array:24 [ "pii" => "S2253808919300680" "issn" => "22538089" "doi" => "10.1016/j.remnie.2019.04.005" "estado" => "S300" "fechaPublicacion" => "2019-09-01" "aid" => "1073" "copyright" => "Sociedad Española de Medicina Nuclear e Imagen Molecular" "copyrightAnyo" => "2019" "documento" => "article" "crossmark" => 1 "subdocumento" => "fla" "cita" => "Rev Esp Med Nucl Imagen Mol. 2019;38:275-9" "abierto" => array:3 [ "ES" => false "ES2" => false "LATM" => false ] "gratuito" => false "lecturas" => array:1 [ "total" => 0 ] "Traduccion" => array:1 [ "es" => array:19 [ "pii" => "S2253654X18300465" "issn" => "2253654X" "doi" => "10.1016/j.remn.2019.04.002" "estado" => "S300" "fechaPublicacion" => "2019-09-01" "aid" => "1073" "copyright" => "Sociedad Española de Medicina Nuclear e Imagen Molecular" "documento" => "article" "crossmark" => 1 "subdocumento" => "fla" "cita" => "Rev Esp Med Nucl Imagen Mol. 2019;38:275-9" "abierto" => array:3 [ "ES" => false "ES2" => false "LATM" => false ] "gratuito" => false "lecturas" => array:2 [ "total" => 42 "formatos" => array:2 [ "HTML" => 23 "PDF" => 19 ] ] "es" => array:13 [ "idiomaDefecto" => true "cabecera" => "<span class="elsevierStyleTextfn">Original</span>" "titulo" => "Precisión diagnóstica mejorada para la imagen de perfusión miocárdica usando redes neuronales artificiales en diferentes variables de entrada incluyendo datos clínicos y de cuantificación" "tienePdf" => "es" "tieneTextoCompleto" => "es" "tieneResumen" => array:2 [ 0 => "es" 1 => "en" ] "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "275" "paginaFinal" => "279" ] ] "titulosAlternativos" => array:1 [ "en" => array:1 [ "titulo" => "Improved diagnostic accuracy for myocardial perfusion imaging using artificial neural networks on different input variables including clinical and quantification data" ] ] "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" => 3079 "Ancho" => 3168 "Tamanyo" => 459734 ] ] "descripcion" => array:1 [ "es" => "<p id="spar0045" class="elsevierStyleSimplePara elsevierViewall">Curvas de rendimiento diagnóstico de una red bicapa de proalimentación para pronosticar el resultado de la coronariografía (normal vs. anormal), EAC obstructiva (ausente vs. presente) y puntuaciones de Gensini (superior vs. inferior a 10). (a) Las variables de entrada fueron el resultado de la IPM; (b) la cuantificación de los 40 segmentos de los mapas polares de esfuerzo y reposo; y (c) la cuantificación de dichos 40 segmentos además del número de factores de riesgo clínico. Además de la tasa de falsos y verdaderos positivos, también se proporcionan los valores de precisión. El rendimiento de la red utilizando la IPM fue inferior a aquellas redes que utilizaron la cuantificación de los 40 segmentos con y sin los factores de riesgo.</p>" ] ] ] "autores" => array:1 [ 0 => array:2 [ "autoresLista" => "R. Rahmani, P. Niazi, M. Naseri, M. Neishabouri, S. Farzanefar, M. Eftekhari, F. Derakhshan, R. Mollazadeh, A. Meysami, M. Abbasi" "autores" => array:10 [ 0 => array:2 [ "nombre" => "R." "apellidos" => "Rahmani" ] 1 => array:2 [ "nombre" => "P." "apellidos" => "Niazi" ] 2 => array:2 [ "nombre" => "M." "apellidos" => "Naseri" ] 3 => array:2 [ "nombre" => "M." "apellidos" => "Neishabouri" ] 4 => array:2 [ "nombre" => "S." "apellidos" => "Farzanefar" ] 5 => array:2 [ "nombre" => "M." "apellidos" => "Eftekhari" ] 6 => array:2 [ "nombre" => "F." "apellidos" => "Derakhshan" ] 7 => array:2 [ "nombre" => "R." "apellidos" => "Mollazadeh" ] 8 => array:2 [ "nombre" => "A." "apellidos" => "Meysami" ] 9 => array:2 [ "nombre" => "M." "apellidos" => "Abbasi" ] ] ] ] ] "idiomaDefecto" => "es" "Traduccion" => array:1 [ "en" => array:9 [ "pii" => "S2253808919300680" "doi" => "10.1016/j.remnie.2019.04.005" "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/S2253808919300680?idApp=UINPBA00004N" ] ] "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2253654X18300465?idApp=UINPBA00004N" "url" => "/2253654X/0000003800000005/v1_201909070732/S2253654X18300465/v1_201909070732/es/main.assets" ] ] "itemSiguiente" => array:19 [ "pii" => "S2253808919300813" "issn" => "22538089" "doi" => "10.1016/j.remnie.2019.06.001" "estado" => "S300" "fechaPublicacion" => "2019-09-01" "aid" => "1067" "copyright" => "Sociedad Española de Medicina Nuclear e Imagen Molecular" "documento" => "article" "crossmark" => 1 "subdocumento" => "fla" "cita" => "Rev Esp Med Nucl Imagen Mol. 2019;38:280-9" "abierto" => array:3 [ "ES" => false "ES2" => false "LATM" => false ] "gratuito" => false "lecturas" => array:2 [ "total" => 13 "formatos" => array:2 [ "HTML" => 9 "PDF" => 4 ] ] "en" => array:13 [ "idiomaDefecto" => true "cabecera" => "<span class="elsevierStyleTextfn">Original Article</span>" "titulo" => "Comparative study of <span class="elsevierStyleSup">18</span>F-FDG PET/CT and CT angiography in the detection of large vessel vasculitis" "tienePdf" => "en" "tieneTextoCompleto" => "en" "tieneResumen" => array:2 [ 0 => "en" 1 => "es" ] "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "280" "paginaFinal" => "289" ] ] "titulosAlternativos" => array:1 [ "es" => array:1 [ "titulo" => "Estudio comparativo de la PET/TC con <span class="elsevierStyleSup">18</span>F-FDG y la angiografía por TC en la detección de la vasculitis de grandes vasos" ] ] "contieneResumen" => array:2 [ "en" => true "es" => true ] "contieneTextoCompleto" => array:1 [ "en" => true ] "contienePdf" => array:1 [ "en" => true ] "resumenGrafico" => array:2 [ "original" => 0 "multimedia" => array:7 [ "identificador" => "fig0020" "etiqueta" => "Fig. 4" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr4.jpeg" "Alto" => 1745 "Ancho" => 1750 "Tamanyo" => 173369 ] ] "descripcion" => array:1 [ "en" => "<p id="spar0060" class="elsevierStyleSimplePara elsevierViewall"><span class="elsevierStyleSup">18</span>F-FDG PET/CT with <span class="elsevierStyleSup">18</span>F-FDG uptake predominantly in the left facial arteries. Coronal and axial PET (A and C) and coronal and axial PET/CT (B and D).</p>" ] ] ] "autores" => array:1 [ 0 => array:2 [ "autoresLista" => "M. Moragas Solanes, M. Andreu Magarolas, J.C. Martín Miramon, A.P. Caresia Aróztegui, M. Monteagudo Jiménez, J.C. Oliva Morera, C. Diaz Martín, A. Rodríguez Revuelto, Z. Bravo Ferrer, Ll. Bernà Roqueta" "autores" => array:10 [ 0 => array:2 [ "nombre" => "M." "apellidos" => "Moragas Solanes" ] 1 => array:2 [ "nombre" => "M." "apellidos" => "Andreu Magarolas" ] 2 => array:2 [ "nombre" => "J.C." "apellidos" => "Martín Miramon" ] 3 => array:2 [ "nombre" => "A.P." "apellidos" => "Caresia Aróztegui" ] 4 => array:2 [ "nombre" => "M." "apellidos" => "Monteagudo Jiménez" ] 5 => array:2 [ "nombre" => "J.C." "apellidos" => "Oliva Morera" ] 6 => array:2 [ "nombre" => "C." "apellidos" => "Diaz Martín" ] 7 => array:2 [ "nombre" => "A." "apellidos" => "Rodríguez Revuelto" ] 8 => array:2 [ "nombre" => "Z." "apellidos" => "Bravo Ferrer" ] 9 => array:2 [ "nombre" => "Ll." "apellidos" => "Bernà Roqueta" ] ] ] ] ] "idiomaDefecto" => "en" "Traduccion" => array:1 [ "es" => array:9 [ "pii" => "S2253654X1930006X" "doi" => "10.1016/j.remn.2019.03.002" "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/S2253654X1930006X?idApp=UINPBA00004N" ] ] "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2253808919300813?idApp=UINPBA00004N" "url" => "/22538089/0000003800000005/v1_201909030619/S2253808919300813/v1_201909030619/en/main.assets" ] "itemAnterior" => array:18 [ "pii" => "S2253808919300941" "issn" => "22538089" "doi" => "10.1016/j.remnie.2019.07.005" "estado" => "S300" "fechaPublicacion" => "2019-09-01" "aid" => "1093" "documento" => "simple-article" "crossmark" => 1 "subdocumento" => "edi" "cita" => "Rev Esp Med Nucl Imagen Mol. 2019;38:273-4" "abierto" => array:3 [ "ES" => false "ES2" => false "LATM" => false ] "gratuito" => false "lecturas" => array:1 [ "total" => 0 ] "en" => array:10 [ "idiomaDefecto" => true "cabecera" => "<span class="elsevierStyleTextfn">Editorial</span>" "titulo" => "Nuclear medicine in epilepsy: New challenges in SPECT and PET analysis" "tienePdf" => "en" "tieneTextoCompleto" => "en" "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "273" "paginaFinal" => "274" ] ] "titulosAlternativos" => array:1 [ "es" => array:1 [ "titulo" => "Medicina Nuclear en la epilepsia: avances en el análisis de los estudios SPECT y PET" ] ] "contieneTextoCompleto" => array:1 [ "en" => true ] "contienePdf" => array:1 [ "en" => true ] "autores" => array:1 [ 0 => array:2 [ "autoresLista" => "S. Rubí, V. Camacho" "autores" => array:2 [ 0 => array:2 [ "nombre" => "S." "apellidos" => "Rubí" ] 1 => array:2 [ "nombre" => "V." "apellidos" => "Camacho" ] ] ] ] ] "idiomaDefecto" => "en" "Traduccion" => array:1 [ "es" => array:9 [ "pii" => "S2253654X19302070" "doi" => "10.1016/j.remn.2019.07.001" "estado" => "S300" "subdocumento" => "" "abierto" => array:3 [ "ES" => false "ES2" => false "LATM" => false ] "gratuito" => false "lecturas" => array:1 [ "total" => 0 ] "idiomaDefecto" => "es" "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2253654X19302070?idApp=UINPBA00004N" ] ] "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2253808919300941?idApp=UINPBA00004N" "url" => "/22538089/0000003800000005/v1_201909030619/S2253808919300941/v1_201909030619/en/main.assets" ] "en" => array:20 [ "idiomaDefecto" => true "cabecera" => "<span class="elsevierStyleTextfn">Original Article</span>" "titulo" => "Improved diagnostic accuracy for myocardial perfusion imaging using artificial neural networks on different input variables including clinical and quantification data" "tieneTextoCompleto" => true "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "275" "paginaFinal" => "279" ] ] "autores" => array:1 [ 0 => array:4 [ "autoresLista" => "Reza Rahmani, Parisa Niazi, Maryam Naseri, Mohamadreza Neishabouri, Saeed Farzanefar, Mohammad