with an unseen dataset for the in-hospital mortality predictive models &#40;SVM&#58; Support Vector Machine &#40;blue&#41;&#44; RF&#58; Random Forest &#40;green&#41;&#44; GB&#58; Gradient Boosting&#41; &#40;orange&#41; built with three different combinations of parameters &#40;A&#58; epidemiological and radiological parameters&#44; B&#58; epidemiological&#44; radiological&#44; clinical and laboratory parameters&#44; C&#58; epidemiological&#44; radiological&#44; clinical&#44; laboratory and CNN-based parameters&#41;&#46; The corresponding values of AUC are shown&#46;</p>"
        ]
      ]
      6 => array:8 [
        "identificador" => "tbl0005"
        "etiqueta" => "Table 1"
        "tipo" => "MULTIMEDIATABLA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0035"
            "detalle" => "Table "
            "rol" => "short"
          ]
        ]
        "tabla" => array:1 [
          "tablatextoimagen" => array:3 [
            0 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " colspan="3" align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">DEMOGRAPHIC INFORMATION</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " colspan="2" align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Age&#42; Median &#40;interquartile range&#41;&#44; &#40;range&#41;&#44; years</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">64 &#40;51-79&#41;&#44; &#40;17-100&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead rowgroup " rowspan="2" align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Sex&#42; No&#46; &#40;&#37; of 440&#41;</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Male&#42;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">246 &#40;55&#44;9&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Female&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">194 &#40;44&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929985.png"
              ]
            ]
            1 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">COMORBIDITIES&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">No&#46; &#40;&#37; of 440&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Hypertension&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">191 &#40;43&#44;4&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Dislypemia&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">125 &#40;28&#44;4&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Diabetes&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">93 &#40;21&#44;1&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Institutionalization&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">75 &#40;17&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Cardiovascular disease&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">56 &#40;12&#44;7&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Immunosuppression&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">46 &#40;10&#44;5&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Corticotherapy and other immunosuppressors&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">16 &#40;3&#44;6&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Advanced chronic kidney disease&#47;Dialysis&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">13 &#40;2&#44;9&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Hematological neoplasm &#47; disease&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">10 &#40;2&#44;3&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Solid organ trasplant&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">8 &#40;1&#44;8&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Human immunodeficiency virus&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">1 &#40;0&#44;2&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Chronic kidney disease &#40;total&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">43 &#40;9&#44;8&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Obesity&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">42 &#40;9&#44;5&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Cerebrovascular disease&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">36 &#40;8&#44;2&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Neoplasm&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">32 &#40;7&#44;3&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Asthma&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">25 &#40;5&#44;7&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Dementia&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">19 &#40;4&#44;3&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Current smoker&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">16 &#40;3&#44;6&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Obstructive sleep apnea&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">16 &#40;3&#44;6&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Ex-smoker&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">15 &#40;3&#44;4&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Hypothyroidism&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">13 &#40;2&#44;9&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Atrial fibrillation&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">13 &#40;2&#44;9&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Chronic obstructive pulmonary disease&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">9 &#40;2&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929987.png"
              ]
            ]
            2 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">NUMBER OF COMORBIDITIES&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">No&#46; &#40;&#37; of 440&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">None&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">92 &#40;20&#44;9&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">1&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">87 &#40;19&#44;8&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">2&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">68 &#40;15&#44;4&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">3&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">54 &#40;12&#44;3&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">&#8805; 4 &#40;4-8&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">139 &#40;31&#44;5&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929996.png"
              ]
            ]
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0035" class="elsevierStyleSimplePara elsevierViewall"><span class="elsevierStyleBold">Characteristics of COVID-19 patients&#46;</span> Demographic variables and comorbidities investigated as potential predictors&#46; &#42; Predictors in the final prognostic prediction models&#46;</p>"
        ]
      ]
      7 => array:8 [
        "identificador" => "tbl0010"
        "etiqueta" => "Table 2"
        "tipo" => "MULTIMEDIATABLA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0040"
            "detalle" => "Table "
            "rol" => "short"
          ]
        ]
        "tabla" => array:1 [
          "tablatextoimagen" => array:4 [
            0 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">INTERVAL SINCE SYMPTOMS ONSET&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Average &#43;&#47;- sd &#40;range&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t"><span class="elsevierStyleItalic">Days</span>&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">6&#44;8 &#43;&#47;- 4&#44;5 &#40;0-30&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929990.png"
              ]
            ]
