was read the article
array:22 [ "pii" => "S1579212920302226" "issn" => "15792129" "doi" => "10.1016/j.arbr.2019.11.020" "estado" => "S300" "fechaPublicacion" => "2020-09-01" "aid" => "2344" "copyrightAnyo" => "2020" "documento" => "article" "crossmark" => 1 "subdocumento" => "fla" "cita" => "Arch Bronconeumol. 2020;56:564-70" "abierto" => array:3 [ "ES" => false "ES2" => false "LATM" => false ] "gratuito" => false "lecturas" => array:1 [ "total" => 0 ] "itemSiguiente" => array:18 [ "pii" => "S1579212920301695" "issn" => "15792129" "doi" => "10.1016/j.arbr.2020.07.004" "estado" => "S300" "fechaPublicacion" => "2020-09-01" "aid" => "2328" "documento" => "article" "crossmark" => 1 "subdocumento" => "fla" "cita" => "Arch Bronconeumol. 2020;56:571-7" "abierto" => array:3 [ "ES" => false "ES2" => false "LATM" => false ] "gratuito" => false "lecturas" => array:1 [ "total" => 0 ] "en" => array:13 [ "idiomaDefecto" => true "cabecera" => "<span class="elsevierStyleTextfn">Original Article</span>" "titulo" => "Prevalence of Alpha-1 antitrypsin deficiency in COPD patients in Argentina. The DAAT.AR study" "tienePdf" => "en" "tieneTextoCompleto" => "en" "tieneResumen" => array:2 [ 0 => "en" 1 => "es" ] "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "571" "paginaFinal" => "577" ] ] "titulosAlternativos" => array:1 [ "es" => array:1 [ "titulo" => "Prevalencia de déficit de alfa-1 antitripsina en pacientes con EPOC en Argentina. Estudio DAAT.AR" ] ] "contieneResumen" => array:2 [ "en" => true "es" => true ] "contieneTextoCompleto" => array:1 [ "en" => true ] "contienePdf" => array:1 [ "en" => true ] "resumenGrafico" => array:2 [ "original" => 0 "multimedia" => array:8 [ "identificador" => "fig0005" "etiqueta" => "Fig. 1" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr1.jpeg" "Alto" => 1367 "Ancho" => 2167 "Tamanyo" => 149237 ] ] "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0005" "detalle" => "Fig. " "rol" => "short" ] ] "descripcion" => array:1 [ "en" => "<p id="spar0005" class="elsevierStyleSimplePara elsevierViewall">Study flow chart.</p>" ] ] ] "autores" => array:1 [ 0 => array:2 [ "autoresLista" => "Guillermo Menga, Mariano Fernandez Acquier, Andrés L. Echazarreta, Patricia B. Sorroche, Maria V. Lorenzon, Martin E. Fernández, María S. Saez" "autores" => array:8 [ 0 => array:2 [ "nombre" => "Guillermo" "apellidos" => "Menga" ] 1 => array:2 [ "nombre" => "Mariano Fernandez" "apellidos" => "Acquier" ] 2 => array:2 [ "nombre" => "Andrés L." "apellidos" => "Echazarreta" ] 3 => array:2 [ "nombre" => "Patricia B." "apellidos" => "Sorroche" ] 4 => array:2 [ "nombre" => "Maria V." "apellidos" => "Lorenzon" ] 5 => array:2 [ "nombre" => "Martin E." "apellidos" => "Fernández" ] 6 => array:2 [ "nombre" => "María S." "apellidos" => "Saez" ] 7 => array:1 [ "colaborador" => "y grupo de estudio DAAT.AR" ] ] ] ] ] "idiomaDefecto" => "en" "Traduccion" => array:1 [ "es" => array:9 [ "pii" => "S0300289619305782" "doi" => "10.1016/j.arbres.2019.11.010" "estado" => "S300" "subdocumento" => "" "abierto" => array:3 [ "ES" => true "ES2" => true "LATM" => true ] "gratuito" => true "lecturas" => array:1 [ "total" => 0 ] "idiomaDefecto" => "es" "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0300289619305782?idApp=UINPBA00003Z" ] ] "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S1579212920301695?idApp=UINPBA00003Z" "url" => "/15792129/0000005600000009/v1_202009150705/S1579212920301695/v1_202009150705/en/main.assets" ] "itemAnterior" => array:19 [ "pii" => "S1579212920301725" "issn" => "15792129" "doi" => "10.1016/j.arbr.2020.07.005" "estado" => "S300" "fechaPublicacion" => "2020-09-01" "aid" => "2346" "copyright" => "SEPAR" "documento" => "article" "crossmark" => 1 "subdocumento" => "fla" "cita" => "Arch Bronconeumol. 