array:24 [ "pii" => "S2387020624003358" "issn" => "23870206" "doi" => "10.1016/j.medcle.2024.01.038" "estado" => "S300" "fechaPublicacion" => "2024-08-30" "aid" => "6617" "copyright" => "Elsevier España, S.L.U.. All rights reserved" "copyrightAnyo" => "2024" "documento" => "article" "crossmark" => 1 "subdocumento" => "fla" "cita" => "Med Clin. 2024;163:167-74" "abierto" => array:3 [ "ES" => false "ES2" => false "LATM" => false ] "gratuito" => false "lecturas" => array:1 [ "total" => 0 ] "Traduccion" => array:1 [ "es" => array:19 [ "pii" => "S0025775324001866" "issn" => "00257753" "doi" => "10.1016/j.medcli.2024.01.040" "estado" => "S300" "fechaPublicacion" => "2024-08-30" "aid" => "6617" "copyright" => "Elsevier España, S.L.U." "documento" => "article" "crossmark" => 1 "subdocumento" => "fla" "cita" => "Med Clin. 2024;163:167-74" "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" => "Árboles de clasificación obtenidos mediante inteligencia artificial para la predicción de insuficiencia cardiaca tras el síndrome coronario agudo" "tienePdf" => "es" "tieneTextoCompleto" => "es" "tieneResumen" => array:2 [ 0 => "es" 1 => "en" ] "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "167" "paginaFinal" => "174" ] ] "titulosAlternativos" => array:1 [ "en" => array:1 [ "titulo" => "Classification tree obtained by artificial intelligence for the prediction of heart failure after acute coronary syndromes" ] ] "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" => "fig0005" "etiqueta" => "Figura 1" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr1.jpeg" "Alto" => 2720 "Ancho" => 2675 "Tamanyo" => 312068 ] ] "descripcion" => array:1 [ "es" => "<p id="spar0045" class="elsevierStyleSimplePara elsevierViewall">Árbol de decisiones obtenido a partir de la partición recursiva basada en modelos para predecir el tiempo de HF con datos censurados y distribución logarítmica normal para los tiempos de supervivencia. Los nódulos terminales representan patrones resultantes de pacientes con insuficiencia cardíaca al experimentar el síndrome coronario agudo.</p>" ] ] ] "autores" => array:1 [ 0 => array:2 [ "autoresLista" => "Alberto Cordero, Vicente Bertomeu-Gonzalez, José V. Segura, Javier Morales, Belén Álvarez-Álvarez, David Escribano, Moisés Rodríguez-Manero, Belén Cid-Alvarez, José M. García-Acuña, José Ramón González-Juanatey, Asunción Martínez-Mayoral" "autores" => array:11 [ 0 => array:2 [ "nombre" => "Alberto" "apellidos" => "Cordero" ] 1 => array:2 [ "nombre" => "Vicente" "apellidos" => "Bertomeu-Gonzalez" ] 2 => array:2 [ "nombre" => "José V." "apellidos" => "Segura" ] 3 => array:2 [ "nombre" => "Javier" "apellidos" => "Morales" ] 4 => array:2 [ "nombre" => "Belén" "apellidos" => "Álvarez-Álvarez" ] 5 => array:2 [ "nombre" => "David" "apellidos" => "Escribano" ] 6 => array:2 [ "nombre" => "Moisés" "apellidos" => "Rodríguez-Manero" ] 7 => array:2 [ "nombre" => "Belén" "apellidos" => "Cid-Alvarez" ] 8 => array:2 [ "nombre" => "José M." "apellidos" => "García-Acuña" ] 9 => array:2 [ "nombre" => "José Ramón" "apellidos" => "González-Juanatey" ] 10 => array:2 [ "nombre" => "Asunción" "apellidos" => "Martínez-Mayoral" ] ] ] ] ] "idiomaDefecto" => "es" "Traduccion" => array:1 [ "en" => array:9 [ "pii" => "S2387020624003358" "doi" => "10.1016/j.medcle.2024.01.038" "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/S2387020624003358?idApp=UINPBA00004N" ] ] "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0025775324001866?idApp=UINPBA00004N" "url" => "/00257753/0000016300000004/v1_202408190637/S0025775324001866/v1_202408190637/es/main.assets" ] ] "itemSiguiente" => array:19 [ "pii" => "S2387020624003425" "issn" => "23870206" "doi" => "10.1016/j.medcle.2024.02.014" "estado" => "S300" "fechaPublicacion" => "2024-08-30" "aid" => "6640" "copyright" => "The Author(s)" "documento" => "article" "crossmark" => 1 "subdocumento" => "fla" "cita" => "Med Clin. 2024;163:175-82" "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 article</span>" "titulo" => "Prognostic value of electrical bioimpedance measured with a portable and wireless device in acute heart failure" "tienePdf" => "en" "tieneTextoCompleto" => "en" "tieneResumen" => array:2 [ 0 => "en" 1 => "es" ] "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "175" "paginaFinal" => "182" ] ] "titulosAlternativos" => array:1 [ "es" => array:1 [ "titulo" => "Valor pronóstico de la bioimpedancia eléctrica medida con el dispositivo IVOL en la insuficiencia cardiaca aguda" ] ] "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" => "fig0010" "etiqueta" => "Figure 2" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr2.jpeg" "Alto" => 3373 "Ancho" => 3341 "Tamanyo" => 526893 ] ] "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0010" "detalle" => "Figure " "rol" => "short" ] ] "descripcion" => array:1 [ "en" => "<p id="spar0010" class="elsevierStyleSimplePara elsevierViewall">Survival according to electrical bioimpedance values measured with the IVOL device: (a) in all study subjects; (b) subgroup with LVEF ≥ 50%; (c) subgroup with LVEF < 50%; (d) subgroup with TAPSE ≥ 17 mmHg, (e) subgroup with TAPSE < 17 mmHg.</p>" ] ] ] "autores" => array:1 [ 0 => array:2 [ "autoresLista" => "Encarnación Gutiérrez-Carretero, Ana María Campos, Luis Giménez-Miranda, Kambitz Rezaei, Amelia Peña, Javier Rossel, Juan Manuel Praena, Tarik Smani, Antonio Ordoñez, Francisco Javier Medrano" "autores" => array:10 [ 0 => array:2 [ "nombre" => "Encarnación" "apellidos" => "Gutiérrez-Carretero" ] 1 => array:2 [ "nombre" => "Ana María" "apellidos" => "Campos" ] 2 => array:2 [ "nombre" => "Luis" "apellidos" => "Giménez-Miranda" ] 3 => array:2 [ "nombre" => "Kambitz" "apellidos" => "Rezaei" ] 4 => array:2 [ "nombre" => "Amelia" "apellidos" => "Peña" ] 5 => array:2 [ "nombre" => "Javier" "apellidos" => "Rossel" ] 6 => array:2 [ "nombre" => "Juan Manuel" "apellidos" => "Praena" ] 7 => array:2 [ "nombre" => "Tarik" "apellidos" => "Smani" ] 8 => array:2 [ "nombre" => "Antonio" "apellidos" => "Ordoñez" ] 9 => array:2 [ "nombre" => "Francisco Javier" "apellidos" => "Medrano" ] ] ] ] ] "idiomaDefecto" => "en" "Traduccion" => array:1 [ "es" => array:9 [ "pii" => "S0025775324002100" "doi" => "10.1016/j.medcli.2024.02.027" "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/S0025775324002100?idApp=UINPBA00004N" ] ] "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2387020624003425?idApp=UINPBA00004N" "url" => "/23870206/0000016300000004/v2_202409040637/S2387020624003425/v2_202409040637/en/main.assets" ] "itemAnterior" => array:19 [ "pii" => "S2387020624003383" "issn" => "23870206" "doi" => "10.1016/j.medcle.2024.07.004" "estado" => "S300" "fechaPublicacion" => "2024-08-30" "aid" => "6630" "copyright" => "The Author(s)" "documento" => "article" "crossmark" => 1 "subdocumento" => "fla" "cita" => "Med Clin. 2024;163:159-66" "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 article</span>" "titulo" => "Clinico-pathological evaluation of tumor budding in the oncological progression of colorectal cancer" "tienePdf" => "en" "tieneTextoCompleto" => "en" "tieneResumen" => array:2 [ 0 => "en" 1 => "es" ] "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "159" "paginaFinal" => "166" ] ] "titulosAlternativos" => array:1 [ "es" => array:1 [ "titulo" => "Evaluación clínico-patológica del <span class="elsevierStyleItalic">tumor budding</span> en la progresión oncológica del cáncer colorrectal" ] ] "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" => "fig0010" "etiqueta" => "Fig. 2" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr2.jpeg" "Alto" => 1229 "Ancho" => 1675 "Tamanyo" => 113169 ] ] "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0010" "detalle" => "Fig. " "rol" => "short" ] ] "descripcion" => array:1 [ "en" => "<p id="spar0010" class="elsevierStyleSimplePara elsevierViewall">Overall survival (OS) according to TB grade (<span class="elsevierStyleItalic">P</span> = .012).</p>" ] ] ] "autores" => array:1 [ 0 => array:2 [ "autoresLista" => "Pietro Giovanni Giordano, Ana Gabriela Díaz Zelaya, Yari Yuritzi Aguilera Molina, Nestor Orlando Taboada Mostajo, Yelene Ajete Ramos, Ricardo Ortega García, Esteban Peralta de Michelis, Juan Carlos Meneu Díaz" "autores" => array:8 [ 0 => array:2 [ "nombre" => "Pietro Giovanni" "apellidos" => "Giordano" ] 1 => array:2 [ "nombre" => "Ana Gabriela" "apellidos" => "Díaz Zelaya" ] 2 => array:2 [ "nombre" => "Yari Yuritzi" "apellidos" => "Aguilera Molina" ] 3 => array:2 [ "nombre" => "Nestor Orlando" "apellidos" => "Taboada Mostajo" ] 4 => array:2 [ "nombre" => "Yelene" "apellidos" => "Ajete Ramos" ] 5 => array:2 [ "nombre" => "Ricardo" "apellidos" => "Ortega García" ] 6 => array:2 [ "nombre" => "Esteban" "apellidos" => "Peralta de Michelis" ] 7 => array:2 [ "nombre" => "Juan Carlos" "apellidos" => "Meneu Díaz" ] ] ] ] ] "idiomaDefecto" => "en" "Traduccion" => array:1 [ "es" => array:9 [ "pii" => "S0025775324002008" "doi" => "10.1016/j.medcli.2024.02.017" "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/S0025775324002008?idApp=UINPBA00004N" ] ] "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2387020624003383?idApp=UINPBA00004N" "url" => "/23870206/0000016300000004/v2_202409040637/S2387020624003383/v2_202409040637/en/main.assets" ] "en" => array:20 [ "idiomaDefecto" => true "cabecera" => "<span class="elsevierStyleTextfn">Original article</span>" "titulo" => "Classification tree obtained by artificial intelligence for the prediction of heart failure after acute coronary syndromes" "tieneTextoCompleto" => true "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "167" "paginaFinal" => "174" ] ] "autores" => array:1 [ 0 => array:4 [ "autoresLista" => "Alberto Cordero, Vicente Bertomeu-Gonzalez, José V. Segura, Javier Morales, Belén Álvarez-Álvarez, David Escribano, Moisés Rodríguez-Manero, Belén Cid-Alvarez, José M. García-Acuña, José Ramón González-Juanatey, Asunción Martínez-Mayoral" "autores" => array:11 [ 0 => array:4 [ "nombre" => "Alberto" "apellidos" => "Cordero" "email" => array:1 [ 0 => "acorderofort@gmail.com" ] "referencia" => array:2 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">a</span>" "identificador" => "aff0005" ] 1 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">*</span>" "identificador" => "cor0005" ] ] ] 1 => array:3 [ "nombre" => "Vicente" "apellidos" => "Bertomeu-Gonzalez" "referencia" => array:3 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">b</span>" "identificador" => "aff0010" ] 1 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">c</span>" "identificador" => "aff0015" ] 2 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">d</span>" "identificador" => "aff0020" ] ] ] 2 => array:3 [ "nombre" => "José V." "apellidos" => "Segura" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">e</span>" "identificador" => "aff0025" ] ] ] 3 => array:3 [ "nombre" => "Javier" "apellidos" => "Morales" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">e</span>" "identificador" => "aff0025" ] ] ] 4 => array:3 [ "nombre" => "Belén" "apellidos" => "Álvarez-Álvarez" "referencia" => array:2 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">c</span>" "identificador" => "aff0015" ] 1 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">f</span>" "identificador" => "aff0030" ] ] ] 5 => array:3 [ "nombre" => "David" "apellidos" => "Escribano" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">g</span>" "identificador" => "aff0035" ] ] ] 6 => array:3 [ "nombre" => "Moisés" "apellidos" => "Rodríguez-Manero" "referencia" => array:2 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">c</span>" "identificador" => "aff0015" ] 1 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">f</span>" "identificador" => "aff0030" ] ] ] 7 => array:3 [ "nombre" => "Belén" "apellidos" => "Cid-Alvarez" "referencia" => array:2 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">c</span>" "identificador" => "aff0015" ] 1 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">f</span>" "identificador" => "aff0030" ] ] ] 8 => array:3 [ "nombre" => "José M." "apellidos" => "García-Acuña" "referencia" => array:2 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">c</span>" "identificador" => "aff0015" ] 1 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">f</span>" "identificador" => "aff0030" ] ] ] 