            1 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">SYMPTOMS Total No&#46; 441&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">No&#46; &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Fever&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">361 &#40;82&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Cough&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">287 &#40;65&#44;2&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Dyspnea&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">178 &#40;40&#44;4&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">General dyscomphort&#47;Asthenia&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">171 &#40;38&#44;9&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Gastrointestinal symptoms&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">103 &#40;23&#44;4&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Myalgias&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">72 &#40;16&#44;4&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Headache&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">47 &#40;10&#44;7&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Hyposmia&#47;Dysgeusia&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">32 &#40;7&#44;3&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929991.png"
              ]
            ]
            2 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">OXYGEN SATURATION&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Average &#43;&#47;- sd &#40;range&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Sat 02 &#40;air room&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">93&#44;7 &#43;&#47;- 5&#44;6 &#40;55-100&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Sat 02 &#47;Fi O2&#42;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">443&#44;5 &#43;&#47;-34&#44;4&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929995.png"
              ]
            ]
            3 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">LABORATORY DATA&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Average&#47; Min &#47; 25&#37; &#47; Median &#47; 75&#37; &#47; Max&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Lactic dehydrogenase &#40;U&#47;l&#41; &#42;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">306 &#47; 16 &#47; 218&#44;2 &#47; 265&#44;5 &#47; 349&#44;7 &#47; 2146&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">C reactive protein &#40;mg&#47;l&#41; &#42;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">81 &#47; 0&#44;3 &#47; 15&#44;5 &#47; 44&#44;6 &#47; 117&#44;2 &#47; 655&#44;5&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Lymphocytes count &#40;x103&#181;&#47;l&#41; &#42;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">1&#44;2 &#47; 0&#44;06 &#47; 0&#44;7 &#47; 1 &#47; 1&#44;4 &#47;12&#44;3&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Platelets count &#40;x103&#181;&#47;l&#41; &#42;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">203&#44;7 &#47; 32 &#47; 150 &#47; 193 &#47; 242 &#47; 716&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Dimer D &#40;ng&#47;l&#41; &#42;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">1390 &#47; 83 &#47; 350 &#47; 608 &#47; 1015 &#47; 38282&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929989.png"
              ]
            ]
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0040" class="elsevierStyleSimplePara elsevierViewall"><span class="elsevierStyleBold">Clinical presentation of COVID-19 patients&#46;</span> Clinical and laboratory variables investigated as potential predictors&#46; Gastrointestinal symptoms&#58; diarrhea&#44; vomiting or abdominal pain&#46; SatO2&#47;FiO2&#58; Peripheral oxygen saturation &#47;inspiratory oxygen fraction &#40;room air or oxygen therapy&#41;&#46; &#42; Predictors in the definitive prognostic prediction models&#46;</p>"
        ]
      ]
      8 => array:8 [
        "identificador" => "tbl0015"
        "etiqueta" => "Table 3"
        "tipo" => "MULTIMEDIATABLA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0045"
            "detalle" => "Table "
            "rol" => "short"
          ]
        ]
        "tabla" => array:1 [
          "tablatextoimagen" => array:4 [
            0 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">PRESENCE AND DENSITY OF LUNG OPACITIES&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">No&#46; &#40;&#37;&#41; Total 440&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">No lung opacities &#40;&#43;&#47;- other findings&#41; - level 0-&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">86 &#40;19&#44;5&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Low-density opacity&#40;ies&#41; - level 1 -&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">254 &#40;57&#44;7&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Consolidation&#47;s &#43;&#47;- low-density opacity&#40;ies&#41; -level 2-&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">100 &#40;22&#44;7&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929992.png"
              ]
            ]
            1 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">DISTRIBUTION&#47;LOCATION OF LUNG OPACITIES&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">No&#46; &#40;&#37;&#41; Total 354&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Bilateral&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">212 &#40;59&#44;9&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Unilateral&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">142 &#40;39&#44;8&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Peripheral &#40;only or predominantly&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">182 &#40;51&#44;1&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Peripheral and central &#40;without predominance&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">116 &#40;32&#44;5&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Central &#40;only or predominantly&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">56 &#40;15&#44;7&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Lower fields&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">290 &#40;81&#44;4&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Medium fields&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">259 &#40;72&#44;7&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Upper fields&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">178 &#40;50&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929986.png"
              ]
            ]
            2 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">EXTENT DEGREES OF LUNG OPACITIES&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">No&#46; &#40;&#37;&#41; Total 440&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">No lung opacities &#40;&#43;&#47;- other findings&#41; - level 0-&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">86 &#40;19&#44;5&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Mild&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">66 &#40;15&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Moderate&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">111 &#40;25&#44;2&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Extensive&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">101 &#40;22&#44;9&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Very extensive&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">76 &#40;17&#44;3&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929993.png"
              ]
            ]
            3 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">SCORE OF LUNG INVOLVEMENT EXTENSION &#42;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Average &#43;&#47;- sd &#40;range&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t"><span class="elsevierStyleItalic">Punctuation &#40;ExtScoreCXR&#41;</span>&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">3&#44;3 &#43;&#47;- 3&#44;07 &#40;0-12&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929994.png"