Eftekhari, Farhang Derakhshan, Reza Mollazadeh, Alipasha Meysami, Mehrshad Abbasi" "autores" => array:10 [ 0 => array:3 [ "nombre" => "Reza" "apellidos" => "Rahmani" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">a</span>" "identificador" => "aff0005" ] ] ] 1 => array:3 [ "nombre" => "Parisa" "apellidos" => "Niazi" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">b</span>" "identificador" => "aff0010" ] ] ] 2 => array:3 [ "nombre" => "Maryam" "apellidos" => "Naseri" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">b</span>" "identificador" => "aff0010" ] ] ] 3 => array:3 [ "nombre" => "Mohamadreza" "apellidos" => "Neishabouri" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">b</span>" "identificador" => "aff0010" ] ] ] 4 => array:3 [ "nombre" => "Saeed" "apellidos" => "Farzanefar" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">b</span>" "identificador" => "aff0010" ] ] ] 5 => array:3 [ "nombre" => "Mohammad" "apellidos" => "Eftekhari" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">c</span>" "identificador" => "aff0015" ] ] ] 6 => array:3 [ "nombre" => "Farhang" "apellidos" => "Derakhshan" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">b</span>" "identificador" => "aff0010" ] ] ] 7 => array:3 [ "nombre" => "Reza" "apellidos" => "Mollazadeh" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">a</span>" "identificador" => "aff0005" ] ] ] 8 => array:3 [ "nombre" => "Alipasha" "apellidos" => "Meysami" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">d</span>" "identificador" => "aff0020" ] ] ] 9 => array:4 [ "nombre" => "Mehrshad" "apellidos" => "Abbasi" "email" => array:1 [ 0 => "meabbasi@tums.ac.ir" ] "referencia" => array:2 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">b</span>" "identificador" => "aff0010" ] 1 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">*</span>" "identificador" => "cor0005" ] ] ] ] "afiliaciones" => array:4 [ 0 => array:3 [ "entidad" => "Cardiology Department, Imam-Khomeini Hospital Complex, Tehran University of Medical Sciences, Tehran, Iran" "etiqueta" => "a" "identificador" => "aff0005" ] 1 => array:3 [ "entidad" => "Department of Nuclear Medicine, Vali-asr Hospital, Tehran University of Medical Sciences, Tehran, Iran" "etiqueta" => "b" "identificador" => "aff0010" ] 2 => array:3 [ "entidad" => "Research Institute for Nuclear Medicine, Shariati Hospital, Tehran University of Medical Sciences, Tehran, Iran" "etiqueta" => "c" "identificador" => "aff0015" ] 3 => array:3 [ "entidad" => "Department of Social Medicine, Tehran University of Medical Sciences, Tehran, Iran" "etiqueta" => "d" "identificador" => "aff0020" ] ] "correspondencia" => array:1 [ 0 => array:3 [ "identificador" => "cor0005" "etiqueta" => "⁎" "correspondencia" => "Corresponding author." ] ] ] ] "titulosAlternativos" => array:1 [ "es" => array:1 [ "titulo" => "Precisión diagnóstica mejorada para la imagen de perfusión miocárdica usando redes neuronales artificiales en diferentes variables de entrada incluyendo datos clínicos y de cuantificación" ] ] "resumenGrafico" => array:2 [ "original" => 0 "multimedia" => array:7 [ "identificador" => "fig0005" "etiqueta" => "Fig. 1" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr1.jpeg" "Alto" => 3079 "Ancho" => 3168 "Tamanyo" => 433905 ] ] "descripcion" => array:1 [ "en" => "<p id="spar0045" class="elsevierStyleSimplePara elsevierViewall">The curve for the diagnostic performance of a two-layer feed-forward network to predict angiography result (normal vs. abnormal), obstructive CAD (absent vs. present), and Gensini scores (above vs. below 10). (a) The input was the result of MPI; (b) quantification of 40 segments of stress and rest polar plots; and (c) quantification of 40 segments in addition to the number of clinical risk factors. In addition to the false and true positive rates, accuracies are also provided. The performance of the network using the MPI was inferior to those of networks using quantification of 40 segments with or without risk factor data.</p>" ] ] ] "textoCompleto" => "<span class="elsevierStyleSections"><span id="sec0005" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0065">Introduction</span><p id="par0005" class="elsevierStylePara elsevierViewall">The significance of myocardial perfusion imaging (MPI) in many clinical scenarios is “de facto”.<a class="elsevierStyleCrossRefs" href="#bib0135"><span class="elsevierStyleSup">1,2</span></a> The erratic non-concordance between MPI and the results of angiography can be attributed to substantial differences between MPI and angiography. MPI evaluates the perfusion at the myocardial cell level and angiography assesses the anatomical stenosis in the coronary arteries.<a class="elsevierStyleCrossRefs" href="#bib0145"><span class="elsevierStyleSup">3,4</span></a> Significant anatomical stenosis should result in hypo-perfusion at cell level,<a class="elsevierStyleCrossRefs" href="#bib0155"><span class="elsevierStyleSup">5,6</span></a> but distal run-off from collateral arteries may provide myocardium with proper perfusion and may result in normal MPIs.<a class="elsevierStyleCrossRef" href="#bib0165"><span class="elsevierStyleSup">7</span></a> Also, if angiography were considered as the gold standard, MPI would present a significant number of false positive results in cases in which functional rather than anatomical stenosis were the cause of the patient's symptoms. Since both modalities assess the perfusion of the myocardium, it is perceived that the result of angiography might be predictable based on MPI, regardless of the differences.</p><p id="par0010" class="elsevierStylePara elsevierViewall">Many researchers have examined adding gated single-photon emission computed tomography (SPECT) indexes including motion, contractility and ejection fraction, and certain clinical risk factors, to MPI findings to predict the anatomical stenosis.<a class="elsevierStyleCrossRefs" href="#bib0170"><span class="elsevierStyleSup">8–11</span></a> In clinical settings, sometimes it is thought that the results of angiography could be predicted by consideration of these additional data. More than a decade ago, Lomsky et al., developed an automated decision support system to predict coronary artery disease (CAD) based on the scan data. The gold standard or desired predicted variable was the result of MPI itself.<a class="elsevierStyleCrossRef" href="#bib0190"><span class="elsevierStyleSup">12</span></a> Similarly, WeAidU developed by Ohlsson, and the perfusion expert system (PERFEX) developed by Ezquerra et al., used scan data in a support system to assist MPI interpreters.<a class="elsevierStyleCrossRefs" href="#bib0195"><span class="elsevierStyleSup">13–16</span></a> They did not incorporate clinical variables to their application. Isma’eel et al. developed an artificial neural network (ANN) for emergency settings to predict the results of MPI and angiography by demographic and clinical data. Their network was important because its application reduced unnecessary imaging and angiographies in the emergency settings.<a class="elsevierStyleCrossRef" href="#bib0215"><span class="elsevierStyleSup">17</span></a> Had the scan data been incorporated as a predictive covariable, the classification power for the results of angiograms would have been enhanced. Arsanjani et al. added age and gender as well as electrocardiography (ECG) findings to the scan data and showed improved diagnostic accuracy for ANN compared with visual and quantification interpretation.<a class="elsevierStyleCrossRef" href="#bib0220"><span class="elsevierStyleSup">18</span></a> The current study hypothesized that adding the clinical risk factors including the history of diabetes and hypertension, would increase the prediction power.</p><p id="par0015" class="elsevierStylePara elsevierViewall">ANNs use simple mathematical functions and calculations to replicate the way the human brain learns such prediction rules.<a class="elsevierStyleCrossRef" href="#bib0225"><span class="elsevierStyleSup">19</span></a> The current study aimed at improving the diagnostic accuracy of MPI by an ANN-based model that adds patient data (i.e. cardiac risk factors) to the scan data to predict the results of angiography and Gensini score.</p></span><span id="sec0010" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0070">Materials and methods</span><p id="par0020" class="elsevierStylePara elsevierViewall">The MPIs performed from September 2012 to April 2013 at the Department of Nuclear Medicine, Vali-asr Hospital, a tertiary referral university center affiliated to Tehran University of Medical Sciences, were retrospectively assessed to find patients with follow-up angiography. Quantification of the 20 segments of the polar plot of stress and rest phases of the study were collected from DICOM (digital imaging and communications in medicine) data of the MPIs. The MPIs were acquired based on a two-day stress and rest protocol using either pharmacological (i.e. dipyridamole or dobutamine) or exercise stress and with injection of 20<span class="elsevierStyleHsp" style=""></span>±<span class="elsevierStyleHsp" style=""></span>2<span class="elsevierStyleHsp" style=""></span>mCi <span class="elsevierStyleSup">99m</span>Tc-MIBI at peak stress. The imaging was performed with a dual head gamma camera (ADAC Forte, Philips Medical Systems, Milpitas, CA). Cardiac risk factors were retrieved from registry forms of the patients including diabetes mellitus, hypertension, dyslipidemia, smoking, and family history of CAD. The angiographies were reviewed by an interventional cardiologist blinded to the scan results, and the Gensini scores were calculated. The final reports of the angiography were also collected as normal/abnormal and obstructive/non-obstructive examinations. Data handling was done employing