9 => array:3 [ "nombre" => "José Ramón" "apellidos" => "González-Juanatey" "referencia" => array:2 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">c</span>" "identificador" => "aff0015" ] 1 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">f</span>" "identificador" => "aff0030" ] ] ] 10 => array:3 [ "nombre" => "Asunción" "apellidos" => "Martínez-Mayoral" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">e</span>" "identificador" => "aff0025" ] ] ] ] "afiliaciones" => array:7 [ 0 => array:3 [ "entidad" => "Departamento de Cardiología, Hospital IMED Elche, Elche, Alicante, Spain" "etiqueta" => "a" "identificador" => "aff0005" ] 1 => array:3 [ "entidad" => "Grupo de Investigación Cardiovascular, Universidad Miguel Hernández, Elche, Alicante, Spain" "etiqueta" => "b" "identificador" => "aff0010" ] 2 => array:3 [ "entidad" => "Centro de Investigación Biomédica en Red de Enfermedades Cardiovasculares (CIBERCV), Madrid, Spain" "etiqueta" => "c" "identificador" => "aff0015" ] 3 => array:3 [ "entidad" => "Departamento de Cardiología, Clínica Benidorm, Benidorm, Alicante, Spain" "etiqueta" => "d" "identificador" => "aff0020" ] 4 => array:3 [ "entidad" => "Departamento de Estadística, Matemáticas e Informática, Instituto Universitario Centro de Investigación Operativa (CIO), Universidad Miguel Hernández, Elche, Alicante, Spain" "etiqueta" => "e" "identificador" => "aff0025" ] 5 => array:3 [ "entidad" => "Departamento de Cardiología, Complejo Hospitalario de la Universidad de Santiago, Santiago de Compostela, A Coruña, Spain" "etiqueta" => "f" "identificador" => "aff0030" ] 6 => array:3 [ "entidad" => "Departamento de Cardiología, Hospital Universitario de San Juan, San Juan de Alicante, Alicante, Spain" "etiqueta" => "g" "identificador" => "aff0035" ] ] "correspondencia" => array:1 [ 0 => array:3 [ "identificador" => "cor0005" "etiqueta" => "⁎" "correspondencia" => "Corresponding author." ] ] ] ] "titulosAlternativos" => array:1 [ "es" => array:1 [ "titulo" => "Árboles de clasificación obtenidos mediante inteligencia artificial para la predicción de insuficiencia cardiaca tras el síndrome coronario agudo" ] ] "resumenGrafico" => array:2 [ "original" => 0 "multimedia" => array:8 [ "identificador" => "fig0015" "etiqueta" => "Fig. 3" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr3.jpeg" "Alto" => 1531 "Ancho" => 2508 "Tamanyo" => 134684 ] ] "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0015" "detalle" => "Fig. " "rol" => "short" ] ] "descripcion" => array:1 [ "en" => "<p id="spar0015" class="elsevierStyleSimplePara elsevierViewall">Evolution of validation metrics to classify individuals as having a HF or not, for a range of percentiles on the time-to-event prediction curves between 0.05 and 0.95.</p>" ] ] ] "textoCompleto" => "<span class="elsevierStyleSections"><span id="sec0005" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0065">Introduction</span><p id="par0005" class="elsevierStylePara elsevierViewall">Coronary heart disease is the main risk factor for heart failure (HF).<a class="elsevierStyleCrossRefs" href="#bib0005"><span class="elsevierStyleSup">1,2</span></a> Acute coronary syndrome (ACS) is the most common form of coronary heart disease onset and the time when the myocardium is most damaged. The incidence of HF during hospitalisation for ACS, together with the left ventricular ejection fraction (LVEF) value, are the main determinants of subsequent hospitalisation for HF.<a class="elsevierStyleCrossRef" href="#bib0015"><span class="elsevierStyleSup">3</span></a> Several clinical characteristics, such as diabetes mellitus, age and incomplete revascularization,<a class="elsevierStyleCrossRefs" href="#bib0020"><span class="elsevierStyleSup">4,5</span></a> have also been independently associated with an increased risk of HF.</p><p id="par0010" class="elsevierStylePara elsevierViewall">Reductions in in-hospital and short-term mortality in patients with ACS have led to an increasing proportion of patients at increased risk of HF.<a class="elsevierStyleCrossRefs" href="#bib0020"><span class="elsevierStyleSup">4,6–8</span></a> However, the incidence of HF is variable, ranging from 5% to 50% across cohorts and patient subgroups.<a class="elsevierStyleCrossRefs" href="#bib0020"><span class="elsevierStyleSup">4,5,8</span></a> Therefore, there is an unmet need for an accurate estimate of HF risk after ACS. Late diagnosis of HF is associated with an adverse prognosis, but also postpones the inclusion of patients in HF follow-up programmes, which have been shown to reduce mortality and hospital readmissions.<a class="elsevierStyleCrossRef" href="#bib0045"><span class="elsevierStyleSup">9</span></a></p><p id="par0015" class="elsevierStylePara elsevierViewall">Data analysis using artificial intelligence techniques based on classification trees represents an advanced strategy in cardiology, as it provides clinical patterns with similar risk to the selected outcome.<a class="elsevierStyleCrossRefs" href="#bib0050"><span class="elsevierStyleSup">10,11</span></a> Our approach takes this a step further by developing an optimal method for automated time-to-event prediction, assuming a parametric model.</p></span><span id="sec0010" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0070">Methods</span><p id="par0020" class="elsevierStylePara elsevierViewall">The study included all consecutive patients admitted for ACS in two Spanish centres between 2006 and 2017, resulting in a cohort of 8,798 patients. Patients who died during hospitalisation (n<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>453) and those lost to follow-up for any reason (n<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>450) were excluded, leaving a total of 7,895 patients, of whom only 7,097 had complete data (798 records had missing values for some variables). Both participating centres have <span class="elsevierStyleItalic">on-site</span> percutaneous coronary intervention capability, with no need to transfer patients for this procedure. The GRACE score was used to assess mortality risk, and patients with a GRACE score of more than 140 were classified as high risk.<a class="elsevierStyleCrossRef" href="#bib0060"><span class="elsevierStyleSup">12</span></a> During admission and after revascularisation of the culprit vessel, patients with multivessel disease underwent complete revascularisation guided by evidence of ischaemia, angina or left ventricular dysfunction.</p><p id="par0025" class="elsevierStylePara elsevierViewall">Trained medical staff collected data on risk factors, medical history, treatments, ancillary tests and primary diagnosis at discharge for all patients. In both centres, diagnostic and therapeutic protocols for non-ST-segment elevation ACS included blood tests on arrival at the emergency department and a fasting blood test on the first day of hospital admission. Medical treatment before, during and after the index hospitalisation was recorded. Patients on beta-blockers, ACE inhibitors, statins and antiplatelet therapy were considered to be receiving optimal medical treatment. The per-protocol duration of dual antiplatelet therapy was 12<span class="elsevierStyleHsp" style=""></span>months. Glomerular filtration rate (GFR) was estimated from serum creatinine with the CKD-EPI creatinine equation.<a class="elsevierStyleCrossRef" href="#bib0065"><span class="elsevierStyleSup">13</span></a> Based on a previous medical history of coronary artery disease, patients with a clinical diagnosis of myocardial infarction, stable or unstable angina, or coronary revascularisation caused by angina were included.</p><p id="par0030" class="elsevierStylePara elsevierViewall">Comorbidity was quantified on the first day of admission using the Charlson comorbidity index.<a class="elsevierStyleCrossRefs" href="#bib0070"><span class="elsevierStyleSup">14,15</span></a> This index considers 17 categories of comorbidity recorded through history-taking, review of patient medical records, or both. Each category is weighted according to one-year mortality risk. The patients’ scores were obtained by adding up the weight of each comorbidity in the Charlson index. Major adverse cardiovascular events during follow-up included all-cause mortality, cardiovascular mortality, myocardial infarction, HF hospitalisation and unplanned repeat revascularisation.</p><p id="par0035" class="elsevierStylePara elsevierViewall">Post-discharge follow-up involved a well-established protocol at each centre and included telephone calls and a review of electronic medical records and institutional databases. In the absence of medical reports, the vital status was verified by telephone. All health-related processes in these centres and their health areas are based on electronic resources. The attending physician in outpatient or inpatient care always records the death of the patient in the electronic database, but the coding department of each health area is solely responsible for changing the status to deceased, which means that vital status is certified by two separate processes. Trained medical staff collected and evaluated clinical events in both databases. The ethics committee of the coordinating hospital approved the study protocol and informed consent.</p><span id="sec0015" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0075">Statistical analysis</span><p id="par0040" class="elsevierStylePara elsevierViewall">Quantitative variables were presented as means and standard deviations, except follow-up time (median, interquartile range), and differences between patients with and without HF readmission were assessed by Student’s t-test. Dichotomous variables were described as absolute and relative frequencies, and the association between these variables and HF readmission was analysed using chi-square tests. P-values were reported for all tests of association.</p><p id="par0045" class="elsevierStylePara elsevierViewall">The tree generation process followed the TRIPOD recommendations<a class="elsevierStyleCrossRef" href="#bib0080"><span class="elsevierStyleSup">16</span></a> (Appendix A Supplementary Table S1) and was carried out using the model-based recursive partitioning algorithm according to the following steps: 1)<span class="elsevierStyleHsp" style=""></span>a parametric model is fitted to a data set; 2)<span class="elsevierStyleHsp" style=""></span>the “parametric instability” (variations in the model parameter estimate) is tested on a set of (explanatory) variables, the response to which is likely to be “split” into two parts; 3)<span class="elsevierStyleHsp" style=""></span> among the variables showing parametric instability, the model is sectioned with respect to the variable with the highest instability (or showing the highest association with the response or the lowest p-value), and the cut-off point providing the greatest improvement is chosen for the model fit with respect to the error function; and finally, 4)<span class="elsevierStyleHsp" style=""></span> the procedure is repeated on each of the resulting subsamples until no further partitioning is possible. It is also possible to stop tree growth by specifying the minimum number of terminal nodes and the maximum tree depth, or even by specifying selection criteria, such as likelihood, Akaike information criteria or Bayesian information criterion (BIC), which is consistently more efficient in providing a goodness-of-fit measure, as it not only maximises the likelihood, but also minimises the complexity of the model in terms of parameters and data volume. The BIC selection criteria indicator is given by BIC<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>-2ln(L) +<span class="elsevierStyleHsp" style=""></span>k<span class="elsevierStyleHsp" style=""></span>ln(n), where L is the estimated likelihood, k is the number of fitted parameters and n is the number of available data. As a result of the fitting, the available data are sorted into k terminal nodes resulting from the partitioning of the predictor variables most related to the response (time to censored event), which provide different time-to-event probability profiles defined by the specific parametric fit within each node, with minimum BIC. In addition, the algorithm behaves automatically by pruning the tree (or stopping the partitioning procedure) when there is no gain in reducing the BIC, thus distinguishing relevant predictors as present in the tree (also automating the variable selection problem). An overall BIC is derived for the fit that allows model comparison, providing an objective measure for choosing the best parametric model (among reliable alternatives) or even the best initial subset of potential predictors.