2020;56:559-63" "abierto" => array:3 [ "ES" => false "ES2" => false "LATM" => false ] "gratuito" => false "lecturas" => array:1 [ "total" => 0 ] "en" => array:13 [ "idiomaDefecto" => true "cabecera" => "<span class="elsevierStyleTextfn">Original Article</span>" "titulo" => "Smoking-Attributable mortality in Spain in 2016" "tienePdf" => "en" "tieneTextoCompleto" => "en" "tieneResumen" => array:2 [ 0 => "en" 1 => "es" ] "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "559" "paginaFinal" => "563" ] ] "titulosAlternativos" => array:1 [ "es" => array:1 [ "titulo" => "Mortalidad atribuible al consumo de tabaco en España 2016" ] ] "contieneResumen" => array:2 [ "en" => true "es" => true ] "contieneTextoCompleto" => array:1 [ "en" => true ] "contienePdf" => array:1 [ "en" => true ] "resumenGrafico" => array:2 [ "original" => 0 "multimedia" => array:8 [ "identificador" => "fig0005" "etiqueta" => "Fig. 1" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr1.jpeg" "Alto" => 1130 "Ancho" => 1500 "Tamanyo" => 74940 ] ] "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at0005" "detalle" => "Fig. " "rol" => "short" ] ] "descripcion" => array:1 [ "en" => "<p id="spar0005" class="elsevierStyleSimplePara elsevierViewall">Mortality attributable to current use (smokers) and past use (former smokers), by sex and age groups. Spanish population ≥35 years, 2016.</p>" ] ] ] "autores" => array:1 [ 0 => array:2 [ "autoresLista" => "Mónica Pérez-Ríos, Anna Schiaffino, Agustín Montes, Esteve Fernández, María José López, José María Martínez-Sánchez, Xisca Sureda, Cristina Martínez, Marcela Fu, Xavier García Continente, José Luis Carretero, Iñaki Galán" "autores" => array:12 [ 0 => array:2 [ "nombre" => "Mónica" "apellidos" => "Pérez-Ríos" ] 1 => array:2 [ "nombre" => "Anna" "apellidos" => "Schiaffino" ] 2 => array:2 [ "nombre" => "Agustín" "apellidos" => "Montes" ] 3 => array:2 [ "nombre" => "Esteve" "apellidos" => "Fernández" ] 4 => array:2 [ "nombre" => "María José" "apellidos" => "López" ] 5 => array:2 [ "nombre" => "José María" "apellidos" => "Martínez-Sánchez" ] 6 => array:2 [ "nombre" => "Xisca" "apellidos" => "Sureda" ] 7 => array:2 [ "nombre" => "Cristina" "apellidos" => "Martínez" ] 8 => array:2 [ "nombre" => "Marcela" "apellidos" => "Fu" ] 9 => array:2 [ "nombre" => "Xavier García" "apellidos" => "Continente" ] 10 => array:2 [ "nombre" => "José Luis" "apellidos" => "Carretero" ] 11 => array:2 [ "nombre" => "Iñaki" "apellidos" => "Galán" ] ] ] ] ] "idiomaDefecto" => "en" "Traduccion" => array:1 [ "es" => array:9 [ "pii" => "S0300289619305964" "doi" => "10.1016/j.arbres.2019.11.021" "estado" => "S300" "subdocumento" => "" "abierto" => array:3 [ "ES" => true "ES2" => true "LATM" => true ] "gratuito" => true "lecturas" => array:1 [ "total" => 0 ] "idiomaDefecto" => "es" "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S0300289619305964?idApp=UINPBA00003Z" ] ] "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S1579212920301725?idApp=UINPBA00003Z" "url" => "/15792129/0000005600000009/v1_202009150705/S1579212920301725/v1_202009150705/en/main.assets" ] "en" => array:21 [ "idiomaDefecto" => true "cabecera" => "<span class="elsevierStyleTextfn">Original Article</span>" "titulo" => "Patient Management Assisted by a Neural Network Reduces