Microsoft Excel 2013 and the data transformations and neural network design were performed using MATLAB, R2017a. For the classification, the neural network pattern recognition tool (nprtool) was used, which classifies data by training a two-layer feed-forward network with a single hidden layer. The current study network consisted of eight neurons in the hidden layer, trained by scaled conjugate gradient backpropagation. The number of neurons in hidden layer was selected by trial and error for training and testing on groups according to network growing method. Training was done on same training data set and testing on same testing group. The current study was started with smallest network and continued increasing neuron numbers to achieve the best diagnostic accuracy. The sample of 93 patients were randomly divided into three subgroups including 65 (70%), 14 (15%), and 14 (15%) patients corresponding to training, validation, and testing groups, respectively. The training process was conducted using the data of the training group; the data of the validation group were used to avoid over training in order to optimize network generalization, and the trained network performance was finally assessed on the test group data. The input variables were the following data: 1-the result of MPI as the interpretation of nuclear physician who had access to the gated SPECT results (Boolean variable), or 2-counts of 40 segments of the stress and rest polar plots (discrete variables), or 3-counts of 40 segments of the stress and rest polar plots in addition to age (continuous variable), gender (Boolean variable), and the number of cardiovascular risk factors including diabetes mellitus, hypertension, dyslipidemia, smoking, and family history of CAD. The number of cardiovascular risk factors was a discrete number in the range of 0–5. The desirable output was one of the following variables in different designs: the results of angiography as normal/abnormal, obstructive CAD (stenosis >50% in at least a vessel), and Gensini score (≥10 and <10). All the output variables were Boolean. Sensitivity, specificity, negative and positive predictive values, and the accuracies of the MPI and ANN employing different combinations of MPI, clinical data, and the counts of polar plots were calculated.</p></span><span id="sec0015" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0075">Results</span><p id="par0025" class="elsevierStylePara elsevierViewall">Out of 923 scans, 276 (29.9%) were reported abnormal. From those patients with abnormal MPI, 88 (31.9%) patients had their coronary arteries catheterized in our hospital. Five patients with normal MPI had angiography, and the reason for catheterization was pure clinical suspicion of the cardiologist and the clinical necessity of the patients. The health characteristics of the 93 participants with available angiography are presented in <a class="elsevierStyleCrossRef" href="#tbl0005">Table 1</a>. In angiography, normal coronary arteries, mild CAD, single vessel obstruction, two vessels obstruction, and three vessel obstruction were detected in 18 (19.1%), 19 (20.2%), 9 (9.6%), 14 (14.9%), and 33 (35.2%) patients, respectively. As the conclusion of angiography, abnormal angiography and obstructive CAD were reported in 75 (80.6%) and 56 (60.2%) patients, respectively. The mean Gensini score was 0.45<span class="elsevierStyleHsp" style=""></span>±<span class="elsevierStyleHsp" style=""></span>0.50. The number of patients with Gensini score ≥10 was 42 (45.2%). The diagnostic performance of MPI alone and the ANN using different combinations of additional data are shown in <a class="elsevierStyleCrossRef" href="#tbl0010">Table 2</a>. The accuracy of MPI was 81.7%, 65.0%, and 50.5% to detect abnormal angiography, obstructive CAD, and high Gensini score (≥10), respectively. The ANN improved these accuracies to 92.9%, 85.7%, and 92.9%, respectively. For different input variables, the curves for true and false positive rates to predict the results of angiography, presence of obstructive CAD, and Gensini score are visually depicted in <a class="elsevierStyleCrossRef" href="#fig0005">Fig. 1</a>. The use of quantification of 40 stress and rest segments with or without additional data about clinical risk factor data showed better diagnostic performance compared with the use of MPI results alone.</p><elsevierMultimedia ident="tbl0005"></elsevierMultimedia><elsevierMultimedia ident="tbl0010"></elsevierMultimedia><elsevierMultimedia ident="fig0005"></elsevierMultimedia></span><span id="sec0020" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0080">Discussion</span><p id="par0030" class="elsevierStylePara elsevierViewall">The current study showed that ANN remarkably improved the predictive power and diagnostic accuracy of MPI when the target endpoint was to detect abnormal angiography results. The accuracy increased from about 82% to 93% when the age, gender, number of cardiac risk factors, and the quantification of stress and rest MPI polar plots were integrated to detect abnormal angiography. The accuracy to predict obstructive CAD and Gensini score also improved from 65% to 86% and from 51% to 93%, respectively. The results of ANN could be used as an additional aid to interpret MPI with incremental value to correlate with the results of angiography. Discordance of the results of MPI and angiography could be minimized by this method.</p><p id="par0035" class="elsevierStylePara elsevierViewall">ANN replicates the way the human brain is perceived to learn.<a class="elsevierStyleCrossRef" href="#bib0225"><span class="elsevierStyleSup">19</span></a> Different patterns and algorithms of effects and the interaction between the features could be integrated to predict a desired outcome.<a class="elsevierStyleCrossRef" href="#bib0230"><span class="elsevierStyleSup">20</span></a> Pattern recognition with ANN is one of the most frequently used algorithms, which back-propagates the error from the outer layers to the inner layers and changes the weights in the nodes in such an extent that minimizes the final error in the next iterations.<a class="elsevierStyleCrossRef" href="#bib0235"><span class="elsevierStyleSup">21</span></a> The validation data are used to prevent the network overtraining with the learning data and stop the learning process when the individual cases are going to be identified instead of the pattern ruling the interactions. When the network is trained, its diagnostic performance is examined in the test data set. Eight nodes in the hidden layer provided us with the best performance and the ANN was stable in the repeated training tries.</p><p id="par0040" class="elsevierStylePara elsevierViewall">The authors previously showed that ANN could be used to replicate the interpretation of the nuclear physician for MPI.<a class="elsevierStyleCrossRef" href="#bib0240"><span class="elsevierStyleSup">22</span></a> Normal or near normal MPI is associated with a low frequency of referral for coronary revascularization.<a class="elsevierStyleCrossRef" href="#bib0245"><span class="elsevierStyleSup">23</span></a> The main problem in the current practice was normal angiograms after abnormal myocardial perfusion scans. We usually justify the differences between the scan and angiogram by the differences in the information provided by both modalities: cell level perfusion versus anatomical stenosis detection. The current study showed the advantages of ANN which may assist further in the joint assessment of the results of MPI and coronary angiography. For such application, clinical and quantification indexes of MPI were employed. The increased predictive ability of angiography should not lead to the conclusion that MPI is enhanced by the use of ANN even if the predictive power for the results of angiography was improved. In other words, MPI essentially does not correspond with angiography since the evaluated endpoint is different between the two modalities, cell perfusion vs. anatomical stenosis. Nevertheless, the current study showed that adding clinical and quantitative data and the use of ANN enabled MPI to better predict the results of angiography.</p><p id="par0045" class="elsevierStylePara elsevierViewall">Recently Shibutani et al. documented that the use of ANN increases the concordance between the results of MPI and angiography.<a class="elsevierStyleCrossRef" href="#bib0250"><span class="elsevierStyleSup">24</span></a> In comparison with similar studies, the improved accuracy we achieved, from 82% to 93%, is remarkable. Based on two different studies, Betancur and his coworkers reported an improved accuracy using deep learning from 78% to 80% and from 78% to 81%.<a class="elsevierStyleCrossRefs" href="#bib0255"><span class="elsevierStyleSup">25,26</span></a> Deep learning in the network we used was improved in several aspects. The higher diagnostic performance reported is possibly a consequence of the integration of clinical risk factors and imaging data. Also they used total perfusion defect, a quantitative index of ischemia, instead of scan overall interpretation, hence they had lower MPI diagnostic performance rates. When comparing the results of different studies, it is crucial to consider studies with similar gold standards, angiography vs. expert interpretation, a fact that excludes many reports from being comparable with the current study.