</p><p id="par0050" class="elsevierStylePara elsevierViewall">The parametric distribution used to model censored time-to-event HF<span class="elsevierStyleHsp" style=""></span>(T) data is lognormal. This assumes that ln(T) has a normal distribution, which works better than exponential or Weibull for these data (based on BIC). The parametric approach with the usual distributions requires the available data to be greater than zero; in our database, several observations (n<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>330) contain zero in the time-to-event data, representing people who died within a month of discharge; these zero data were increased by 0.5, the midpoint between the interval [0,1] (in fact, 0.1 was also used, without affecting the results). We evaluated two approaches with different sets of variables (as shown in <a class="elsevierStyleCrossRef" href="#tbl0005">Table 1</a>), and the same result was obtained (classification tree). Statistical analysis was performed with R (<a href="http://www.R-project.org">www.R-project.org</a>), and specifically with the partykit library<a class="elsevierStyleCrossRef" href="#bib0085"><span class="elsevierStyleSup">17</span></a> and the mob function in partykit.</p><elsevierMultimedia ident="tbl0005"></elsevierMultimedia></span></span><span id="sec0020" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0080">Results</span><p id="par0055" class="elsevierStylePara elsevierViewall"><a class="elsevierStyleCrossRef" href="#tbl0010">Table 2</a> shows the clinical characteristics of the 7,097 patients included in the study, according to whether or not they were readmitted for HF. Patients hospitalised for HF had a higher mean age, Charlson index and GRACE score (99% confidence level), and lower GFR, LVEF and haemoglobin values. The mean length of hospitalisation in patients readmitted for HF was 26.1<span class="elsevierStyleHsp" style=""></span>months, compared with a follow-up time of 53.8<span class="elsevierStyleHsp" style=""></span>months in patients who did not experience a second HF.</p><elsevierMultimedia ident="tbl0010"></elsevierMultimedia><p id="par0060" class="elsevierStylePara elsevierViewall">Median follow-up was 53<span class="elsevierStyleHsp" style=""></span>months (interquartile range: 18–77). A total of 1550 (21%) patients died, with 1049 (14.8%) deaths attributable to cardiovascular causes. A total of 964 (13.6%) patients were readmitted for HF. The percentage of women was higher in the HF readmission group. Diabetes, arterial hypertension, coronary heart disease, previous HF, peripheral arterial disease, chronic obstructive pulmonary disease (COPD), atrial fibrillation (AF) and HF in ACS were also higher in the HF readmission group. Revascularisation, current smoking, OMT, statins and antiplatelet therapy were more common in the non-HF readmission group. Angiotensin-converting enzyme inhibitor or angiotensin receptor blocker (ACEI-ARB) showed no association with HF readmission.</p><p id="par0065" class="elsevierStylePara elsevierViewall">When the algorithm was started with the predictor subsets M1 and M2, the resulting tree was the same, reinforcing the robustness of the fit. The BIC value for the fitted model was 12,108.36. As shown in <a class="elsevierStyleCrossRef" href="#fig0005">Fig. 1</a>, eight variables were identified as relevant for predicting HF hospitalisation time in the decision tree; 3 binary (HF in hospitalisation rate, diabetes and AF) and 5 quantitative: GFR (cut-off points 48.6, 49.9 and 67.3<span class="elsevierStyleHsp" style=""></span>ml/min/1.73<span class="elsevierStyleHsp" style=""></span>m<span class="elsevierStyleSup">2</span>), age (cut-off point 64<span class="elsevierStyleHsp" style=""></span>years), Charlson index (cut-off point<span class="elsevierStyleHsp" style=""></span>2), haemoglobin (cut-off point<span class="elsevierStyleHsp" style=""></span>11.2<span class="elsevierStyleHsp" style=""></span>mg/dl) and LVEF (cut-off points 45%, 52% and 54%).</p><elsevierMultimedia ident="fig0005"></elsevierMultimedia><p id="par0070" class="elsevierStylePara elsevierViewall">All other variables considered in sets M1 and M2 (<a class="elsevierStyleCrossRef" href="#tbl0005">Table 1</a>) were considered irrelevant for predicting time to adverse event in the presence of those selected. The model resulted in 15 clinical risk patterns (Appendix A, Supplementary Table S1). <a class="elsevierStyleCrossRef" href="#fig0010">Fig. 2</a> shows the HF readmission probability curves for time intervals 0 to 96<span class="elsevierStyleHsp" style=""></span>months (the longest time observed in the data), both for the fitted model as a result of recursive partitioning based on models with log-normal distribution for survival times, and for the Kaplan-Meier estimate, which resembles the behaviour of the data. The similarity of the fitted curve to the trend provided by the data reinforces the validity of the fit. These curves facilitate the prediction of the probability of an event in any given patient, once classified into one of 15 risk patterns based on their characteristics on admission to hospital. The lowest risk pattern, called RP1, for the highest time value in the period considered (96<span class="elsevierStyleHsp" style=""></span>months) gives an adverse event probability of only 0.009. A medium risk pattern, for example RP8, gives an adverse event probability at 96<span class="elsevierStyleHsp" style=""></span>months of 0.279. The highest risk pattern, RP15, yields a HF re-admission probability of 0.5 at 20.8<span class="elsevierStyleHsp" style=""></span>months and 0.76 at 96<span class="elsevierStyleHsp" style=""></span>months.</p><elsevierMultimedia ident="fig0010"></elsevierMultimedia><p id="par0075" class="elsevierStylePara elsevierViewall">Although the ultimate goal of our model is not the classification of individuals according to HF readmission risk but their classification into profile groups with similar time-to-event prediction curves, such classification is also possible through the survival prediction functions for each terminal node of the tree. This is done by setting a percentile in the survival function to estimate the time to event for each individual (given the profile/node into which it has been classified), and then comparing this value with its observed time, whatever the group: those who suffer the event and those who do not. With these comparisons we can evaluate the confusion matrix and then assess the usual validation metrics, such as accuracy, precision, recall and score<span class="elsevierStyleHsp" style=""></span>f1 (all of them with values between 0 and 1, and values close to<span class="elsevierStyleHsp" style=""></span>1, which provide a better model fit). These metrics have been evaluated for the percentile range between 0.05 and 0.95, in steps of 0.05, and are shown in <a class="elsevierStyleCrossRef" href="#tbl0015">Table 3</a> and <a class="elsevierStyleCrossRef" href="#fig0015">Fig. 3</a>. For the 0.5 percentile, the classification metrics are 0.860, 0.866, 0.991 and 0.924 for accuracy, precision, recall and score f1, respectively. These results provide reliable evidence of the performance of our model, even though it was not designed to classify whether or not individuals suffer from HF.</p><elsevierMultimedia ident="tbl0015"></elsevierMultimedia><elsevierMultimedia ident="fig0015"></elsevierMultimedia></span><span id="sec0025" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0085">Discussion</span><p id="par0080" class="elsevierStylePara elsevierViewall">The application of artificial intelligence algorithms to this large cohort of ACS patients revealed 15 distinct clinical patterns with different risks of HF hospitalisation after hospital discharge. These clinical patterns were created by considering the eight variables associated with the development of HF: age, HF during index hospitalisation, diabetes, atrial fibrillation, GFR, Charlson index, haemoglobin and LVEF. Since the clinical characteristics and event rates were similar to previous reports,<a class="elsevierStyleCrossRefs" href="#bib0010"><span class="elsevierStyleSup">2,4,14,15</span></a><span class="elsevierStyleSup">,</span><a class="elsevierStyleCrossRefs" href="#bib0090"><span class="elsevierStyleSup">18,19</span></a> we believe that the results may be representative and useful for clinical practice. Furthermore, our results may also have relevant implications for the management of ACS patients and the estimation of the actual individual risk of HF hospitalisation after hospital discharge.</p><p id="par0085" class="elsevierStylePara elsevierViewall">Due to their capabilities for automated learning from data, artificial intelligence and machine learning methods have become very popular in recent years, with cardiology being one of the beneficiaries.<a class="elsevierStyleCrossRefs" href="#bib0050"><span class="elsevierStyleSup">10,20</span></a> Automatically identifying predictors and characterising patient profiles based on available data, without subjective decisions attributable to existing literature or researcher bias, could help improve predictions and tailor care to different populations with different conditioning risk factors. Decision tree models, a type of machine learning procedure, have been proposed in different areas and clinical settings<a class="elsevierStyleCrossRefs" href="#bib0105"><span class="elsevierStyleSup">21,22</span></a> to select variables or predictors associated with a characteristic of interest and to generate different patient profiles and classifications based on these selected predictors. There are several algorithms for fitting decision trees, with CART<a class="elsevierStyleCrossRef" href="#bib0105"><span class="elsevierStyleSup">21</span></a> and those based on unbiased conditioning<a class="elsevierStyleCrossRef" href="#bib0085"><span class="elsevierStyleSup">17</span></a> being the most popular. Of course, some algorithms have been shown to be more efficient for classification with censored survival times.<a class="elsevierStyleCrossRefs" href="#bib0115"><span class="elsevierStyleSup">23–25</span></a> However, we have not found significant literature on cardiology related to recursive partitioning based on models.<a class="elsevierStyleCrossRef" href="#bib0085"><span class="elsevierStyleSup">17</span></a> One of the main advantages of these partitioning trees is their ability to predict time-to-event probabilities using a parametric approach with the available data, hence the purpose of this article. The objective of estimation based on parametric models is to minimise a certain function that quantifies the error between the expected survival time estimate and the observed value, and which depends on the variables included in the parametric model. The specification of a probability distribution for the survival data provides a natural way to measure goodness-of-fit through probability, and thus to compare and choose the best model among different alternatives.</p><p id="par0090" class="elsevierStylePara elsevierViewall">While hospitalisation rates for coronary heart disease have declined in recent decades, the rate of HF hospitalisations has stabilized.<a class="elsevierStyleCrossRef" href="#bib0130"><span class="elsevierStyleSup">26</span></a> HF readmissions in our study were quite high, as previously reported,<a class="elsevierStyleCrossRefs" href="#bib0010"><span class="elsevierStyleSup">2,4,8</span></a> and this clearly impairs patients’ quality of life and should induce changes in patient management, such as closer follow-up and treatment modifications.