              ]
            ]
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0045" class="elsevierStyleSimplePara elsevierViewall"><span class="elsevierStyleBold">Lung involvement on CXR&#44; distribution and extension&#46;</span> CXR features investigated as potential predictors&#46; ExtScoreCXR&#58; Extent score of lung involvement on CXR&#46; &#42; Predictor in the final prognostic prediction models&#46;</p>"
        ]
      ]
      9 => array:8 [
        "identificador" => "tbl0020"
        "etiqueta" => "Table 4"
        "tipo" => "MULTIMEDIATABLA"
        "mostrarFloat" => true
        "mostrarDisplay" => false
        "detalles" => array:1 [
          0 => array:3 [
            "identificador" => "at0050"
            "detalle" => "Table "
            "rol" => "short"
          ]
        ]
        "tabla" => array:1 [
          "tablatextoimagen" => array:2 [
            0 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " colspan="7" align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">SEVERITY PREDICTIVE MODELS</th></tr><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Combination of parameters&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Sensitivity &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Specificity &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">PPV &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">NPV &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">AUC-ROC &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">AUC-PRC &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Epidemiological and Radiological&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">92&#46;5&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">68&#46;2&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">59&#46;8&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">93&#46;6&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">85&#46;7&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">71&#46;3&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Epidemiological&#44; Radiological&#44; Clinical and Laboratory&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">83&#46;1&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">87&#46;9&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">77&#46;5&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">95&#46;1&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">93&#46;8&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">87&#46;6&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Epidemiological&#44; Radiological&#44; Clinical&#44; Laboratory and CNN-based&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">86&#46;4&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">84&#46;1&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">72&#46;5&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">96&#46;7&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">91&#46;4&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">82&#46;3&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929997.png"
              ]
            ]
            1 => array:2 [
              "tabla" => array:1 [
                0 => """
                  <table border="0" frame="\n
                  \t\t\t\t\tvoid\n
                  \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " colspan="8" align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">MORTALITY PREDICTIVE MODELS</th></tr><tr title="table-row"><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Combination of parameters&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Model Architecture&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Sensitivity &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Specificity &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">PPV &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">NPV &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">AUC-ROC &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th><th class="td" title="\n
                  \t\t\t\t\ttable-head\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t" scope="col" style="border-bottom: 2px solid black">AUC-PRC &#40;&#37;&#41;&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t\t\t</th></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Epidemiological and Radiological&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">RF&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">71&#46;8&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">90&#46;3&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">59&#46;5&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">92&#46;2&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">86&#46;7&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">69&#46;3&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Epidemiological&#44; Radiological&#44; Clinical and Laboratory&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">GB&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">90&#46;0&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">93&#46;7&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">69&#46;2&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">98&#46;3&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">96&#46;5&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">77&#46;9&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">Epidemiological&#44; Radiological&#44; Clinical&#44; Laboratory and CNN-based&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">GB&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">90&#46;0&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">92&#46;1&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">64&#46;3&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">98&#46;3&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">97&#46;1&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td><td class="td" title="\n
                  \t\t\t\t\ttable-entry\n
                  \t\t\t\t  " align="left" valign="\n
                  \t\t\t\t\ttop\n
                  \t\t\t\t">83&#46;4&nbsp;\t\t\t\t\t\t\n
                  \t\t\t\t</td></tr></tbody></table>
                  """
              ]
              "imagenFichero" => array:1 [
                0 => "xTab2929988.png"
              ]
            ]
          ]
        ]
        "descripcion" => array:1 [
          "en" => "<p id="spar0050" class="elsevierStyleSimplePara elsevierViewall"><span class="elsevierStyleBold">Metrics of the severity and mortality predictive models&#46;</span> Performance metrics of the internal validation performed with an unseen dataset for each of the selected severity and in-hospital mortality predictive models built with three different combinations of parameters&#46; The Youden index was used for the optimal threshold selection of the classification models&#46; RF&#58; Random Forest&#44; GB&#58; Gradient Boosting&#46;</p>"
        ]
      ]
      10 => array:5 [
        "identificador" => "upi0005"
        "tipo" => "MULTIMEDIAECOMPONENTE"
        "mostrarFloat" => false
        "mostrarDisplay" => true
        "Ecomponente" => array:2 [
          "fichero" => "mmc1.pdf"
          "ficheroTamanyo" => 397625
        ]
      ]
    ]
    "bibliografia" => array:2 [
      "titulo" => "References"
      "seccion" => array:1 [
        0 => array:2 [
          "identificador" => "bibs0005"
          "bibliografiaReferencia" => array:34 [
            0 => array:3 [
              "identificador" => "bib0005"
              "etiqueta" => "1"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "CT Imaging Features of 2019 Novel Coronavirus &#40;2019-nCoV&#41;"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "M&#46; Chung"