</p><p id="par0050" class="elsevierStylePara elsevierViewall">The current study had a major limitation because, on one hand, patients with normal MPI usually would not undergo angiography and, on the other hand, in cases in which the cardiologist decided to perform angiography in spite of a normal MPI, the clinical risk for CAD might have been high. Due to this limitation, the specificity and sensitivity would be under and overestimated, respectively. Therefore, the exact specificity and sensitivity should be interpreted cautiously; albeit, the current study focused on the fact that the ANN may improve the predictive power of the MPI over visual interpretation in the population of the current study. Furthermore, since the optimal network in the current study was selected based on the accuracy in the testing group, a sub-sample of a single center population, the results could be biased; further validation and suitable optimization should be done using well-separated and independent samples in future studies. Lastly, because of small sample size, the observations were rather limited which caused wide confidence intervals for diagnostic performance data.</p></span><span id="sec0025" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0085">Compliance with ethical standards</span><p id="par0055" class="elsevierStylePara elsevierViewall">This study has been approved by the Tehran University of Medical Sciences ethics committee and has therefore been performed in accordance with the ethical standards laid down in the 1964 Declaration of Helsinki and all subsequent revisions.</p></span><span id="sec0030" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0090">Funding</span><p id="par0060" class="elsevierStylePara elsevierViewall">The research was done as a part of M.D. thesis of Tehran University of Medical Sciences.</p></span><span id="sec0035" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0095">Conflict of interest</span><p id="par0065" class="elsevierStylePara elsevierViewall">The authors declare they have no conflict of interest.</p></span></span>" "textoCompletoSecciones" => array:1 [ "secciones" => array:12 [ 0 => array:3 [ "identificador" => "xres1238156" "titulo" => "Abstract" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0005" "titulo" => "Objective" ] 1 => array:2 [ "identificador" => "abst0010" "titulo" => "Methods" ] 2 => array:2 [ "identificador" => "abst0015" "titulo" => "Results" ] 3 => array:2 [ "identificador" => "abst0020" "titulo" => "Conclusion" ] ] ] 1 => array:2 [ "identificador" => "xpalclavsec1149268" "titulo" => "Keywords" ] 2 => array:3 [ "identificador" => "xres1238155" "titulo" => "Resumen" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0025" "titulo" => "Objetivo" ] 1 => array:2 [ "identificador" => "abst0030" "titulo" => "Métodos" ] 2 => array:2 [ "identificador" => "abst0035" "titulo" => "Resultados" ] 3 => array:2 [ "identificador" => "abst0040" "titulo" => "Conclusión" ] ] ] 3 => array:2 [ "identificador" => "xpalclavsec1149267" "titulo" => "Palabras clave" ] 4 => array:2 [ "identificador" => "sec0005" "titulo" => "Introduction" ] 5 => array:2 [ "identificador" => "sec0010" "titulo" => "Materials and methods" ] 6 => array:2 [ "identificador" => "sec0015" "titulo" => "Results" ] 7 => array:2 [ "identificador" => "sec0020" "titulo" => "Discussion" ] 8 => array:2 [ "identificador" => "sec0025" "titulo" => "Compliance with ethical standards" ] 9 => array:2 [ "identificador" => "sec0030" "titulo" => "Funding" ] 10 => array:2 [ "identificador" => "sec0035" "titulo" => "Conflict of interest" ] 11 => array:1 [ "titulo" => "References" ] ] ] "pdfFichero" => "main.pdf" "tienePdf" => true "fechaRecibido" => "2018-02-21" "fechaAceptado" => "2019-04-08" "PalabrasClave" => array:2 [ "en" => array:1 [ 0 => array:4 [ "clase" => "keyword" "titulo" => "Keywords" "identificador" => "xpalclavsec1149268" "palabras" => array:4 [ 0 => "Myocardial perfusion imaging" 1 => "Coronary artery disease" 2 => "Gensini score" 3 => "Artificial neural networks" ] ] ] "es" => array:1 [ 0 => array:4 [ "clase" => "keyword" "titulo" => "Palabras clave" "identificador" => "xpalclavsec1149267" "palabras" => array:4 [ 0 => "Imagen de perfusión miocárdica" 1 => "Enfermedad de las arterias coronarias" 2 => "Puntuación de gensini" 3 => "Redes neurales artificiales" ] ] ] ] "tieneResumen" => true "resumen" => array:2 [ "en" => array:3 [ "titulo" => "Abstract" "resumen" => "<span id="abst0005" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0010">Objective</span><p id="spar0005" class="elsevierStyleSimplePara elsevierViewall">Diagnostic accuracy of myocardial perfusion imaging (MPI) is not optimal to predict the result of angiography. The current study aimed at investigating the application of artificial neural network (ANN) to integrate the clinical data with the result and quantification of MPI.</p></span> <span id="abst0010" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0015">Methods</span><p id="spar0010" class="elsevierStyleSimplePara elsevierViewall">Out of 923 patients with MPI, 93 who underwent angiography were recruited. The clinical data including the cardiac risk factors were collected and the results of MPI and coronary angiography were recorded. The quantification of MPI polar plots (i.e. the counts of 20 segments of each stress and rest polar plots) and the Gensini score of angiographies were calculated. Feed-forward ANN was designed integrating clinical and quantification data to predict the result of angiography (normal vs. abnormal), non-obstructive or obstructive coronary artery disease (CAD), and Gensini score (≥10 and <10). The ANNs were designed to predict the results of angiography using different combinations of data as follows: reports of MPI, the counts of 40 segments of stress and rest polar plots, and the count of these 40 segments in addition to age, gender, and the number of risk factors. The diagnostic performance of MPI with different ANNs was compared.</p></span> <span id="abst0015" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0020">Results</span><p id="spar0015" class="elsevierStyleSimplePara elsevierViewall">The accuracy of MPI to predict the result of angiography, obstructive CAD, and Gensini score increased from 81.7% to 92.9%, 65.0% to 85.7%, and 50.5% to 92.9%, respectively by ANN using counts and clinical risk factors.</p></span> <span id="abst0020" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0025">Conclusion</span><p id="spar0020" class="elsevierStyleSimplePara elsevierViewall">The diagnostic accuracy of MPI could be improved by ANN, using clinical and quantification data.</p></span>" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0005" "titulo" => "Objective" ] 1 => array:2 [ "identificador" => "abst0010" "titulo" => "Methods" ] 2 => array:2 [ "identificador" => "abst0015" "titulo" => "Results" ] 3 => array:2 [ "identificador" => "abst0020" "titulo" => "Conclusion" ] ] ] "es" => array:3 [ "titulo" => "Resumen" "resumen" => "<span id="abst0025" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0035">Objetivo</span><p id="spar0025" class="elsevierStyleSimplePara elsevierViewall">La precisión diagnóstica de la imagen de perfusión miocárdica (IPM) no es óptima para predecir el resultado de la angiografía. El objetivo del presente estudio es investigar la aplicación de la red neuronal artificial (RNA) para integrar los datos clínicos con el resultado y la cuantificación del IPM.</p></span> <span id="abst0030" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0040">Métodos</span><p id="spar0030" class="elsevierStyleSimplePara elsevierViewall">De 923 pacientes con IPM, se reclutaron 93 que se sometieron a angiografía. Se recogieron los datos clínicos, incluidos los factores de riesgo cardíaco, y se registraron los resultados de la IPM y la angiografía coronaria. Se calculó la cuantificación de las gráficas polares IPM (es decir, los recuentos de 20 segmentos de cada una de las gráficas polares de esfuerzo y de reposo) y la puntuación de Gensini de las angiografías. ANN fue diseñado integrando datos clínicos y de cuantificación para predecir el resultado de la angiografía (normal vs. anormal), la enfermedad coronaria no obstructiva u obstructiva (EAC), y la puntuación de Gensini (≥10 y <10). Las RNA fueron diseñadas para predecir los resultados de la angiografía usando diferentes combinaciones de datos como sigue: informes de IPM, la cuantificación de 40 segmentos de diagramas polares de esfuerzo y reposo, y la cuantificación de estos 40 segmentos además de la edad, el sexo y el número de factores de riesgo. Se comparó el rendimiento diagnóstico del IPM con diferentes RNA.</p></span> <span id="abst0035" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0045">Resultados</span><p id="spar0035" class="elsevierStyleSimplePara elsevierViewall">La precisión del IPM para predecir el resultado de la angiografía, la EAC obstructiva y la puntuación de Gensini aumentó del 81,7% al 92,9%, del 65,0% al 85,7% y del 50,5% al 92,9%, respectivamente, mediante la RNA con cuantificación y factores de riesgo clínicos.</p></span> <span id="abst0040" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0050">Conclusión</span><p id="spar0040" class="elsevierStyleSimplePara elsevierViewall">La precisión diagnóstica de la IPM podría mejorarse mediante la RNA, utilizando datos clínicos y de cuantificación.</p></span>" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0025" "titulo" => "Objetivo" ] 1 => array:2 [ "identificador" => "abst0030" "titulo" => "Métodos" ] 2 => array:2 [ "identificador" => "abst0035" "titulo" => "Resultados" ] 3 => array:2 [ "identificador" => "abst0040" "titulo" => "Conclusión" ] ] ] ] "NotaPie" => array:1 [ 0 => array:2 [ "etiqueta" => "☆" "nota" => "<p class="elsevierStyleNotepara" id="npar0025">Please cite this article as: Rahmani R, Niazi P, Naseri M, Neishabouri M, Farzanefar S, Eftekhari M, et al. Precisión diagnóstica mejorada para la imagen de perfusión miocárdica usando redes neuronales artificiales en diferentes variables de entrada incluyendo datos clínicos y de cuantificación. Rev Esp Med Nucl Imagen Mol. 2019;38:275–279.