<a class="elsevierStyleCrossRef" href="#bib0005"><span class="elsevierStyleSup">1</span></a> Identifying patients at higher risk of HF readmission after hospitalisation for ACS is a key issue, and our artificial intelligence approach clearly identified a subset of patients who require more intensive follow-up and management.</p><p id="par0095" class="elsevierStylePara elsevierViewall">Artificial intelligence algorithms, and specifically model-based decision trees, provide a more accurate identification of risk factors<a class="elsevierStyleCrossRefs" href="#bib0055"><span class="elsevierStyleSup">11,22,27</span></a> through an automated procedure that provides the best fit in terms of efficiency, defined by maximising the likelihood and minimising the complexity of the model. Comparison of models is also possible in terms of the index selection criteria, as well as the choice of the best parametric way of predicting the data. We believe that artificial intelligence algorithms are a very useful, accurate and cost-effective tool. Conventional survival analyses, for example Cox regression models, assume that all people categorised by a certain variable have a similar prognosis; thereafter, the role of diabetes or renal dysfunction is analysed as a single variable. In contrast, artificial intelligence models are able to generate person-by-person analyses and risk patterns.<a class="elsevierStyleCrossRef" href="#bib0050"><span class="elsevierStyleSup">10</span></a> Our results demonstrate the differential risk of eight variables according to their combinations and with different cut-off points. This approach could provide even more realistic results and better applicability with more representative datasets. Our group proposed a clinical risk score to predict HF readmission using standard statistical analyses after identifying variables associated with an increased risk of this event.<a class="elsevierStyleCrossRef" href="#bib0025"><span class="elsevierStyleSup">5</span></a> Using artificial intelligence models, we were able to distinguish 15 risk patterns or clusters with distinctly different HF readmission probabilities, as opposed to approaches based on the sum of clinical score points. We have also created an application that will make our results publicly available (URL: <a href="https://javier-morales-socuellamos.shinyapps.io/TreeClass/">https://javier-morales-socuellamos.shinyapps.io/TreeClass/</a>).</p><p id="par0100" class="elsevierStylePara elsevierViewall">HF hospitalisations after ACS are associated with a fourfold increased risk of death<a class="elsevierStyleCrossRef" href="#bib0140"><span class="elsevierStyleSup">28</span></a> and should therefore be considered a priority for secondary prevention. Several interventions have demonstrated reductions in myocardial damage and left ventricular remodelling, as well as survival benefits in patients with ACS.<a class="elsevierStyleCrossRefs" href="#bib0040"><span class="elsevierStyleSup">8,29</span></a> However, no medical treatment showed a protective effect on the incidence of HF in our study, except revascularization.<a class="elsevierStyleCrossRefs" href="#bib0040"><span class="elsevierStyleSup">8,30</span></a> The lack of benefit of medical therapy could be attributed to the detailed analysis of interactions provided by the decision trees, but also to the low rate of some of the medical treatments that showed reductions in HF hospitalisations, such as SGLT2 transport inhibitors<a class="elsevierStyleCrossRef" href="#bib0145"><span class="elsevierStyleSup">29</span></a> or sacubitril-valsartan.<a class="elsevierStyleCrossRef" href="#bib0150"><span class="elsevierStyleSup">30</span></a> However, a previous analysis of this cohort showed a low rate of mineralocorticoid receptor antagonists and their lack of effect on HF hospitalisation or mortality.<a class="elsevierStyleCrossRef" href="#bib0015"><span class="elsevierStyleSup">3</span></a> Our decision tree models did not identify a preventive effect for any medical treatment on HF readmission, possibly reflecting an unmet need for personalised therapies for heterogeneous ACS patients. However, the risk patterns with the highest rates of HF readmission were those combining the presence of HF in the ACS index with age above 64<span class="elsevierStyleHsp" style=""></span>years, renal dysfunction, anaemia, diabetes or left ventricular dysfunction in different sequences.</p><p id="par0105" class="elsevierStylePara elsevierViewall">Validation metrics have also been evaluated for the classification of patients who are or are not readmitted for HF. Although this is not the focus of our model, the validation results are indeed good for the classification obtained with the usual percentile, which normally is 0.5.</p><p id="par0110" class="elsevierStylePara elsevierViewall">Our study has some limitations. First, as with all prospective observational studies, there are some inherent limitations, such as lack of randomisation, long-term variations in medical treatments and uncontrolled variables. The diagnosis of HF at onset could also be disputed, but since we analysed only hospital readmissions, we believe that we included real cases of HF and did not count other cases of dyspnoea or respiratory disorders. Since the study period was quite long, the use of concurrent treatments might have changed over time. Also, loss to follow-up could have led to attrition bias or loss bias, caused by the systematic difference in dropouts, losses or adherence between the compared groups. However, overall, the clinical characteristics and incidence of long-term events were similar to previous reports,<a class="elsevierStyleCrossRefs" href="#bib0010"><span class="elsevierStyleSup">2,4,14,15</span></a><span class="elsevierStyleSup">,</span><a class="elsevierStyleCrossRefs" href="#bib0090"><span class="elsevierStyleSup">18–20</span></a> so we believe that the limitations of the study may not have a relevant impact on our results. Further research is needed to address these issues, but we believe that our results can be used in a clinical setting to stratify the risk of developing HF and thus plan both pharmacological treatment and a follow-up programme before discharge from an ACS admission.</p></span><span id="sec0030" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0090">Conclusions</span><p id="par0115" class="elsevierStylePara elsevierViewall">The artificial intelligence analysis identified eight leading variables capable of predicting this event with high accuracy, and generated differentiated clinical risk patterns in terms of the likelihood of being hospitalised for HF.</p></span><span id="sec0035" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0095">Ethical considerations</span><p id="par0120" class="elsevierStylePara elsevierViewall">The research ethics committee of the Hospital Universitario de San Juan approved the study protocol and informed consent.</p></span><span id="sec0040" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0100">Funding</span><p id="par0125" class="elsevierStylePara elsevierViewall">This work has received a grant from the <span class="elsevierStyleGrantSponsor" id="gs0005">Conselleria de Sanitat Valencia</span> as part of the PROMETEO/2021/063 project of the Ministerio de Economía y Competencia del Instituto Carlos<span class="elsevierStyleHsp" style=""></span>III (<span class="elsevierStyleGrantNumber" refid="gs0005">CB16/11/00226</span> and <span class="elsevierStyleGrantNumber" refid="gs0005">CB16/11/00420</span>), and also from the <span class="elsevierStyleGrantSponsor" id="gs0010">Fundación para el Fomento de la Investigación Sanitaria y Biomédica de la Comunitat Valenciana</span> (FISABIO) in the 2021 call for applications for UMH-Fisabio joint Preparatory Actions and Innovation Projects.</p></span><span id="sec0045" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0105">Authors’ contribution</span><p id="par0130" class="elsevierStylePara elsevierViewall">Concept and first draft: Alberto Cordero and Vicente Bertomeu-Gonzalez.</p><p id="par0135" class="elsevierStylePara elsevierViewall">Data collection: Belén Álvarez-Álvarez, David Escribano, Moisés Rodríguez-Manero, Belén Cid-Alvarez, José M. García-Acuña and M. Amparo Quintanilla.</p><p id="par0140" class="elsevierStylePara elsevierViewall">Statistical analysis: José V. Segura, Javier Morales and Asunción Martínez-Mayoral</p><p id="par0145" class="elsevierStylePara elsevierViewall">Manuscript revision: José Ramón González-Juanatey.</p></span><span id="sec0050" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0110">Conflict of interest</span><p id="par0150" class="elsevierStylePara elsevierViewall">Alberto Cordero reports lecture fees from AstraZeneca, AMGEN, Bristol-Myers Squibb, Ferrer, Boehringer Ingelheim, MSD, Daiichi Sankyo, Novartis, Novo Nordisk and Amarin, and consultancy fees from AstraZeneca, Ferrer, AMGEN, Novartis, Lilly, Novo Nordisk and Amarin.</p><p id="par0155" class="elsevierStylePara elsevierViewall">Vicente Bertomeu-González reports lecture fees from Daiichi Sankyo, Boehringer Ingelheim, Bayer, Pfizer-BMS, LivaNova, Ferrer, Cardiome, MSD, and a research grant from Medtronic Ibérica.</p><p id="par0160" class="elsevierStylePara elsevierViewall">Moisés Rodríguez-Mañero reports research grant from Fundación Mutua Madrileña, Biosense Webseter, Medtronic, Instituto de Salud Carlos<span class="elsevierStyleHsp" style=""></span>III and the Ministry of Economy and Competitiveness (Spain).</p><p id="par0165" class="elsevierStylePara elsevierViewall">José Ramón González-Juanatey reports lecture fees from Eli Lilly, Daiichi Sankyo, Bayer, Pfizer, Abbott, Boehringer Ingelheim, MSD, Ferrer and Bristol-Myers Squibb; consultancy payments from AstraZeneca, Ferrer, Bayer, Boehringer-Ingelheim, and research grant with AstraZeneca, Boehringer-Ingelheim and Daiichi-Sankyo.</p><p id="par0170" class="elsevierStylePara elsevierViewall">The other authors have no conflict of interest.</p></span></span>" "textoCompletoSecciones" => array:1 [ "secciones" => array:14 [ 0 => array:3 [ "identificador" => "xres2235422" "titulo" => "Abstract" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0005" "titulo" => "Background" ] 1 => array:2 [ "identificador" => "abst0010" "titulo" => "Methods" ] 2 => array:2 [ "identificador" => "abst0015" "titulo" => "Results" ] 3 => array:2 [ "identificador" => "abst0020" "titulo" => "Conclusions" ] ] ] 1 => array:2 [ "identificador" => "xpalclavsec1871114" "titulo" => "Keywords" ] 2 => array:3 [ "identificador" => "xres2235421" "titulo" => "Resumen" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0025" "titulo" => "Introducción" ] 1 => array:2 [ "identificador" => "abst0030" "titulo" => "Métodos" ] 2 => array:2 [ "identificador" => "abst0035" "titulo" => "Resultados" ] 3 => array:2 [ "identificador" => "abst0040" "titulo" => "Conclusiones" ] ] ] 3 => array:2 [ "identificador" => "xpalclavsec1871115" "titulo" => "Palabras clave" ] 4 => array:2 [ "identificador" => "sec0005" "titulo" => "Introduction" ] 5 => array:3 [ "identificador" => "sec0010" "titulo" => "Methods" "secciones" => array:1 [ 0 => array:2 [ "identificador" => "sec0015" "titulo" => "Statistical analysis" ] ] ] 6 => array:2 [ "identificador" => "sec0020" "titulo" => "Results" ] 7 => array:2 [ "identificador" => "sec0025" "titulo" => "Discussion" ] 8 => array:2 [ "identificador" => "sec0030" "titulo" => "Conclusions" ] 9 => array:2 [ "identificador" => "sec0035" "titulo" => "Ethical considerations" ] 10 => array:2 [ "identificador" => "sec0040" "titulo" => "Funding" ] 11 => array:2 [ "identificador" => "sec0045" "titulo" => "Authors’ contribution" ] 12 => array:2 [ "identificador" => "sec0050" "titulo" => "Conflict of interest" ] 13 => array:1 [ "titulo" => "References" ] ] ] "pdfFichero" => "main.pdf" "tienePdf" => true "fechaRecibido" => "2023-06-30" "fechaAceptado" => "2024-01-28" "PalabrasClave" => array:2 [ "en" => array:1 [ 0 => array:4 [ "clase" => "keyword" "titulo" => "Keywords" "identificador" => "xpalclavsec1871114" "palabras" => array:5 [ 0 => "Acute coronary syndrome" 1 => "Heart failure" 2 => "Artificial intelligence" 3 => "Decision tree model" 4 => "Machine learning" ] ] ] "es" => array:1 [ 0 => array:4 [ "clase" => "keyword" "titulo" => "Palabras clave" "identificador" => "xpalclavsec1871115" "palabras" => array:5 [ 0 => "Síndrome coronario agudo" 1 => "Insuficiencia cardiaca" 2 => "Inteligencia artificial" 3 => "Modelo de árbol de decisión" 4 => "Aprendizaje automático" ] ] ] ] "tieneResumen" => true "resumen" => array:2 [ "en" => array:3 [ "titulo" => "Abstract" "resumen" => "<span id="abst0005" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0010">Background</span><p id="spar0045" class="elsevierStyleSimplePara elsevierViewall">Coronary heart disease is the leading cause of heart failure (HF), and tools are needed to identify patients with a higher probability of developing HF after an acute coronary syndrome (ACS). Artificial intelligence (AI) has proven to be useful in identifying variables related to the development of cardiovascular complications.