                            1 => "A&#46; Bernheim"
                            2 => "X&#46; Mei"
                            3 => "N&#46; Zhang"
                            4 => "M&#46; Huang"
                            5 => "X&#46; Zeng"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1148/radiol.2020200230"
                      "Revista" => array:6 [
                        "tituloSerie" => "Radiology"
                        "fecha" => "2020"
                        "volumen" => "295"
                        "paginaInicial" => "202"
                        "paginaFinal" => "207"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32017661"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            1 => array:3 [
              "identificador" => "bib0010"
              "etiqueta" => "2"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Chest CT Findings in Coronavirus Disease-19 &#40;COVID-19&#41;&#58; Relationship to Duration of Infection"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "A&#46; Bernheim"
                            1 => "X&#46; Mei"
                            2 => "M&#46; Huang"
                            3 => "Y&#46; Yang"
                            4 => "Z&#46;A&#46; Fayad"
                            5 => "N&#46; Zhang"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1148/radiol.2020200463"
                      "Revista" => array:3 [
                        "tituloSerie" => "Radiology"
                        "fecha" => "2020"
                        "volumen" => "295"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            2 => array:3 [
              "identificador" => "bib0015"
              "etiqueta" => "3"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "C&#46; Time Course of Lung Changes at Chest CT during Recovery from Coronavirus Disease 2019 &#40;COVID-19&#41;"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "F&#46; Pan"
                            1 => "T&#46; Ye"
                            2 => "P&#46; Sun"
                            3 => "S&#46; Gui"
                            4 => "B&#46; Liang"
                            5 => "L&#46; Li"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1148/radiol.2020200370"
                      "Revista" => array:6 [
                        "tituloSerie" => "Radiology"
                        "fecha" => "2020"
                        "volumen" => "295"
                        "paginaInicial" => "715"
                        "paginaFinal" => "721"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32053470"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            3 => array:3 [
              "identificador" => "bib0020"
              "etiqueta" => "4"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Performance of Radiologists in Differentiating COVID-19 from Non-COVID-19 Viral Pneumonia at Chest CT"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "H&#46;X&#46; Bai"
                            1 => "B&#46; Hsieh"
                            2 => "Z&#46; Xiong"
                            3 => "K&#46; Halsey"
                            4 => "J&#46;W&#46; Choi"
                            5 => "T&#46;M&#46;L&#46; Tran"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1148/radiol.2020200823"
                      "Revista" => array:7 [
                        "tituloSerie" => "Radiology"
                        "fecha" => "2020"
                        "volumen" => "296"
                        "paginaInicial" => "E46"
                        "paginaFinal" => "E54"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32155105"
                            "web" => "Medline"
                          ]
                        ]
                        "itemHostRev" => array:3 [
                          "pii" => "S0140673620302622"
                          "estado" => "S300"
                          "issn" => "01406736"
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            4 => array:3 [
              "identificador" => "bib0025"
              "etiqueta" => "5"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Coronavirus Disease 2019 &#40;COVID-19&#41;&#58; A Systematic Review of Imaging Findings in 919 Patients"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:4 [
                            0 => "S&#46; Salehi"
                            1 => "A&#46; Abedi"
                            2 => "S&#46; Balakrishnan"
                            3 => "A&#46; Gholamrezanezhad"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.2214/AJR.20.23034"
                      "Revista" => array:6 [
                        "tituloSerie" => "AJR Am J Roentgenol"
                        "fecha" => "2020"
                        "volumen" => "215"
                        "paginaInicial" => "87"
                        "paginaFinal" => "93"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32174129"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            5 => array:3 [
              "identificador" => "bib0030"
              "etiqueta" => "6"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Clinical and Chest Radiography Features Determine Patient Outcomes in Young and Middle-aged Adults with COVID-19"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "D&#46; Toussie"
                            1 => "N&#46; Voutsinas"
                            2 => "M&#46; Finkelstein"
                            3 => "M&#46;A&#46; Cedillo"
                            4 => "S&#46; Manna"
                            5 => "S&#46;Z&#46; Maron"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1148/radiol.2020201754"
                      "Revista" => array:6 [
                        "tituloSerie" => "Radiology"
                        "fecha" => "2020"
                        "volumen" => "297"
                        "paginaInicial" => "E197"
                        "paginaFinal" => "E206"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32407255"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            6 => array:3 [
              "identificador" => "bib0035"
              "etiqueta" => "7"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Model-based Prediction of Critical Illness in Hospitalized Patients with COVID-19"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "S&#46; Schalekamp"
                            1 => "M&#46; Huisman"
                            2 => "R&#46;A&#46; van Dijk"
                            3 => "M&#46;F&#46; Boomsma"
                            4 => "P&#46;J&#46; Freire Jorge"
                            5 => "W&#46;S&#46; de Boer"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1148/radiol.2020202723"
                      "Revista" => array:7 [
                        "tituloSerie" => "Radiology"
                        "fecha" => "2021"
                        "volumen" => "298"
                        "paginaInicial" => "E46"
                        "paginaFinal" => "E54"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32787701"
                            "web" => "Medline"
                          ]
                        ]
                        "itemHostRev" => array:3 [
                          "pii" => "S1470204517300128"
                          "estado" => "S300"
                          "issn" => "14702045"
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            7 => array:3 [
              "identificador" => "bib0040"
              "etiqueta" => "8"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Chest radiograph at admission predicts early intubation among inpatient COVID-19 patients"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "N&#46; Xiao"