</p>" ] ] "multimedia" => array:3 [ 0 => array:7 [ "identificador" => "fig0005" "etiqueta" => "Fig. 1" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr1.jpeg" "Alto" => 3079 "Ancho" => 3168 "Tamanyo" => 433905 ] ] "descripcion" => array:1 [ "en" => "<p id="spar0045" class="elsevierStyleSimplePara elsevierViewall">The curve for the diagnostic performance of a two-layer feed-forward network to predict angiography result (normal vs. abnormal), obstructive CAD (absent vs. present), and Gensini scores (above vs. below 10). (a) The input was the result of MPI; (b) quantification of 40 segments of stress and rest polar plots; and (c) quantification of 40 segments in addition to the number of clinical risk factors. In addition to the false and true positive rates, accuracies are also provided. The performance of the network using the MPI was inferior to those of networks using quantification of 40 segments with or without risk factor data.</p>" ] ] 1 => array:8 [ "identificador" => "tbl0005" "etiqueta" => "Table 1" "tipo" => "MULTIMEDIATABLA" "mostrarFloat" => true "mostrarDisplay" => false "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at1" "detalle" => "Table " "rol" => "short" ] ] "tabla" => array:3 [ "leyenda" => "<p id="spar0055" class="elsevierStyleSimplePara elsevierViewall">Data are expressed as number (percentage) and mean (standard deviation). Chi-square test was used for gender, hypertension, diabetes mellitus, hyperlipidemia, coronary artery disease (CAD) and smoking. Independent samples t test was used to compare means of age, ejection fraction, and Gensini score. The median of the number of risk factors was compared by nonparametric independent samples <span class="elsevierStyleItalic">t</span> test.</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="" 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 " colspan="2" align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Myocardial perfusion scan</th><th class="td" title="\n \t\t\t\t\ttable-head\n \t\t\t\t " colspan="2" align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Angiography</th><th class="td" title="\n \t\t\t\t\ttable-head\n \t\t\t\t " colspan="2" align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Obstructive CAD</th><th class="td" title="\n \t\t\t\t\ttable-head\n \t\t\t\t " colspan="2" align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Gensini score</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">Total \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="" 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">Normal N<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>5 \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">Abnormal N<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>88 \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">Normal N<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>18 \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">Abnormal N<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>75 \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">Absent N<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>37 \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">Present N<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>56 \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"><10<span class="elsevierStyleItalic">N</span><span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>51 \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">≥10<span class="elsevierStyleItalic">N</span><span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>42 \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="" 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></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">Female \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">4 (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">39 (44.3) \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">14 (77.8) \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">29 (38.7)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (62.2) \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">20 (35.7)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">31 (60.8) \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">12 (28.6)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">43 (46.2) \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">Hypertension \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (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">33 (37.5) \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">3 (16.7) \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">30 (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">8 (21.6) \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">25 (44.6)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (33.3) \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">16 (38.1) \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 (35.5) \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">Diabetes mellitus \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (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">36 (40.9) \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">3 (16.7) \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">33 (44)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (27) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (46.4) \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 (29.4) \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">21 (50)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">36 (38.7) \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">Hyperlipidemia \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (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">20 (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">3 (16.7) \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">17 (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">7 (18.9) \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">13 (23.2) \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">11 (21.6) \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">9 (21.4) \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">20 (21.5) \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">CAD \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (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">14 (15.9) \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">1 (5.6) \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">13 (17.3) \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">1 (2.7) \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">13 (23.2)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (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">13 (31)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (15.1) \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">Smoking \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (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">15 (17) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (16.7) \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">13 (17.3) \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">3 (8.1) \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">13 (23.2) \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 (11.8) \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">10 (23.8) \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">16 (17.2) \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">Number of risk factors \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.2 (0.4) \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">1.3 (1.2)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.7 (0.9) \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">1.4 (1.2)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.8 (0.9) \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">1.6 (1.2)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (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">1.6 (1.2)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.3 (1.2) \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">Age \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (12.2) \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">62.3 (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">57.2 (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">63.1 (11.1)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">59.1 (12.5) \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">63.8 (9.5)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">60.9 (12.2) \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">63.2 (9.3) \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">61.9 (11) \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">Ejection fraction \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">59.8 (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">51.1 (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">58 (8.1) \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">49.7 (11.1)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">55.8 (10.2) \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">48.9 (10.8)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">55.8 (9.3) \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">45.8 (10.7)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">51.7 (11) \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">Gensini score \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.2 (1.7) \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">24.2 (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">0 (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">28.5 (36.2)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.8 (2.7) \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">36.9 (38.4)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (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">47.2 (39.2)<a class="elsevierStyleCrossRef" href="#tblfn0005"><span class="elsevierStyleSup">†</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 (34.4) \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab2115629.png" ] ] ] "notaPie" => array:1 [ 0 => array:3 [ "identificador" => "tblfn0005" "etiqueta" => "†" "nota" => "<p class="elsevierStyleNotepara" id="npar0005">Indicates statistically significant difference between normal and abnormal, CAD absent and present, or Gensini scores <10 and ≥10.