</p></span> <span id="abst0010" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0015">Methods</span><p id="spar0050" class="elsevierStyleSimplePara elsevierViewall">We included all consecutive patients discharged after ACS in two Spanish centers between 2006 and 2017. Clinical data were collected and patients were followed up for a median of 53 months. Decision tree models were created by the model-based recursive partitioning algorithm.</p></span> <span id="abst0015" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0020">Results</span><p id="spar0055" class="elsevierStyleSimplePara elsevierViewall">The cohort consisted of 7,097 patients with a median follow-up of 53 months (interquartile range 18–77). The readmission rate for HF was 13.6% (964 patients). Eight relevant variables were identified to predict HF hospitalization time: HF at index hospitalization, diabetes, atrial fibrillation, glomerular filtration rate, age, Charlson index, hemoglobin, and left ventricular ejection fraction. The decision tree model provided 15 clinical risk patterns with significantly different HF readmission rates.</p></span> <span id="abst0020" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0025">Conclusions</span><p id="spar0060" class="elsevierStyleSimplePara elsevierViewall">The decision tree model, obtained by AI, identified 8 leading variables capable of predicting HF and generated 15 differentiated clinical patterns with respect to the probability of being hospitalized for HF. An electronic application was created and made available for free.</p></span>" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0005" "titulo" => "Background" ] 1 => array:2 [ "identificador" => "abst0010" "titulo" => "Methods" ] 2 => array:2 [ "identificador" => "abst0015" "titulo" => "Results" ] 3 => array:2 [ "identificador" => "abst0020" "titulo" => "Conclusions" ] ] ] "es" => array:3 [ "titulo" => "Resumen" "resumen" => "<span id="abst0025" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0035">Introducción</span><p id="spar0065" class="elsevierStyleSimplePara elsevierViewall">La cardiopatía isquémica es la primera causa de insuficiencia cardíaca (IC) y se necesitan herramientas para identificar a los pacientes con mayor probabilidad de desarrollar IC tras un síndrome coronario agudo (SCA). La inteligencia artificial (IA) ha demostrado ser útil para identificar variables relacionadas con el desarrollo de complicaciones cardiovasculares.</p></span> <span id="abst0030" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0040">Métodos</span><p id="spar0070" class="elsevierStyleSimplePara elsevierViewall">Incluimos todos los consecutivos dados de alta tras SCA en dos centros españoles entre 2006 y 2017. Se recopilaron datos clínicos y se realizó un seguimiento de los pacientes durante una mediana de 53 meses. Los modelos de árboles de decisión fueron creados por el algoritmo de partición recursivo basado en modelos.</p></span> <span id="abst0035" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0045">Resultados</span><p id="spar0075" class="elsevierStyleSimplePara elsevierViewall">La cohorte fue de 7097 pacientes con una mediana de seguimiento de 53 meses (rango intercuartílico 18-77). La tasa de reingreso por IC fue del 13,6% (964 pacientes). Se identificaron ocho variables relevantes para predecir el tiempo de hospitalización por IC: IC en la hospitalización índice, diabetes, fibrilación auricular, tasa de filtración glomerular, edad, índice de Charlson, hemoglobina y fracción de eyección del ventrículo izquierdo. El modelo de árbol de decisiones proporcionó 15 patrones de riesgo clínico con tasas de reingreso por IC estadísticamente diferentes.</p></span> <span id="abst0040" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0050">Conclusiones</span><p id="spar0080" class="elsevierStyleSimplePara elsevierViewall">El modelo de árbol de decisión, obtenido por IA, identificó 8 variables principales capaces de predecir IC y generó 15 patrones clínicos diferenciados con respecto a la probabilidad de ser hospitalizado por IC. Se creó una aplicación electrónica gratuita.</p></span>" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0025" "titulo" => "Introducción" ] 1 => array:2 [ "identificador" => "abst0030" "titulo" => "Métodos" ] 2 => array:2 [ "identificador" => "abst0035" "titulo" => "Resultados" ] 3 => array:2 [ "identificador" => "abst0040" "titulo" => "Conclusiones" ] ] ] ] "apendice" => array:1 [ 0 => array:1 [ "seccion" => array:1 [ 0 => array:4 [ "apendice" => "<p id="par0180" class="elsevierStylePara elsevierViewall">The following is Supplementary data to this article:<elsevierMultimedia ident="upi0005"></elsevierMultimedia></p>" "etiqueta" => "Appendix A" "titulo" => "Supplementary data" "identificador" => "sec0060" ] ] ] ] "multimedia" => array:7 [ 0 => array:8 [ "identificador" => "fig0005" "etiqueta" => "Fig. 1" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr1.jpeg" "Alto" => 2720 "Ancho" => 2675 "Tamanyo" => 327220 ] ] "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0005" "detalle" => "Fig. " "rol" => "short" ] ] "descripcion" => array:1 [ "en" => "<p id="spar0005" class="elsevierStyleSimplePara elsevierViewall">Decision tree obtained from model-based recursive partitioning to predict HF time with censored data and log-normal distribution for survival times. Terminal nodules represent patterns derived from heart failure patients experiencing acute coronary syndrome.</p>" ] ] 1 => array:8 [ "identificador" => "fig0010" "etiqueta" => "Fig. 2" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr2.jpeg" "Alto" => 2386 "Ancho" => 2508 "Tamanyo" => 402367 ] ] "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0010" "detalle" => "Fig. " "rol" => "short" ] ] "descripcion" => array:1 [ "en" => "<p id="spar0010" class="elsevierStyleSimplePara elsevierViewall">Time to heart failure readmission according to time, for the 15 patterns (nodes in the figure) identified from the tree based on the fitted model. The red curves show the crude incidence of heart failure readmission and the blue curves show the adjusted incidence obtained by the multivariate model.</p>" ] ] 2 => array:8 [ "identificador" => "fig0015" "etiqueta" => "Fig. 3" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr3.jpeg" "Alto" => 1531 "Ancho" => 2508 "Tamanyo" => 134684 ] ] "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0015" "detalle" => "Fig. " "rol" => "short" ] ] "descripcion" => array:1 [ "en" => "<p id="spar0015" class="elsevierStyleSimplePara elsevierViewall">Evolution of validation metrics to classify individuals as having a HF or not, for a range of percentiles on the time-to-event prediction curves between 0.05 and 0.95.</p>" ] ] 3 => array:8 [ "identificador" => "tbl0005" "etiqueta" => "Table 1" "tipo" => "MULTIMEDIATABLA" "mostrarFloat" => true "mostrarDisplay" => false "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0020" "detalle" => "Table " "rol" => "short" ] ] "tabla" => array:2 [ "leyenda" => "<p id="spar0025" class="elsevierStyleSimplePara elsevierViewall">ACEi: angiotensin-converting enzyme inhibitor; ACS: acute coronary syndrome; HF: heart failure; ARB: angiotensin receptor blocker; COPD: chronic obstructive pulmonary disease; HF: heart failure.</p>" "tablatextoimagen" => array:1 [ 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"> \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">Shared predictors \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">Specific predictors \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">M1 \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"><span class="elsevierStyleItalic">Numerical:</span> age, glomerular filtration rate, ejection fraction, Charlson index, haemoglobin \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"><span class="elsevierStyleItalic">Dichotomous:</span> optimal medical treatment \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">M2 \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"><span class="elsevierStyleItalic">Dichotomous:</span> ischaemic heart disease, peripheral artery disease, diabetes mellitus, COPD, atrial fibrillation, current smoker, hypertension, HF in ACS, previous HF, revascularisation and gender. \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"><span class="elsevierStyleItalic">Numeric:</span> GRACE score<span class="elsevierStyleItalic">Dichotomous:</span> antiplatelet, ACEi-ARB, beta-blocker, statins \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab3643972.png" ] ] ] ] "descripcion" => array:1 [ "en" => "<p id="spar0020" class="elsevierStyleSimplePara elsevierViewall">Initial subgroups of potential predictors considered for the partitioning model.</p>" ] ] 4 => array:8 [ "identificador" => "tbl0010" "etiqueta" => "Table 2" "tipo" => "MULTIMEDIATABLA" "mostrarFloat" => true "mostrarDisplay" => false "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0025" "detalle" => "Table " "rol" => "short" ] ] "tabla" => array:2 [ "leyenda" => "<p id="spar0035" class="elsevierStyleSimplePara elsevierViewall">ACE: angiotensin-converting enzyme inhibitor; COPD: chronic obstructive pulmonary disease; GFR: glomerular filtration rate; ACS: acute coronary syndrome; HF: heart failure; ACS: acute coronary syndrome with ST-segment elevation; ACS: acute coronary syndrome with ST-segment elevation; GFR: glomerular filtration rate; HF: heart failure; COPD: chronic obstructive pulmonary disease.</p>" "tablatextoimagen" => array:1 [ 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"> \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"> \t\t\t\t\t\t\n \t\t\t\t\t\t</th><th class="td-with-role" title="\n \t\t\t\t\ttable-head\n \t\t\t\t ; entry_with_role_colgroup " colspan="2" align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Readmission for heart failure</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"> \t\t\t\t\t\t\n \t\t\t\t\t\t</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">Variable \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">Total \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 \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">Yes \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">p \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">n</span> \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">7,097 \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">6,133 (86,4%) \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">964 (13,6%) \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"> \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"><span class="elsevierStyleItalic">Age</span> \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">66.6 (12.9) \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">65.4 (12.9) \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">74.2 (9.6) \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Women</span> \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">27.1% \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">26.1% \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">33.9% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Diabetes