                            1 => "J&#46;G&#46; Cooper"
                            2 => "J&#46;M&#46; Godbe"
                            3 => "M&#46;A&#46; Bechel"
                            4 => "M&#46;B&#46; Scott"
                            5 => "E&#46; Nguyen"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1007/s00330-020-07354-y"
                      "Revista" => array:6 [
                        "tituloSerie" => "Eur Radiol"
                        "fecha" => "2021"
                        "volumen" => "31"
                        "paginaInicial" => "2825"
                        "paginaFinal" => "2832"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/33051736"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            8 => array:3 [
              "identificador" => "bib0045"
              "etiqueta" => "9"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "COVID-19 outbreak in Italy&#58; experimental chest X-ray scoring system for quantifying and monitoring disease progression"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "A&#46; Borghesi"
                            1 => "R&#46; Maroldi"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1007/s11547-020-01200-3"
                      "Revista" => array:6 [
                        "tituloSerie" => "Radiol Med"
                        "fecha" => "2020"
                        "volumen" => "125"
                        "paginaInicial" => "509"
                        "paginaFinal" => "513"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32358689"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            9 => array:3 [
              "identificador" => "bib0050"
              "etiqueta" => "10"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Association of radiologic findings with mortality of patients infected with 2019 novel coronavirus in Wuhan&#44; China"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:5 [
                            0 => "M&#46; Yuan"
                            1 => "W&#46; Yin"
                            2 => "Z&#46; Tao"
                            3 => "W&#46; Tan"
                            4 => "Y&#46; Hu"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1371/journal.pone.0244157"
                      "Revista" => array:4 [
                        "tituloSerie" => "PLoS One"
                        "fecha" => "2020"
                        "volumen" => "15"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/33362259"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            10 => array:3 [
              "identificador" => "bib0055"
              "etiqueta" => "11"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Prediction models for diagnosis and prognosis of covid-19&#58; systematic review and critical appraisal"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "L&#46; Wynants"
                            1 => "B&#46; Van Calster"
                            2 => "G&#46;S&#46; Collins"
                            3 => "R&#46;D&#46; Riley"
                            4 => "G&#46; Heinze"
                            5 => "E&#46; Schuit"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1136/bmj.m1328"
                      "Revista" => array:5 [
                        "tituloSerie" => "BMJ"
                        "fecha" => "2020"
                        "volumen" => "369"
                        "paginaInicial" => "m1328"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32265220"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            11 => array:3 [
              "identificador" => "bib0060"
              "etiqueta" => "12"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Well-aerated Lung on Admitting Chest CT to Predict Adverse Outcome in COVID-19 Pneumonia"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "D&#46; Colombi"
                            1 => "F&#46;C&#46; Bodini"
                            2 => "M&#46; Petrini"
                            3 => "G&#46; Maffi"
                            4 => "N&#46; Morelli"
                            5 => "G&#46; Milanese"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1148/radiol.2020201433"
                      "Revista" => array:6 [
                        "tituloSerie" => "Radiology"
                        "fecha" => "2020"
                        "volumen" => "296"
                        "paginaInicial" => "E86"
                        "paginaFinal" => "E96"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32301647"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            12 => array:3 [
              "identificador" => "bib0065"
              "etiqueta" => "13"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis &#40;TRIPOD&#41;&#58; The TRIPOD Statement"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:4 [
                            0 => "G&#46;S&#46; Collins"
                            1 => "J&#46;B&#46; Reitsma"
                            2 => "D&#46;G&#46; Altman"
                            3 => "K&#46;G&#46;M&#46; Moons"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.7326/M14-0697"
                      "Revista" => array:6 [
                        "tituloSerie" => "Ann Intern Med"
                        "fecha" => "2015"
                        "volumen" => "162"
                        "paginaInicial" => "55"
                        "paginaFinal" => "63"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25560714"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            13 => array:3 [
              "identificador" => "bib0070"
              "etiqueta" => "14"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "PROBAST Group&#8224;&#46; PROBAST&#58; A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "R&#46;F&#46; Wolff"
                            1 => "K&#46;G&#46;M&#46; Moons"
                            2 => "R&#46;D&#46; Riley"
                            3 => "P&#46;F&#46; Whiting"
                            4 => "M&#46; Westwood"
                            5 => "Collins"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.7326/M18-1376"
                      "Revista" => array:7 [
                        "tituloSerie" => "Ann Intern Med"
                        "fecha" => "2019"
                        "volumen" => "170"
                        "paginaInicial" => "51"
                        "paginaFinal" => "58"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/30596875"
                            "web" => "Medline"
                          ]
                        ]
                        "itemHostRev" => array:3 [
                          "pii" => "S1470204520304435"
                          "estado" => "S300"
                          "issn" => "14702045"
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            14 => array:3 [
              "identificador" => "bib0075"
              "etiqueta" => "15"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Modified Chest X-Ray Scoring System in Evaluating Severity of COVID-19 Patient in Dr&#46; Soetomo General Hospital Surabaya&#44; Indonesia"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "R&#46; Setiawati"
                            1 => "A&#46; Widyoningroem"
                            2 => "T&#46; Handarini"
                            3 => "F&#46; Hayati"
                            4 => "A&#46;T&#46; Basja"
                            5 => "A&#46;R&#46;D&#46;S&#46; Putri"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.2147/IJGM.S310577"
                      "Revista" => array:6 [
                        "tituloSerie" => "Int J Gen Med"
                        "fecha" => "2021"
                        "volumen" => "14"
                        "paginaInicial" => "2407"