</p>" ] ] ] "descripcion" => array:1 [ "en" => "<p id="spar0050" class="elsevierStyleSimplePara elsevierViewall">Health characteristics of the participants with and without abnormal MPI.</p>" ] ] 2 => array:8 [ "identificador" => "tbl0010" "etiqueta" => "Table 2" "tipo" => "MULTIMEDIATABLA" "mostrarFloat" => true "mostrarDisplay" => false "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at2" "detalle" => "Table " "rol" => "short" ] ] "tabla" => array:3 [ "leyenda" => "<p id="spar0065" class="elsevierStyleSimplePara elsevierViewall">Data in the parentheses are 95% confidence intervals.</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="" 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="" 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">Specificity \t\t\t\t\t\t\n \t\t\t\t\t\t</th><th class="td" title="\n \t\t\t\t\ttable-head\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Sensitivity \t\t\t\t\t\t\n \t\t\t\t\t\t</th><th class="td" title="\n \t\t\t\t\ttable-head\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">NPV<a class="elsevierStyleCrossRef" href="#tblfn0010"><span class="elsevierStyleSup">a</span></a> \t\t\t\t\t\t\n \t\t\t\t\t\t</th><th class="td" title="\n \t\t\t\t\ttable-head\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">PPV<a class="elsevierStyleCrossRef" href="#tblfn0015"><span class="elsevierStyleSup">b</span></a> \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></tr></thead><tbody title="tbody"><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " colspan="7" align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t"><span class="elsevierStyleItalic">Angiography (normal/abnormal)</span></td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="" 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">MPI \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">16.7 (3.6–41.4) \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">97.3 (90.7–99.7) \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">60.0 (21.3–89.3) \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">83.0 (79.8–85.7) \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">81.7 (72.4–89.0) \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">ANN \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">MPI \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">33.3 (0.8–90.6) \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">100 (71.5–100.0) \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">100.0 (20.7–100.0) \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">84.6 (71.2–92.5) \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">85.7 (57.2–98.2) \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="" 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">Counts of 40 segments \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">50.0 (1.3–98.7) \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">91.7 (61.5–99.8) \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">50.0 (8.8–91.2) \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">91.7 (73.1–97.80) \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">85.7 (57.2–98.2) \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="" 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">Counts and clinical risk factors<a class="elsevierStyleCrossRef" href="#tblfn0020"><span class="elsevierStyleSup">c</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">100.0 (2.5–100.0) \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">92.3 (64.0–99.8) \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">50.0 (13.2–86.8) \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">100.0 (75.8–100.0) \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">92.9 (66.1–99.8) \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " colspan="7" align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t"><span class="elsevierStyleVsp" style="height:0.5px"></span></td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " colspan="7" align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t"><span class="elsevierStyleItalic">Obstructive CAD</span></td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="" 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">MPI \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">13.5 (4.5–28.8) \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">100.0 (93.6–100.0) \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">100.0 (56.6–100.0) \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">63.6 (60.6–66.5) \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">65.0 (55.0–75.1) \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">ANN \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">MPI \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">25.0 (0.6–80.6) \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">100.0)69.2–100.0( \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">100.0 (20.7–100.0) \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">76.9 (65.4–85.4) \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">78.6 (49.2–95.3) \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="" 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">Counts of 40 segments \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">66.7 (22.3–95.7) \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">87.5 (47.4–99.7) \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">80.0 (37.0–96.5) \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">77.8 (52.3–91.8) \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">78.6 (49.2–95.3) \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="" 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">Counts and clinical risk factors<a class="elsevierStyleCrossRef" href="#tblfn0020"><span class="elsevierStyleSup">c</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">100.0 (29.2–100.0) \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">81.8 (48.2–97.7) \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">60.0 (30.0–84.0) \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">100.0 (70.1–100.0) \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">85.7 (57.2–98.2) \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " colspan="7" align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t"><span class="elsevierStyleVsp" style="height:0.5px"></span></td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " colspan="7" align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t"><span class="elsevierStyleItalic">Gensini score (≥10 and <10)</span></td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="" 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">MPI \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">9.8 (3.3–21.4) \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">100.0 (91.6–100.0) \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">100.0 (56.6–100.0) \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">47.7 (45.5–50.0) \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">50.5 (40.0–61.1) \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">ANN \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">MPI \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">14.3 (0.4–57.9) \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">100 (59.0–100.0) \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">100.0 (20.7–100.0) \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">53.9 (46.3–61.2) \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">57.1 (28.8–82.3) \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="" 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">Counts of 40 segments \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">90.0 (55.5–99.8) \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">100.0 (39.8–100.0) \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">100.0 (70.1–100.0) \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">80.0 (38.4–96.3) \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">92.9 (66.1–99.8) \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="" 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">Counts and clinical risk factors<a class="elsevierStyleCrossRef" href="#tblfn0020"><span class="elsevierStyleSup">c</span></a> \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">77.8 (40.0–97.2) \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">80.0 (28.4–99.5) \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">87.5 (54.0–97.7) \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">66.7 (35.3–88.0) \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">78.6 (49.2–95.3) \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab2115630.png" ] ] ] "notaPie" => array:3 [ 0 => array:3 [ "identificador" => "tblfn0010" "etiqueta" => "a" "nota" => "<p class="elsevierStyleNotepara" id="npar0010">Negative predictive value.</p>" ] 1 => array:3 [ "identificador" => "tblfn0015" "etiqueta" => "b" "nota" => "<p class="elsevierStyleNotepara" id="npar0015">Positive predictive value.</p>" ] 2 => array:3 [ "identificador" => "tblfn0020" "etiqueta" => "c" "nota" => "<p class="elsevierStyleNotepara" id="npar0020">Clinical risk factors are age, gender, and the number of coronary artery disease (CAD) risk factors including smoking, dyslipidemia, hypertension, diabetes mellitus, and family history of CAD.