mellitus</span> \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">27.8% \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">24.7% \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">47.8% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Hypertension</span> \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">57.7% \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">54.9% \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">75.3% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Smokers</span> \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">28.4% \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">30.4% \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">15.5% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Ischaemic heart disease</span> \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">22.5% \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">20.6% \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">34.9% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Heart failure</span> \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">3.6% \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">2.5% \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">10.4% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Peripheral arterial disease</span> \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">8.2% \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">6.9% \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">17.0% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">COPD</span> \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">9.6% \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">8.4% \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">17.5% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Atrial fibrillation</span> \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">11.1% \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">9.2% \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">23.1% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Charlson Index</span> \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">2.2 (2.2) \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">2.1 (2.1) \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">3.2 (2.5) \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">SCACEST</span> \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">34.3% \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">35.4% \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">26.4% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">HF at admission</span> \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">16.2% \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">12.9% \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">37.3% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">GRACE score</span> \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">140.0 (36.7) \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">137.0 (35.9) \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">160.1 (35.8) \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">GFR (ml/min/1,72<span class="elsevierStyleHsp" style=""></span>m<span class="elsevierStyleSup">2</span>)</span> \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">75.2 (23.1) \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">77.5 (22.3) \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">60.5 (22.7) \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Ejection fraction</span> \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">55.4 (10.9) \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">56.1 (10.4) \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">50.9 (13.1) \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Haemoglobin (g/dl)</span> \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">13.9 (2.9) \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">14.0 (2.4) \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">13.2 (5.1) \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Revascularisation</span> \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">76.5% \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">78.2% \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">65.4% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleItalic">Discharge treatment</span> \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"> \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"> \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"> \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"> \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"><span class="elsevierStyleHsp" style=""></span>Beta-blockers \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">73.8% \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">75.4% \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">63.6% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleHsp" style=""></span>ACEi-ARB \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">67.5% \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">67.2% \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">69.2% \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">0.245 \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"><span class="elsevierStyleHsp" style=""></span>Statins \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">86.5% \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">87.1% \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">83.2% \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">0.001 \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"><span class="elsevierStyleHsp" style=""></span>Anti-platelet \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">93.8% \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">94.6% \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">88.8% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \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"><span class="elsevierStyleHsp" style=""></span>Optimal medical treatment \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">48.0% \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">49.5% \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">38.3% \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"><<span class="elsevierStyleHsp" style=""></span>0.001 \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab3643971.png" ] ] ] ] "descripcion" => array:1 [ "en" => "<p id="spar0030" class="elsevierStyleSimplePara elsevierViewall">Cohort description according to whether or not they were readmitted for heart failure.</p>" ] ] 5 => array:8 [ "identificador" => "tbl0015" "etiqueta" => "Table 3" "tipo" => "MULTIMEDIATABLA" "mostrarFloat" => true "mostrarDisplay" => false "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0030" "detalle" => "Table " "rol" => "short" ] ] "tabla" => array:1 [ "tablatextoimagen" => array:1 [ 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">Percentile \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">Accuracy \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">Precision \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">Recall \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">F1 Score \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">0.95 \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">0.864 \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">0.864 \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">1.000 \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">0.927 \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">0.90 \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">0.864 \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">0.864 \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">1.000 \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">0.927 \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">0.85 \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">0.864 \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">0.864 \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">1.000 \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">0.927 \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">0.80 \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">0.864 \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">0.864 \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">1.000 \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">0.927 \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">0.75 \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">0.864 \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">0.864 \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">1.000 \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">0.927 \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">0.70 \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">0.862 \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">0.864 \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">0.998 \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">0.926 \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">0.65 \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">0.862 \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">0.865 \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">0.996 \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">0.926 \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">0.60 \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">0.861 \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">0.865 \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">0.995 \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">0.925 \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">0.55 \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">0.861 \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">0.865 \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">0.994 \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">0.925 \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">0.50 \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">0.860 \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">0.866 \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">0.991 \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">0.924 \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">0.45 \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">0.855 \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">0.866 \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">0.985 \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">0.922 \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">0.40 \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">0.850 \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">0.868 \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">0.974 \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">0.918 \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">0.35 \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">0.832 \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">0.870 \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">0.947 \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">0.907 \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">0.30 \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">0.805 \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">0.872 \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">0.908 \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">0.889 \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">0.25 \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">0.774 \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">0.876 \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">0.860 \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">0.868 \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">0.20 \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">0.730 \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">0.879 \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">0.797 \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">0.836 \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">0.15 \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">0.680 \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">0.884 \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">0.725 \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">0.797 \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">0.10 \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">0.580 \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">0.886 \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">0.590 \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">0.708 \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">0.05 \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">0.452 \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">0.898 \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">0.412 \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">0.565 \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab3643970.png" ] ] ] ] "descripcion" => array:1 [ "en" => "<p id="spar0040" class="elsevierStyleSimplePara elsevierViewall">Validation measures for event classification at different percentiles with time-to-event curves.