                        "paginaFinal" => "2412"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/34135624"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            15 => array:3 [
              "identificador" => "bib0080"
              "etiqueta" => "16"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A survey on addressing high-class imbalance in big data"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:4 [
                            0 => "J&#46;L&#46; Leevy"
                            1 => "T&#46;M&#46; Khoshgoftaar"
                            2 => "R&#46;A&#46; Bauder"
                            3 => "N&#46; Seliya"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:4 [
                        "tituloSerie" => "J Big Data"
                        "fecha" => "2018"
                        "volumen" => "5"
                        "paginaInicial" => "42"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            16 => array:3 [
              "identificador" => "bib0085"
              "etiqueta" => "17"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Comparing the areas under two or more correlated receiver operating characteristic curves&#58; a nonparametric approach"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "E&#46;R&#46; DeLong"
                            1 => "D&#46;M&#46; DeLong"
                            2 => "D&#46;L&#46; Clarke-Pearson"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:1 [
                      "Revista" => array:6 [
                        "tituloSerie" => "Biometrics"
                        "fecha" => "1988"
                        "volumen" => "44"
                        "paginaInicial" => "837"
                        "paginaFinal" => "845"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/3203132"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            17 => array:3 [
              "identificador" => "bib0090"
              "etiqueta" => "18"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "European Society of Radiology &#40;ESR&#41; and the European Society of Thoracic Imaging &#40;ESTI&#41;&#46; COVID-19 patients and the radiology department - advice from the European Society of Radiology &#40;ESR&#41; and the European Society of Thoracic Imaging &#40;ESTI&#41;"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "M&#46;P&#46; Revel"
                            1 => "A&#46;P&#46; Parkar"
                            2 => "H&#46; Prosch"
                            3 => "M&#46; Silva"
                            4 => "N&#46; Sverzellati"
                            5 => "F&#46; Gleeson"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1007/s00330-020-06865-y"
                      "Revista" => array:6 [
                        "tituloSerie" => "Eur Radiol"
                        "fecha" => "2020"
                        "volumen" => "30"
                        "paginaInicial" => "4903"
                        "paginaFinal" => "4909"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32314058"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            18 => array:3 [
              "identificador" => "bib0095"
              "etiqueta" => "19"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "PERT Consortium&#46; Diagnosis and Treatment of Pulmonary Embolism During the Coronavirus Disease 2019 Pandemic&#58; A Position Paper From the National PERT Consortium"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "R&#46;P&#46; Rosovsky"
                            1 => "C&#46; Grodzin"
                            2 => "R&#46; Channick"
                            3 => "G&#46;A&#46; Davis"
                            4 => "J&#46;S&#46; Giri"
                            5 => "J&#46; Horowitz"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1016/j.chest.2020.08.2064"
                      "Revista" => array:6 [
                        "tituloSerie" => "Chest"
                        "fecha" => "2020"
                        "volumen" => "158"
                        "paginaInicial" => "2590"
                        "paginaFinal" => "2601"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32861692"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            19 => array:3 [
              "identificador" => "bib0100"
              "etiqueta" => "20"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Value of initial chest radiographs for predicting clinical outcomes in patients with severe acute respiratory syndrome"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "T&#46;N&#46; Chau"
                            1 => "P&#46;O&#46; Lee"
                            2 => "K&#46;W&#46; Choi"
                            3 => "C&#46;M&#46; Lee"
                            4 => "K&#46;F&#46; Ma"
                            5 => "T&#46;Y&#46; Tsang"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1016/j.amjmed.2004.03.020"
                      "Revista" => array:6 [
                        "tituloSerie" => "Am J Med"
                        "fecha" => "2004"
                        "volumen" => "117"
                        "paginaInicial" => "249"
                        "paginaFinal" => "254"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/15308434"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            20 => array:3 [
              "identificador" => "bib0105"
              "etiqueta" => "21"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "A correlation between the severity of lung lesions on radiographs and clinical findings in patients with severe acute respiratory syndrome"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "Y&#46;L&#46; Wan"
                            1 => "P&#46;K&#46; Tsay"
                            2 => "Y&#46;C&#46; Cheung"
                            3 => "P&#46;C&#46; Chiang"
                            4 => "C&#46;H&#46; Wang"
                            5 => "Y&#46;H&#46; Tsai"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.3348/kjr.2007.8.6.466"
                      "Revista" => array:6 [
                        "tituloSerie" => "Korean J Radiol"
                        "fecha" => "2007"
                        "volumen" => "8"
                        "paginaInicial" => "466"
                        "paginaFinal" => "474"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/18071276"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            21 => array:3 [
              "identificador" => "bib0110"
              "etiqueta" => "22"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Mild versus severe COVID-19&#58; Laboratory markers"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "T&#46;P&#46; Velavan"
                            1 => "C&#46;G&#46; Meyer"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1016/j.ijid.2020.04.061"
                      "Revista" => array:6 [
                        "tituloSerie" => "Int J Infect Dis"
                        "fecha" => "2020"
                        "volumen" => "95"
                        "paginaInicial" => "304"
                        "paginaFinal" => "307"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32344011"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            22 => array:3 [
              "identificador" => "bib0115"
              "etiqueta" => "23"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan&#44; China&#58; a retrospective cohort study"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "F&#46; Zhou"
                            1 => "T&#46; Yu"
                            2 => "R&#46; Du"
                            3 => "G&#46; Fan"
                            4 => "Y&#46; Liu"
                            5 => "Liu"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1016/S0140-6736(20)30566-3"