</p>" ] ] ] "descripcion" => array:1 [ "en" => "<p id="spar0060" class="elsevierStyleSimplePara elsevierViewall">Diagnostic performance of MPI alone and the ANN using MPI in addition to incremental combinations of age, gender, number of cardiac risk factors and counts of stress and rest MPI polar plots.</p>" ] ] ] "bibliografia" => array:2 [ "titulo" => "References" "seccion" => array:1 [ 0 => array:2 [ "identificador" => "bibs0015" "bibliografiaReferencia" => array:26 [ 0 => array:3 [ "identificador" => "bib0135" "etiqueta" => "1" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "12-Year outcome after normal myocardial perfusion SPECT in patients with known coronary artery disease" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "M.J. Ottenhof" 1 => "M.C.T.J. Wai" 2 => "H.J. Boiten" 3 => "R.S. Korbee" 4 => "R. Valkema" 5 => "R.T. van Domburg" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/s12350-013-9713-3" "Revista" => array:6 [ "tituloSerie" => "J Nucl Cardiol" "fecha" => "2013" "volumen" => "20" "paginaInicial" => "748" "paginaFinal" => "754" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/23912382" "web" => "Medline" ] ] ] ] ] ] ] ] 1 => array:3 [ "identificador" => "bib0140" "etiqueta" => "2" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Comparison of the short-term survival benefit associated with revascularization compared with medical therapy in patients with no prior coronary artery disease undergoing stress myocardial perfusion single photon emission computed tomography" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:5 [ 0 => "R. Hachamovitch" 1 => "S.W. Hayes" 2 => "J.D. Friedman" 3 => "I. Cohen" 4 => "D.S. Berman" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1161/01.CIR.0000072790.23090.41" "Revista" => array:6 [ "tituloSerie" => "Circulation" "fecha" => "2003" "volumen" => "107" "paginaInicial" => "2900" "paginaFinal" => "2907" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/12771008" "web" => "Medline" ] ] ] ] ] ] ] ] 2 => array:3 [ "identificador" => "bib0145" "etiqueta" => "3" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Predictors of high-risk coronary artery disease in subjects with normal SPECT myocardial perfusion imaging" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "R. Nakanishi" 1 => "H. Gransar" 2 => "P. Slomka" 3 => "R. Arsanjani" 4 => "A. Shalev" 5 => "Y. Otaki" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/s12350-015-0150-3" "Revista" => array:6 [ "tituloSerie" => "J Nucl Cardiol" "fecha" => "2016" "volumen" => "23" "paginaInicial" => "530" "paginaFinal" => "541" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25971987" "web" => "Medline" ] ] ] ] ] ] ] ] 3 => array:3 [ "identificador" => "bib0150" "etiqueta" => "4" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "SPECT imaging for detecting coronary artery disease and determining prognosis by noninvasive assessment of myocardial perfusion and myocardial viability" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "G.A. Beller" 1 => "R.C. Heede" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/s12265-011-9290-2" "Revista" => array:6 [ "tituloSerie" => "J Cardiovasc Transl Res" "fecha" => "2011" "volumen" => "4" "paginaInicial" => "416" "paginaFinal" => "424" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/21732226" "web" => "Medline" ] ] ] ] ] ] ] ] 4 => array:3 [ "identificador" => "bib0155" "etiqueta" => "5" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Multimodality image fusion for diagnosing coronary artery disease" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "M. Piccinelli" 1 => "E. Garcia" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.7555/JBR.27.20130138" "Revista" => array:5 [ "tituloSerie" => "J Biomed Res" "fecha" => "2013" "volumen" => "27" "paginaInicial" => "439" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/24285942" "web" => "Medline" ] ] ] ] ] ] ] ] 5 => array:3 [ "identificador" => "bib0160" "etiqueta" => "6" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Potential utility of rubidium 82 PET quantification in patients with 3-vessel coronary artery disease" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "R. Parkash" 1 => "T. Ruddy" 2 => "A. Kitsikis" 3 => "R. Hart" 4 => "L. Beauschene" 5 => "K. Williams" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.nuclcard.2004.04.005" "Revista" => array:6 [ "tituloSerie" => "J Nucl Cardiol" "fecha" => "2004" "volumen" => "11" "paginaInicial" => "440" "paginaFinal" => "449" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/15295413" "web" => "Medline" ] ] ] ] ] ] ] ] 6 => array:3 [ "identificador" => "bib0165" "etiqueta" => "7" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Relation between coronary “steal” and contractile function at rest in collateral-dependent myocardium of humans with ischemic heart disease" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "G. Holmvang" 1 => "S. Fry" 2 => "H.A. Skopicki" 3 => "S.A. Abraham" 4 => "N.M. Alpert" 5 => "A.J. Fischman" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1161/01.cir.99.19.2510" "Revista" => array:6 [ "tituloSerie" => "Circulation" "fecha" => "1999" "volumen" => "99" "paginaInicial" => "2510" "paginaFinal" => "2516" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/10330381" "web" => "Medline" ] ] ] ] ] ] ] ] 7 => array:3 [ "identificador" => "bib0170" "etiqueta" => "8" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Incremental value of combined perfusion and function over perfusion alone by gated SPECT myocardial perfusion imaging for detection of severe three-vessel coronary artery disease" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "R.S. Lima" 1 => "D.D. Watson" 2 => "A.R. Goode" 3 => "M.S. Siadaty" 4 => "M. Ragosta" 5 => "G.A. Beller" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/s0735-1097(03)00562-x" "Revista" => array:6 [ "tituloSerie" => "J Am Coll Cardiol" "fecha" => "2003" "volumen" => "42" "paginaInicial" => "64" "paginaFinal" => "70" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/12849661" "web" => "Medline" ] ] ] ] ] ] ] ] 8 => array:3 [ "identificador" => "bib0175" "etiqueta" => "9" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Underestimation of extent of ischemia by gated SPECT myocardial perfusion imaging in patients with left main coronary artery disease" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "D.S. Berman" 1 => "X. Kang" 2 => "P.J. Slomka" 3 => "J. Gerlach" 4 => "L. de Yang" 5 => "S.W. Hayes" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.nuclcard.2007.05.008" "Revista" => array:6 [ "tituloSerie" => "J Nucl Cardiol" "fecha" => "2007" "volumen" => "14" "paginaInicial" => "521" "paginaFinal" => "528" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/17679060" "web" => "Medline" ] ] ] ] ] ] ] ] 9 => array:3 [ "identificador" => "bib0180" "etiqueta" => "10" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Reversible regional wall motion abnormalities on exercise technetium-99m–gated cardiac single photon emission computed tomography predict high-grade angiographic stenoses" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:6 [ 0 => "L. Emmett" 1 => "R.M. Iwanochko" 2 => "M.R. Freeman" 3 => "A. Barolet" 4 => "D.S. Lee" 5 => "M. Husain" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/s0735-1097(02)01707-2" "Revista" => array:6 [ "tituloSerie" => "J Am Coll Cardiol" "fecha" => "2002" "volumen" => "39" "paginaInicial" => "991" "paginaFinal" => "998" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/11897441" "web" => "Medline" ] ] ] ] ] ] ] ] 10 => array:3 [ "identificador" => "bib0185" "etiqueta" => "11" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Diagnostic accuracy of rest/stress ECG-gated Rb-82 myocardial perfusion PET: comparison with ECG-gated Tc-99m sestamibi SPECT" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "T.M. Bateman" 1 => "G.V. Heller" 2 => "A.I. McGhie" 3 => "J.D. Friedman" 4 => "J.A. Case" 5 => "J.R. Bryngelson" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.nuclcard.2005.12.004" "Revista" => array:6 [ "tituloSerie" => "J Nucl Cardiol" "fecha" => "2006" "volumen" => "13" "paginaInicial" => "24" "paginaFinal" => "33" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/16464714" "web" => "Medline" ] ] ] ] ] ] ] ] 11 => array:3 [ "identificador" => "bib0190" "etiqueta" => "12" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Evaluation of a decision support system for interpretation of myocardial perfusion gated SPECT" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "M. Lomsky" 1 => "P. Gjertsson" 2 => "L. Johansson" 3 => "J. Richter" 4 => "M. Ohlsson" 5 => "D. Tout" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/s00259-008-0746-9" "Revista" => array:6 [ "tituloSerie" => "Eur J Nucl Med Mol Imaging" "fecha" => "2008" "volumen" => "35" "paginaInicial" => "1523" "paginaFinal" => "1529" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/18392822" "web" => "Medline" ] ] ] ] ] ] ] ] 12 => array:3 [ "identificador" => "bib0195" "etiqueta" => "13" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "PERFEX: an expert system for interpreting 3D myocardial perfusion" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:5 [ 0 => "N. Ezquerra" 1 => "R. Mullick" 2 => "C.D. Cooke" 3 => "E.G. Krawczynska" 4 => "E.V. Garcia" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:6 [ "tituloSerie" => "Expert Syst Appl" "fecha" => "1993" "volumen" => "6" "paginaInicial" => "459" "paginaFinal" => "468" "itemHostRev" => array:3 [ "pii" => "S1462388909001409" "estado" => "S300" "issn" => "14623889" ] ] ] ] ] ] ] 13 => array:3 [ "identificador" => "bib0200" "etiqueta" => "14" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Development of an expert system for