</p>" ] ] 6 => array:5 [ "identificador" => "upi0005" "tipo" => "MULTIMEDIAECOMPONENTE" "mostrarFloat" => false "mostrarDisplay" => true "Ecomponente" => array:2 [ "fichero" => "mmc1.doc" "ficheroTamanyo" => 142848 ] ] ] "bibliografia" => array:2 [ "titulo" => "References" "seccion" => array:1 [ 0 => array:2 [ "identificador" => "bibs0005" "bibliografiaReferencia" => array:30 [ 0 => array:3 [ "identificador" => "bib0005" "etiqueta" => "1" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "2023 Focused Update of the 2021 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure: developed by the task force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC) With the special contribution of the Heart Failure Association (HFA) of the ESC" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "T.A. McDonagh" 1 => "M. Metra" 2 => "M. Adamo" 3 => "R.S. Gardner" 4 => "A. Baumbach" 5 => "M. Böhm" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1093/eurheartj/ehad195" "Revista" => array:6 [ "tituloSerie" => "Eur Heart J" "fecha" => "2023" "volumen" => "44" "paginaInicial" => "3627" "paginaFinal" => "3639" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/37622666" "web" => "Medline" ] ] ] ] ] ] ] ] 1 => array:3 [ "identificador" => "bib0010" "etiqueta" => "2" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Risk factors for heart failure: 20-year population-based trends by sex, socioeconomic status, and ethnicity" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "C.A. Lawson" 1 => "F. Zaccardi" 2 => "I. Squire" 3 => "H. Okhai" 4 => "M. Davies" 5 => "W. Huang" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1161/CIRCHEARTFAILURE.119.006472" "Revista" => array:3 [ "tituloSerie" => "Circ Heart Fail" "fecha" => "2020" "volumen" => "13" ] ] ] ] ] ] 2 => array:3 [ "identificador" => "bib0015" "etiqueta" => "3" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Determinants and prognostic impact of heart failure and left ventricular ejection fraction in acute coronary syndrome settings" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "R. Agra Bermejo" 1 => "A. Cordero" 2 => "J.M. García-Acuña" 3 => "I. Gómez Otero" 4 => "A. Varela Román" 5 => "Á Martínez" ] ] ] ] ] "host" => array:2 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Rev Esp Cardiol (Eng Ed)" "fecha" => "2018" "volumen" => "71" "paginaInicial" => "820" "paginaFinal" => "828" ] ] 1 => array:1 [ "WWW" => array:1 [ "link" => "https://www.revespcardiol.org/en-determinants-prognostic-impact-heart-failure-articulo-S1885585717305133" ] ] ] ] ] ] 3 => array:3 [ "identificador" => "bib0020" "etiqueta" => "4" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Heart failure is a common complication after acute myocardial infarction in patients with diabetes: a nationwide study in the SWEDEHEART registry" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:5 [ 0 => "V. Ritsinger" 1 => "T. Nyström" 2 => "N. Saleh" 3 => "B. Lagerqvist" 4 => "A. Norhammar" ] ] ] ] ] "host" => array:2 [ 0 => array:2 [ "doi" => "10.1177/2047487319901063" "Revista" => array:6 [ "tituloSerie" => "Eur J Prev Cardiol" "fecha" => "2020" "volumen" => "27" "paginaInicial" => "1890" "paginaFinal" => "1901" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32019365" "web" => "Medline" ] ] ] ] 1 => array:2 [ "doi" => "10.1177/2047487319901063" "WWW" => array:1 [ "link" => "https://academic.oup.com/eurjpc/article/27/17/1890/6125548" ] ] ] ] ] ] 4 => array:3 [ "identificador" => "bib0025" "etiqueta" => "5" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Proposal of a novel clinical score to predict heart failure incidence in long-term survivors of acute coronary syndromes" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "M. Rodriguez-Manero" 1 => "A. Cordero" 2 => "O. Kreidieh" 3 => "J.M. Garcia-Acuna" 4 => "J. Seijas" 5 => "R.M. Agra-Bermejo" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.ijcard.2017.07.084" "Revista" => array:6 [ "tituloSerie" => "Int J Cardiol" "fecha" => "2017" "volumen" => "243" "paginaInicial" => "211" "paginaFinal" => "215" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/28747024" "web" => "Medline" ] ] ] ] ] ] ] ] 5 => array:3 [ "identificador" => "bib0030" "etiqueta" => "6" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Temporal trends between association of evidence-based treatment and outcomes in patients with non-ST-elevation myocardial infarction" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "B. Alvarez-Alvarez" 1 => "C. Abou Jokh Casas" 2 => "J.M. Garcia Acuña" 3 => "B. Cid Alvarez" 4 => "R.M. Agra Bermejo" 5 => "A. Cordero Fort" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.ijcard.2018.02.110" "Revista" => array:6 [ "tituloSerie" => "Int J Cardiol" "fecha" => "2018" "volumen" => "260" "paginaInicial" => "1" "paginaFinal" => "6" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/29506939" "web" => "Medline" ] ] ] ] ] ] ] ] 6 => array:3 [ "identificador" => "bib0035" "etiqueta" => "7" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Proposal of a novel clinical score to predict heart failure incidence in long-term survivors of acute coronary syndromes" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "M. Rodriguez-Manero" 1 => "A. Cordero" 2 => "O. Kreidieh" 3 => "J.M. Garcia-Acuna" 4 => "J. Seijas" 5 => "R.M. Agra-Bermejo" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.ijcard.2017.07.084" "Revista" => array:6 [ "tituloSerie" => "Int J Cardiol" "fecha" => "2017" "volumen" => "243" "paginaInicial" => "211" "paginaFinal" => "215" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/28747024" "web" => "Medline" ] ] ] ] ] ] ] ] 7 => array:3 [ "identificador" => "bib0040" "etiqueta" => "8" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "New-onset heart failure after acute coronary syndrome in patients without heart failure or left ventricular dysfunction" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "A. Cordero" 1 => "M. Rodríguez-Mañero" 2 => "V. Bertomeu-González" 3 => "J.M. García-Acuña" 4 => "A. Baluja" 5 => "R. Agra-Bermejo" ] ] ] ] ] "host" => array:2 [ 0 => array:2 [ "doi" => "10.1016/j.rec.2020.03.011" "Revista" => array:6 [ "tituloSerie" => "Rev Esp Cardiol (Engl Ed)" "fecha" => "2021" "volumen" => "74" "paginaInicial" => "494" "paginaFinal" => "501" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32448726" "web" => "Medline" ] ] ] ] 1 => array:2 [ "doi" => "10.1016/j.rec.2020.03.011" "WWW" => array:1 [ "link" => "https://pubmed.ncbi.nlm.nih.gov/32448726/" ] ] ] ] ] ] 8 => array:3 [ "identificador" => "bib0045" "etiqueta" => "9" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Timing of first postdischarge follow-up and medication adherence after acute myocardial infarction" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:6 [ 0 => "K.F. Faridi" 1 => "E.D. Peterson" 2 => "L.A. McCoy" 3 => "L. Thomas" 4 => "J. Enriquez" 5 => "T.Y. Wang" ] ] ] ] ] "host" => array:2 [ 0 => array:2 [ "doi" => "10.1001/jamacardio.2016.0001" "Revista" => array:6 [ "tituloSerie" => "JAMA Cardiol" "fecha" => "2016" "volumen" => "1" "paginaInicial" => "147" "paginaFinal" => "155" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/27437885" "web" => "Medline" ] ] ] ] 1 => array:2 [ "doi" => "10.1001/jamacardio.2016.0001" "WWW" => array:1 [ "link" => "https://pubmed.ncbi.nlm.nih.gov/27437885/" ] ] ] ] ] ] 9 => array:3 [ "identificador" => "bib0050" "etiqueta" => "10" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Artificial intelligence in cardiology" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "K.W. Johnson" 1 => "J. Torres Soto" 2 => "B.S. Glicksberg" 3 => "K. Shameer" 4 => "R. Miotto" 5 => "M. Ali" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.jacc.2018.03.521" "Revista" => array:6 [ "tituloSerie" => "J Am Coll Cardiol" "fecha" => "2018" "volumen" => "71" "paginaInicial" => "2668" "paginaFinal" => "2679" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/29880128" "web" => "Medline" ] ] ] ] ] ] ] ] 10 => array:3 [ "identificador" => "bib0055" "etiqueta" => "11" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Modelos generativos y sus aplicaciones en biomedicina" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "Á Iglesias-Puzas" 1 => "P. Boixeda" 2 => "E. López-Bran" ] ] ] ] ] "host" => array:2 [ 0 => array:2 [ "doi" => "10.1016/j.medcli.2020.01.026" "Revista" => array:5 [ "tituloSerie" => "Med Clin (Barc)" "fecha" => "2021" "volumen" => "156" "paginaInicial" => "471" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32336472" "web" => "Medline" ] ] ] ] 1 => array:2 [ "doi" => "10.1016/j.medcli.2020.01.026" "WWW" => array:1 [ "link" => "https://www.elsevier.es/es-revista-medicina-clinica-2-articulo-modelos-generativos-sus-aplicaciones-biomedicina-S0025775320301652" ] ] ] ] ] ] 11 => array:3 [ "identificador" => "bib0060" "etiqueta" => "12" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "2020 ESC Guidelines for the management of acute coronary syndromes in patients presenting without persistent ST-segment elevation: the Task Force for the management of acute coronary syndromes in patients presenting without persistent ST-segment elevation of the European Society of Cardiology (ESC)" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "J.P. Collet" 1 => "H. Thiele" 2 => "E. Barbato" 3 => "O. Barthélémy" 4 => "J. Bauersachs" 5 => "D.L. Bhatt" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1093/eurheartj/ehaa575" "Revista" => array:6 [ "tituloSerie" => "Eur Heart J" "fecha" => "2021" "volumen" => "42" "paginaInicial" => "1289" "paginaFinal" => "1367" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32860058" "web" => "Medline" ] ] ] ] ] ] ] ] 12 => array:3 [ "identificador" => "bib0065" "etiqueta" => "13" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A new equation to estimate glomerular filtration rate" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "A.S. Levey" 1 => "L.A. Stevens" 2 => "C.H. Schmid" 3 => "Y.L. Zhang" 4 => "A.F. Castro 3rd" 5 => "H.I. Feldman" ] ] ] ] ] "host" => array:2 [ 0 => array:2 [ "doi" => "10.7326/0003-4819-150-9-200905050-00006" "Revista" => array:6 [ "tituloSerie" => "Ann Intern Med" "fecha" => "2009" "volumen" => "150" "paginaInicial" => "604" "paginaFinal" => "612" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/19414839" "web" => "Medline" ] ] ] ] 1 => array:2 [ "doi" => "10.7326/0003-4819-150-9-200905050-00006" "WWW" => array:1 [ "link" => "https://www.ncbi.nlm.nih.gov/pubmed/19414839" ] ] ] ] ] ] 13 => array:3 [ "identificador" => "bib0070" "etiqueta" => "14" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Influencia de la comorbilidad en el tratamiento intrahospitalario y al alta de los pacientes con infarto de miocardio" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "L. Facila Rubio" 1 => "J. Nunez Villota" 2 => "V. Bertomeu Gonzalez" 3 => "J. Sanchis Fores" 4 => "V. Bodi Peris" 5 => "L. Consuegra Sanchez" ] ] ] ] ] "host" => array:2 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Med Clin (Barc)" "fecha" => "2005" "volumen" => "124" "paginaInicial" => "447" "paginaFinal" => "450" ] ] 1 => array:1 [ "WWW" => array:1 [ "link" => "http://www.ncbi.nlm.nih.gov/pubmed/15826580" ] ] ] ] ] ] 14 => array:3 [ "identificador" => "bib0075" "etiqueta" => "15" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Valor pronóstico del índice de Charlson en la mortalidad en pacientes con embolia pulmonar asociada a cáncer frente a embolia pulmonar no tumoral" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "L.A. Fernández Bermejo" 1 => "C. Gutiérrez Ortega" 2 => "J.J. Jareño Esteban" ] ] ] ] ] "host" => array:2 [ 0 => array:2 [ "doi" => "10.1016/j.medcli.2021.02.007" "Revista" => array:6 [ "tituloSerie" => "Med Clin (Barc)" "fecha" => "2022" "volumen" => "158" "paginaInicial" => "201" "paginaFinal" => "205" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/33836857" "web" => "Medline" ] ] ] ] 1 => array:2 [ "doi" => "10.1016/j.medcli.2021.02.007" "WWW" => array:1 [ "link" => "https://www.elsevier.es/es-revista-medicina-clinica-2-articulo-valor-pronostico-del-indice-charlson-S0025775321001263" ] ] ] ] ] ] 15 => array:3 [ "identificador" => "bib0080" "etiqueta" => "16" "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 (TRIPOD): the TRIPOD statement" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "G.S. Collins" 1 => "J.B. Reitsma" 2 => "D.G. Altman" 3 => "K.G. 