                      "Revista" => array:6 [
                        "tituloSerie" => "Lancet&#46;"
                        "fecha" => "2020"
                        "volumen" => "395"
                        "paginaInicial" => "1054"
                        "paginaFinal" => "1062"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32171076"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            23 => array:3 [
              "identificador" => "bib0120"
              "etiqueta" => "24"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Risk Factors Associated With Acute Respiratory Distress Syndrome and Death in Patients With Coronavirus Disease 2019 Pneumonia in Wuhan&#44; China"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "C&#46; Wu"
                            1 => "X&#46; Chen"
                            2 => "Y&#46; Cai"
                            3 => "J&#46; Xia"
                            4 => "X&#46; Zhou"
                            5 => "S&#46; Xu"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1001/jamainternmed.2020.0994"
                      "Revista" => array:6 [
                        "tituloSerie" => "JAMA Intern Med"
                        "fecha" => "2020"
                        "volumen" => "180"
                        "paginaInicial" => "934"
                        "paginaFinal" => "943"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32167524"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            24 => array:3 [
              "identificador" => "bib0125"
              "etiqueta" => "25"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Risk factors of critical &#38; mortal COVID-19 cases&#58; A systematic literature review and meta-analysis"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "Z&#46; Zheng"
                            1 => "F&#46; Peng"
                            2 => "B&#46; Xu"
                            3 => "J&#46; Zhao"
                            4 => "H&#46; Liu"
                            5 => "J&#46; Peng"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1016/j.jinf.2020.04.021"
                      "Revista" => array:6 [
                        "tituloSerie" => "J Infect"
                        "fecha" => "2020"
                        "volumen" => "81"
                        "paginaInicial" => "e16"
                        "paginaFinal" => "e25"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32800797"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            25 => array:3 [
              "identificador" => "bib0130"
              "etiqueta" => "26"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Clinical characteristics of 140 patients infected with SARS-CoV-2 in Wuhan&#44; China"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "J&#46;J&#46; Zhang"
                            1 => "X&#46; Dong"
                            2 => "Y&#46;Y&#46; Cao"
                            3 => "Y&#46;D&#46; Yuan"
                            4 => "Y&#46;B&#46; Yang"
                            5 => "Y&#46;Q&#46; Yan"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1111/all.14238"
                      "Revista" => array:7 [
                        "tituloSerie" => "Allergy"
                        "fecha" => "2020"
                        "volumen" => "75"
                        "numero" => "July"
                        "paginaInicial" => "1730"
                        "paginaFinal" => "1741"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32077115"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            26 => array:3 [
              "identificador" => "bib0135"
              "etiqueta" => "27"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Clinical predictors of mortality due to COVID-19 based on an analysis of data of 150 patients from Wuhan&#44; China"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:5 [
                            0 => "Q&#46; Ruan"
                            1 => "K&#46; Yang"
                            2 => "W&#46; Wang"
                            3 => "L&#46; Jiang"
                            4 => "J&#46; Song"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1007/s00134-020-05991-x"
                      "Revista" => array:6 [
                        "tituloSerie" => "Intensive Care Med"
                        "fecha" => "2020"
                        "volumen" => "46"
                        "paginaInicial" => "846"
                        "paginaFinal" => "848"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32125452"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            27 => array:3 [
              "identificador" => "bib0140"
              "etiqueta" => "28"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Obesity in patients with COVID-19&#58; a systematic review and meta-analysis"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:6 [
                            0 => "Y&#46; Huang"
                            1 => "Y&#46; Lu"
                            2 => "Y&#46;M&#46; Huang"
                            3 => "M&#46; Wang"
                            4 => "W&#46; Ling"
                            5 => "Y&#46; Sui"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1016/j.metabol.2020.154378"
                      "Revista" => array:3 [
                        "tituloSerie" => "Metabolism"
                        "fecha" => "2020"
                        "volumen" => "113"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            28 => array:3 [
              "identificador" => "bib0145"
              "etiqueta" => "29"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "China Medical Treatment Expert Group for COVID-19&#46; Development and Validation of a Clinical Risk Score to Predict the Occurrence of Critical Illness in Hospitalized Patients With COVID-19"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "W&#46; Liang"
                            1 => "H&#46; Liang"
                            2 => "L&#46; Ou"
                            3 => "B&#46; Chen"
                            4 => "A&#46; Chen"
                            5 => "C&#46; Li"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1001/jamainternmed.2020.2033"
                      "Revista" => array:5 [
                        "tituloSerie" => "JAMA Intern Med"
                        "fecha" => "2020"
                        "volumen" => "180"
                        "paginaInicial" => "1081"
                        "paginaFinal" => "1089"
                      ]
                    ]
                  ]
                ]
              ]
            ]
            29 => array:3 [
              "identificador" => "bib0150"
              "etiqueta" => "30"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Prognostic Accuracy of the SIRS&#44; qSOFA&#44; and NEWS for Early Detection of Clinical Deterioration in SARS-CoV-2 Infected Patients"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:5 [
                            0 => "J&#46;G&#46; Jang"
                            1 => "J&#46; Hur"
                            2 => "K&#46;S&#46; Hong"
                            3 => "W&#46; Lee"
                            4 => "J&#46;H&#46; Ahn"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.3346/jkms.2020.35.e234"
                      "Revista" => array:5 [
                        "tituloSerie" => "J Korean Med Sci"
                        "fecha" => "2020"
                        "volumen" => "35"
                        "paginaInicial" => "e234"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32597046"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            30 => array:3 [
              "identificador" => "bib0155"