interpreting medical images. Proceedings of the IEEE International Conference on Systems" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "N. Ezquerra" 1 => "E. Garcia" 2 => "E. DePuey" 3 => "W. Robbins" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "Man Cybern" "fecha" => "1986" "volumen" => "1" "paginaInicial" => "205" "paginaFinal" => "210" ] ] ] ] ] ] 14 => array:3 [ "identificador" => "bib0205" "etiqueta" => "15" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Diagnostic performance of an expert system for the interpretation of myocardial perfusion SPECT studies" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "E.V. Garcia" 1 => "C.D. Cooke" 2 => "R.D. Folks" 3 => "C.A. Santana" 4 => "E.G. Krawczynska" 5 => "L. De Braal" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:6 [ "tituloSerie" => "J Nucl Med" "fecha" => "2001" "volumen" => "42" "paginaInicial" => "1185" "paginaFinal" => "1191" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/11483678" "web" => "Medline" ] ] ] ] ] ] ] ] 15 => array:3 [ "identificador" => "bib0210" "etiqueta" => "16" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "WeAidU—a decision support system for myocardial perfusion images using artificial neural networks" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "M. Ohlsson" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:6 [ "tituloSerie" => "Artif Intell Med" "fecha" => "2004" "volumen" => "30" "paginaInicial" => "49" "paginaFinal" => "60" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/14684264" "web" => "Medline" ] ] ] ] ] ] ] ] 16 => array:3 [ "identificador" => "bib0215" "etiqueta" => "17" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Artificial neural network modeling enhances risk stratification and can reduce downstream testing for patients with suspected acute coronary syndromes, negative cardiac biomarkers, and normal ECGs" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "H.A. Isma’eel" 1 => "P.C. Cremer" 2 => "S. Khalaf" 3 => "M.M. Almedawar" 4 => "I.H. Elhajj" 5 => "G.E. Sakr" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/s10554-015-0821-9" "Revista" => array:7 [ "tituloSerie" => "Int J Cardiovasc Imaging" "fecha" => "2016" "volumen" => "32" "paginaInicial" => "687" "paginaFinal" => "696" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/26626458" "web" => "Medline" ] ] "itemHostRev" => array:3 [ "pii" => "S1462388911000512" "estado" => "S300" "issn" => "14623889" ] ] ] ] ] ] ] 17 => array:3 [ "identificador" => "bib0220" "etiqueta" => "18" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Improved accuracy of myocardial perfusion SPECT for detection of coronary artery disease by machine learning in a large population" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "R. Arsanjani" 1 => "Y. Xu" 2 => "D. Dey" 3 => "V. Vahistha" 4 => "A. Shalev" 5 => "R. Nakanishi" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/s12350-013-9706-2" "Revista" => array:6 [ "tituloSerie" => "J Nucl Cardiol" "fecha" => "2013" "volumen" => "20" "paginaInicial" => "553" "paginaFinal" => "562" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/23703378" "web" => "Medline" ] ] ] ] ] ] ] ] 18 => array:3 [ "identificador" => "bib0225" "etiqueta" => "19" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:1 [ "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "M.T. Hagan" 1 => "H.B. Demuth" 2 => "M.H. Beale" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Libro" => array:3 [ "fecha" => "1996" "editorial" => "PWS Pub" "editorialLocalizacion" => "Boston" ] ] ] ] ] ] 19 => array:3 [ "identificador" => "bib0230" "etiqueta" => "20" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Potential diagnostic value of 131 I-MIBG myocardial scintigraphy in discrimination between Alzheimer disease and dementia with Lewy bodies" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "M. Abbasi" 1 => "N. Ghalandari" 2 => "S. Farzanefar" 3 => "V. Aghamollaii" 4 => "M. Ahmadi" 5 => "M. Ganji" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.clineuro.2017.10.024" "Revista" => array:6 [ "tituloSerie" => "Clin Neurol Neurosurg" "fecha" => "2017" "volumen" => "163" "paginaInicial" => "163" "paginaFinal" => "166" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/29112909" "web" => "Medline" ] ] ] ] ] ] ] ] 20 => array:3 [ "identificador" => "bib0235" "etiqueta" => "21" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Deep residual learning for image recognition" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "K. He" 1 => "X. Zhang" 2 => "S. Ren" 3 => "J. Sun" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "LibroEditado" => array:4 [ "titulo" => "Proceedings of the IEEE conference on computer vision and pattern recognition" "paginaInicial" => "770" "paginaFinal" => "778" "serieFecha" => "2016" ] ] ] ] ] ] 21 => array:3 [ "identificador" => "bib0240" "etiqueta" => "22" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Automated interpretation of myocardial perfusion images with multilayer perceptron network as a decision support system" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "M. Eftekhari" 1 => "M. Abbasi" 2 => "A. Tarafdari" 3 => "A. Emami-Ardekani" 4 => "S. Farzanefar" 5 => "F. Kalantari" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "J Med Imaging Health Inf" "fecha" => "2018" "volumen" => "8" "paginaInicial" => "1844" "paginaFinal" => "1849" ] ] ] ] ] ] 22 => array:3 [ "identificador" => "bib0245" "etiqueta" => "23" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "The prognostic value of cardiac SPECT performed at the primary care physician's office" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "R. Doukky" 1 => "N. Frogge" 2 => "G. Balakrishnan" 3 => "K. Hayes" 4 => "F.M. Collado" 5 => "M.O. Rangel" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/s12350-013-9676-4" "Revista" => array:6 [ "tituloSerie" => "J Nucl Cardiol" "fecha" => "2013" "volumen" => "20" "paginaInicial" => "519" "paginaFinal" => "528" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/23475438" "web" => "Medline" ] ] ] ] ] ] ] ] 23 => array:3 [ "identificador" => "bib0250" "etiqueta" => "24" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Accuracy of an artificial neural network for detecting a regional abnormality in myocardial perfusion SPECT" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "T. Shibutani" 1 => "K. Nakajima" 2 => "H. Wakabayashi" 3 => "H. Mori" 4 => "S. Matsuo" 5 => "H. Yoneyama" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/s12149-012-0652-x" "Revista" => array:5 [ "tituloSerie" => "Ann Nucl Med" "fecha" => "2018" "paginaInicial" => "1" "paginaFinal" => "7" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/22914968" "web" => "Medline" ] ] ] ] ] ] ] ] 24 => array:3 [ "identificador" => "bib0255" "etiqueta" => "25" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Deep learning analysis of upright-supine high-efficiency SPECT myocardial perfusion imaging for prediction of obstructive coronary artery disease: a multicenter study" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "J.A. Betancur" 1 => "L.-H. Hu" 2 => "F. Commandeur" 3 => "T. Sharir" 4 => "A.J. Einstein" 5 => "M.B. Fish" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.2967/jnumed.118.213538" "Revista" => array:5 [ "tituloSerie" => "J Nucl Med" "fecha" => "2018" "volumen" => "59" "paginaInicial" => "507" "itemHostRev" => array:3 [ "pii" => "S0140673605665440" "estado" => "S300" "issn" => "01406736" ] ] ] ] ] ] ] 25 => array:3 [ "identificador" => "bib0260" "etiqueta" => "26" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Deep learning for prediction of obstructive disease from fast myocardial perfusion SPECT: a multicenter study" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "J. Betancur" 1 => "F. Commandeur" 2 => "M. Motlagh" 3 => "T. Sharir" 4 => "A.J. Einstein" 5 => "S. Bokhari" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.jcmg.2018.01.020" "Revista" => array:6 [ "tituloSerie" => "JACC Cardiovasc Imaging" "fecha" => "2018" "volumen" => "11" "paginaInicial" => "1654" "paginaFinal" => "1663" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/29550305" "web" => "Medline" ] ] ] ] ] ] ] ] ] ] ] ] ] "idiomaDefecto" => "en" "url" => "/22538089/0000003800000005/v1_201909030619/S2253808919300680/v1_201909030619/en/main.assets" "Apartado" => array:4 [ "identificador" => "34047" "tipo" => "SECCION" "en" => array:2 [ "titulo" => "Original article" "idiomaDefecto" => true ] "idiomaDefecto" => "en" ] "PDF" => "https://static.elsevier.es/multimedia/22538089/0000003800000005/v1_201909030619/S2253808919300680/v1_201909030619/en/main.pdf?idApp=UINPBA00004N&text.app=https://www.elsevier.es/" "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S2253808919300680?idApp=UINPBA00004N" ]
Journal Information
Share
Download PDF
More article options
Original Article
Improved diagnostic accuracy for myocardial perfusion imaging using artificial neural networks on different input variables including clinical and quantification data
Precisión diagnóstica mejorada para la imagen de perfusión miocárdica usando redes neuronales artificiales en diferentes variables de entrada incluyendo datos clínicos y de cuantificación
Reza Rahmania, Parisa Niazib, Maryam Naserib, Mohamadreza Neishabourib, Saeed Farzanefarb, Mohammad Eftekharic, Farhang Derakhshanb, Reza Mollazadeha, Alipasha Meysamid, Mehrshad Abbasib,
Corresponding author
a Cardiology Department, Imam-Khomeini Hospital Complex, Tehran University of Medical Sciences, Tehran, Iran
b Department of Nuclear Medicine, Vali-asr Hospital, Tehran University of Medical Sciences, Tehran, Iran
c Research Institute for Nuclear Medicine, Shariati Hospital, Tehran University of Medical Sciences, Tehran, Iran
d Department of Social Medicine, Tehran University of Medical Sciences, Tehran, Iran