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" ] ] ] ] ] ] ] ] 16 => array:3 [ "identificador" => "bib0085" "etiqueta" => "17" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Unbiased recursive partitioning: a conditional inference framework" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "T. Hothorn" 1 => "K. Hornik" 2 => "A. Zeileis" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1198/106186006X133933" "Revista" => array:5 [ "tituloSerie" => "J Comput Graph Stat" "fecha" => "2006" "volumen" => "15" "paginaInicial" => "651" "paginaFinal" => "674" ] ] ] ] ] ] 17 => array:3 [ "identificador" => "bib0090" "etiqueta" => "18" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Mortalidad y cumplimiento de los objetivos de prevención secundaria de la cardiopatía isquémica en pacientes ≥70 años: estudio observacional" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "E. Marcos-Forniol" 1 => "E. Corbella" 2 => "X. Pintó" ] ] ] ] ] "host" => array:2 [ 0 => array:2 [ "doi" => "10.1016/j.medcli.2019.06.020" "Revista" => array:6 [ "tituloSerie" => "Med Clin (Barc)" "fecha" => "2020" "volumen" => "154" "paginaInicial" => "243" "paginaFinal" => "247" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/31492451" "web" => "Medline" ] ] ] ] 1 => array:2 [ "doi" => "10.1016/j.medcli.2019.06.020" "WWW" => array:1 [ "link" => "https://www.sciencedirect.com/science/article/pii/S0025775319305068" ] ] ] ] ] ] 18 => array:3 [ "identificador" => "bib0095" "etiqueta" => "19" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Comparación entre CA125 y NT-proBNP para valorar la congestión en insuficiencia cardíaca aguda" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "P. Llàcer" 1 => "MÁ Gallardo" 2 => "P. Palau" 3 => "M.C. Moreno" 4 => "C. Castillo" 5 => "C. Fernández" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.medcli.2020.05.063" "Revista" => array:6 [ "tituloSerie" => "Med Clin (Barc)" "fecha" => "2021" "volumen" => "156" "paginaInicial" => "589" "paginaFinal" => "594" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32951882" "web" => "Medline" ] ] ] ] ] ] ] ] 19 => array:3 [ "identificador" => "bib0100" "etiqueta" => "20" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "F. D’Ascenzo" 1 => "O. De Filippo" 2 => "G. Gallone" 3 => "G. Mittone" 4 => "M.A. Deriu" 5 => "M. Iannaccone" ] ] ] ] ] "host" => array:2 [ 0 => array:2 [ "doi" => "10.1016/S0140-6736(20)32519-8" "Revista" => array:6 [ "tituloSerie" => "Lancet" "fecha" => "2021" "volumen" => "397" "paginaInicial" => "199" "paginaFinal" => "207" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/33453782" "web" => "Medline" ] ] ] ] 1 => array:2 [ "doi" => "10.1016/S0140-6736(20)32519-8" "WWW" => array:1 [ "link" => "https://pubmed.ncbi.nlm.nih.gov/33453782/" ] ] ] ] ] ] 20 => array:3 [ "identificador" => "bib0105" "etiqueta" => "21" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Decision tree model for predicting in-hospital cardiac arrest among patients admitted with acute coronary syndrome" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "H. Li" 1 => "T.T. Wu" 2 => "D.L. Yang" 3 => "Y.S. Guo" 4 => "P.C. Liu" 5 => "Y. Chen" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1002/clc.23255" "Revista" => array:6 [ "tituloSerie" => "Clin Cardiol" "fecha" => "2019" "volumen" => "42" "paginaInicial" => "1087" "paginaFinal" => "1093" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/31509271" "web" => "Medline" ] ] ] ] ] ] ] ] 21 => array:3 [ "identificador" => "bib0110" "etiqueta" => "22" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Tree-based analysis: a practical approach to create clinical decision-making tools" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "M. Banerjee" 1 => "E. Reynolds" 2 => "H.B. Andersson" 3 => "B.K. Nallamothu" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1161/CIRCOUTCOMES.118.004879" "Revista" => array:4 [ "tituloSerie" => "Circ Cardiovasc Qual Outcomes" "fecha" => "2019" "volumen" => "12" "paginaInicial" => "4879" ] ] ] ] ] ] 22 => array:3 [ "identificador" => "bib0115" "etiqueta" => "23" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Relative risk trees for censored survival data" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "M. LeBlanc" 1 => "J. Crowley" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:6 [ "tituloSerie" => "Biometrics" "fecha" => "1992" "volumen" => "48" "paginaInicial" => "411" "paginaFinal" => "425" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/1637970" "web" => "Medline" ] ] ] ] ] ] ] ] 23 => array:3 [ "identificador" => "bib0120" "etiqueta" => "24" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Censoring unbiased regression trees and ensembles" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "J.A. Steingrimsson" 1 => "L. Diao" 2 => "R.L. Strawderman" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1080/01621459.2017.1407775" "Revista" => array:6 [ "tituloSerie" => "J Am Stat Assoc" "fecha" => "2019" "volumen" => "114" "paginaInicial" => "370" "paginaFinal" => "383" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/31190691" "web" => "Medline" ] ] ] ] ] ] ] ] 24 => array:3 [ "identificador" => "bib0125" "etiqueta" => "25" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Evaluating different selection criteria for phase type survival tree construction" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "L. Garg" 1 => "S.I. McClean" 2 => "M. Barton" 3 => "B.J. Meenan" 4 => "K. Fullerton" 5 => "G. Kontonatsios" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:3 [ "tituloSerie" => "Big Data Res" "fecha" => "2021" "volumen" => "25" ] ] ] ] ] ] 25 => array:3 [ "identificador" => "bib0130" "etiqueta" => "26" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Trends in hospitalizations for heart failure and ischemic heart disease among US adults with diabetes" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "M.C. Honigberg" 1 => "R.B. Patel" 2 => "A. Pandey" 3 => "G.C. Fonarow" 4 => "J. Butler" 5 => "D.K. McGuire" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1001/jamacardio.2020.5921" "Revista" => array:6 [ "tituloSerie" => "JAMA Cardiol" "fecha" => "2020" "volumen" => "6" "paginaInicial" => "354" "paginaFinal" => "357" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/33237259" "web" => "Medline" ] ] ] ] ] ] ] ] 26 => array:3 [ "identificador" => "bib0135" "etiqueta" => "27" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Balancing the risks of bleeding and stent thrombosis: a decision analytic model to compare durations of dual antiplatelet therapy after drug-eluting stents" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:5 [ 0 => "P. Garg" 1 => "B.Z. Galper" 2 => "D.J. Cohen" 3 => "R.W. Yeh" 4 => "L. Mauri" ] ] ] ] ] "host" => array:2 [ 0 => array:2 [ "doi" => "10.1016/j.ahj.2014.11.002" "Revista" => array:6 [ "tituloSerie" => "Am Heart J" "fecha" => "2015" "volumen" => "169" "paginaInicial" => "222" "paginaFinal" => "3300000" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25641531" "web" => "Medline" ] ] ] ] 1 => array:2 [ "doi" => "10.1016/j.ahj.2014.11.002" "WWW" => array:1 [ "link" => "http://www.ncbi.nlm.nih.gov/pubmed/25641531" ] ] ] ] ] ] 27 => array:3 [ "identificador" => "bib0140" "etiqueta" => "28" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Risk factors and trends in incidence of heart failure following acute myocardial infarction" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:5 [ 0 => "J. Wellings" 1 => "J.B. Kostis" 2 => "D. Sargsyan" 3 => "J. Cabrera" 4 => "W.J. Kostis" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.amjcard.2018.03.005" "Revista" => array:6 [ "tituloSerie" => "Am J Cardiol" "fecha" => "2018" "volumen" => "122" "paginaInicial" => "1" "paginaFinal" => "5" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/29685572" "web" => "Medline" ] ] ] ] ] ] ] ] 28 => array:3 [ "identificador" => "bib0145" "etiqueta" => "29" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "SGLT2 inhibitors in patients with heart failure with reduced ejection fraction: a meta-analysis of the EMPEROR-Reduced and DAPA-HF trials" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "F. Zannad" 1 => "J.P. Ferreira" 2 => "S.J. Pocock" 3 => "S.D. Anker" 4 => "J. Butler" 5 => "G. Filippatos" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/S0140-6736(20)31824-9" "Revista" => array:6 [ "tituloSerie" => "Lancet" "fecha" => "2020" "volumen" => "396" "paginaInicial" => "819" "paginaFinal" => "829" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/32877652" "web" => "Medline" ] ] ] ] ] ] ] ] 29 => array:3 [ "identificador" => "bib0150" "etiqueta" => "30" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Impact of sacubitril/valsartan versus ramipril on total heart failure events in the PARADISE-MI trial" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "M.A. Pfeffer" 1 => "B. Claggett" 2 => "E.F. Lewis" 3 => "C.B. Granger" 4 => "L. Køber" 5 => "A.P. Maggioni" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1161/CIRCULATIONAHA.121.057429" "Revista" => array:6 [ "tituloSerie" => "Circulation" "fecha" => "2022" "volumen" => "145" "paginaInicial" => "87" "paginaFinal" => "89" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/34797725" "web" => "Medline" ] ] ] ] ] ] ] ] ] ] ] ] ] "idiomaDefecto" => "en" "url" => "/23870206/0000016300000004/v2_202409040637/S2387020624003358/v2_202409040637/en/main.assets" "Apartado" => array:4 [ "identificador" => "43310" "tipo" => "SECCION" "en" => array:2 [ "titulo" => "Original articles" "idiomaDefecto" => true ] "idiomaDefecto" => "en" ] "PDF" => "https://static.elsevier.es/multimedia/23870206/0000016300000004/v2_202409040637/S2387020624003358/v2_202409040637/en/main.pdf?idApp=UINPBA00004N&text.app=https://www.elsevier.es/" "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2387020624003358?idApp=UINPBA00004N" ]
Información de la revista
Compartir
Descargar PDF
Más opciones de artículo
Original article
Classification tree obtained by artificial intelligence for the prediction of heart failure after acute coronary syndromes
Árboles de clasificación obtenidos mediante inteligencia artificial para la predicción de insuficiencia cardiaca tras el síndrome coronario agudo
Alberto Corderoa,
, Vicente Bertomeu-Gonzalezb,c,d, José V. Segurae, Javier Moralese, Belén Álvarez-Álvarezc,f, David Escribanog, Moisés Rodríguez-Maneroc,f, Belén Cid-Alvarezc,f, José M. García-Acuñac,f, José Ramón González-Juanateyc,f, Asunción Martínez-Mayorale
Autor para correspondencia
a Departamento de Cardiología, Hospital IMED Elche, Elche, Alicante, Spain
b Grupo de Investigación Cardiovascular, Universidad Miguel Hernández, Elche, Alicante, Spain
c Centro de Investigación Biomédica en Red de Enfermedades Cardiovasculares (CIBERCV), Madrid, Spain
d Departamento de Cardiología, Clínica Benidorm, Benidorm, Alicante, Spain
e Departamento de Estadística, Matemáticas e Informática, Instituto Universitario Centro de Investigación Operativa (CIO), Universidad Miguel Hernández, Elche, Alicante, Spain
f Departamento de Cardiología, Complejo Hospitalario de la Universidad de Santiago, Santiago de Compostela, A Coruña, Spain
g Departamento de Cardiología, Hospital Universitario de San Juan, San Juan de Alicante, Alicante, Spain