              "etiqueta" => "31"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "National Early Warning Score 2 &#40;NEWS2&#41; on admission predicts severe disease and in-hospital mortality from Covid-19 - a prospective cohort study"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "M&#46; Myrstad"
                            1 => "H&#46; Ihle-Hansen"
                            2 => "A&#46;A&#46; Tveita"
                            3 => "E&#46;L&#46; Andersen"
                            4 => "S&#46; Nyg&#229;rd"
                            5 => "A&#46; Tveit"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1186/s13049-020-00764-3"
                      "Revista" => array:5 [
                        "tituloSerie" => "Scand J Trauma Resusc Emerg Med"
                        "fecha" => "2020"
                        "volumen" => "28"
                        "paginaInicial" => "66"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32660623"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            31 => array:3 [
              "identificador" => "bib0160"
              "etiqueta" => "32"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Characteristics of and Important Lessons From the Coronavirus Disease 2019 &#40;COVID-19&#41; Outbreak in China&#58; Summary of a Report of 72 314 Cases From the Chinese Center for Disease Control and Prevention"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:2 [
                            0 => "Z&#46; Wu"
                            1 => "J&#46;M&#46; McGoogan"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1001/jama.2020.2648"
                      "Revista" => array:6 [
                        "tituloSerie" => "JAMA"
                        "fecha" => "2020"
                        "volumen" => "323"
                        "paginaInicial" => "1239"
                        "paginaFinal" => "1242"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32091533"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            32 => array:3 [
              "identificador" => "bib0165"
              "etiqueta" => "33"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Presenting Characteristics&#44; Comorbidities&#44; and Outcomes Among 5700 Patients Hospitalized With COVID-19 in the New York City Area"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => true
                          "autores" => array:6 [
                            0 => "S&#46; Richardson"
                            1 => "J&#46;S&#46; Hirsch"
                            2 => "M&#46; Narasimhan"
                            3 => "J&#46;M&#46; Crawford"
                            4 => "T&#46; McGinn"
                            5 => "K&#46;W&#46; Davidson"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1001/jama.2020.6775"
                      "Revista" => array:6 [
                        "tituloSerie" => "JAMA"
                        "fecha" => "2020"
                        "volumen" => "323"
                        "paginaInicial" => "2052"
                        "paginaFinal" => "2059"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32320003"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
            33 => array:3 [
              "identificador" => "bib0170"
              "etiqueta" => "34"
              "referencia" => array:1 [
                0 => array:2 [
                  "contribucion" => array:1 [
                    0 => array:2 [
                      "titulo" => "Sample size considerations for the external validation of a multivariable prognostic model&#58; a resampling study"
                      "autores" => array:1 [
                        0 => array:2 [
                          "etal" => false
                          "autores" => array:3 [
                            0 => "G&#46;S&#46; Collins"
                            1 => "E&#46;O&#46; Ogundimu"
                            2 => "D&#46;G&#46; Altman"
                          ]
                        ]
                      ]
                    ]
                  ]
                  "host" => array:1 [
                    0 => array:2 [
                      "doi" => "10.1002/sim.6787"
                      "Revista" => array:6 [
                        "tituloSerie" => "Stat Med"
                        "fecha" => "2016"
                        "volumen" => "35"
                        "paginaInicial" => "214"
                        "paginaFinal" => "226"
                        "link" => array:1 [
                          0 => array:2 [
                            "url" => "https://www.ncbi.nlm.nih.gov/pubmed/26553135"
                            "web" => "Medline"
                          ]
                        ]
                      ]
                    ]
                  ]
                ]
              ]
            ]
          ]
        ]
      ]
    ]
    "agradecimientos" => array:1 [
      0 => array:4 [
        "identificador" => "xack609173"
        "titulo" => "Acknowledgments"
        "texto" => "<p id="par0275" class="elsevierStylePara elsevierViewall">Acknowledgments to all the personnel working at University and Polytechnic La Fe Hospital for their dedication during the COVID-19 pandemic and specially to Carlos Baeza&#44; Jos&#233; S&#225;nchez&#44; Ignacio G&#243;mez&#44; Ana Gil&#44; Rodrigo Blanco&#44; Pau Lozano&#44; Alberto Garc&#237;a&#44; Marta Montero&#44; Pilar Estell&#233;s&#44; Javier Mill&#225;n and Cristina Aguado&#46;</p>"
        "vista" => "all"
      ]
    ]
  ]
  "idiomaDefecto" => "en"
  "url" => "/21735107/0000006400000003/v1_202206060554/S2173510722000222/v1_202206060554/en/main.assets"
  "Apartado" => array:4 [
    "identificador" => "66551"
    "tipo" => "SECCION"
    "en" => array:2 [
      "titulo" => "Original articles"
      "idiomaDefecto" => true
    ]
    "idiomaDefecto" => "en"
  ]
  "PDF" => "https://static.elsevier.es/multimedia/21735107/0000006400000003/v1_202206060554/S2173510722000222/v1_202206060554/en/main.pdf?idApp=UINPBA00004N&text.app=https://www.elsevier.es/"
  "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2173510722000222?idApp=UINPBA00004N"
]
Article information
ISSN: 21735107
Original language: English
DOI:10.1016/j.rxeng.2021.09.004
The statistics are updated each day
Year/Month Html Pdf Total
2024 November 2 0 2
2024 October 26 0 26
2024 September 50 4 54
2024 August 27 0 27
2024 July 58 0 58
2024 June 13 1 14
2024 May 19 0 19
2024 April 24 0 24
2024 March 41 1 42
2024 February 41 0 41
2024 January 34 0 34
2023 December 58 0 58
2023 November 99 3 102
2023 October 185 3 188
2023 September 73 5 78
2023 August 74 3 77
2023 July 60 2 62
2023 June 67 4 71
2023 May 55 0 55
2023 April 38 2 40
2023 March 24 0 24
2023 February 31 0 31
2023 January 20 2 22
2022 December 40 0 40
2022 November 52 4 56
2022 October 40 2 42
2022 September 26 0 26
2022 August 69 14 83
2022 July 32 2 34
2022 June 43 2 45
2022 February 0 2 2
Show all

Follow this link to access the full text of the article

Subscribe to our newsletter

Publish in
Radiología
Radiología (English Edition) is a member and subscribes the principles of, the Committee on Publication Ethics (COPE)
www.publicationethics.org.
Free access articles
Presurgical diagnosis of diffuse gliomas in adults:...
Radiologia. 2024;66:260-77
Radiologic aspects of COVID-19 pneumonia: Outcomes and...
Radiologia. 2021;63:74-88
Radiologic diagnosis of patients with...
Radiologia. 2021;63:56-73

Radiología (English Edition) follows the Recommendations for the Conduct, Reporting, Editing and Publication of Scholarly Work in Medical Journals

es en pt

¿Es usted profesional sanitario apto para prescribir o dispensar medicamentos?

Are you a health professional able to prescribe or dispense drugs?

Você é um profissional de saúde habilitado a prescrever ou dispensar medicamentos