Mortality in an Intermediate Care Unit" "tieneTextoCompleto" => true "paginas" => array:1 [ 0 => array:2 [ "paginaInicial" => "564" "paginaFinal" => "570" ] ] "autores" => array:1 [ 0 => array:4 [ "autoresLista" => "Sarah Heili-Frades, Pablo Minguez, Ignacio Mahillo Fernández, Luis Jiménez Hiscock, Arnoldo Santos, Daniel Heili Frades, María del Pilar Carballosa de Miguel, Itziar Fernández Ormaechea, Laura Álvarez Suárez, Alba Naya Prieto, Nicolás González Mangado, Germán Peces-Barba Romero" "autores" => array:12 [ 0 => array:4 [ "nombre" => "Sarah" "apellidos" => "Heili-Frades" "email" => array:1 [ 0 => "SHeili@fjd.es" ] "referencia" => array:2 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">a</span>" "identificador" => "aff0005" ] 1 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">*</span>" "identificador" => "cor0005" ] ] ] 1 => array:4 [ "nombre" => "Pablo" "apellidos" => "Minguez" "email" => array:1 [ 0 => "pablo.minguez@quironsalud.es" ] "referencia" => array:2 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">b</span>" "identificador" => "aff0010" ] 1 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">*</span>" "identificador" => "cor0005" ] ] ] 2 => array:3 [ "nombre" => "Ignacio" "apellidos" => "Mahillo Fernández" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">c</span>" "identificador" => "aff0015" ] ] ] 3 => array:3 [ "nombre" => "Luis" "apellidos" => "Jiménez Hiscock" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">d</span>" "identificador" => "aff0020" ] ] ] 4 => array:3 [ "nombre" => "Arnoldo" "apellidos" => "Santos" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">e</span>" "identificador" => "aff0025" ] ] ] 5 => array:3 [ "nombre" => "Daniel" "apellidos" => "Heili Frades" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">f</span>" "identificador" => "aff0030" ] ] ] 6 => array:3 [ "nombre" => "María del Pilar" "apellidos" => "Carballosa de Miguel" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">a</span>" "identificador" => "aff0005" ] ] ] 7 => array:3 [ "nombre" => "Itziar" "apellidos" => "Fernández Ormaechea" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">a</span>" "identificador" => "aff0005" ] ] ] 8 => array:3 [ "nombre" => "Laura" "apellidos" => "Álvarez Suárez" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">a</span>" "identificador" => "aff0005" ] ] ] 9 => array:3 [ "nombre" => "Alba" "apellidos" => "Naya Prieto" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">a</span>" "identificador" => "aff0005" ] ] ] 10 => array:3 [ "nombre" => "Nicolás" "apellidos" => "González Mangado" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">a</span>" "identificador" => "aff0005" ] ] ] 11 => array:3 [ "nombre" => "Germán" "apellidos" => "Peces-Barba Romero" "referencia" => array:1 [ 0 => array:2 [ "etiqueta" => "<span class="elsevierStyleSup">a</span>" "identificador" => "aff0005" ] ] ] ] "afiliaciones" => array:6 [ 0 => array:3 [ "entidad" => "Intermediate Respiratory Care Unit, IIS-Fundación Jiménez Díaz Quirón Salud, Madrid, CIBER de enfermedades respiratorias (CIBERES), REVA Network, Madrid, Spain, Avda Reyes Católicos n°2, CP 28040 Madrid, Spain" "etiqueta" => "a" "identificador" => "aff0005" ] 1 => array:3 [ "entidad" => "Genetics and Genomics Department, IIS-Fundación Jiménez Díaz, Madrid, Center for Biomedical Network Research on Rare Diseases (CIBERER), ISCIII, Madrid, Spain" "etiqueta" => "b" "identificador" => "aff0010" ] 2 => array:3 [ "entidad" => "Department of Biostatistics and Epidemiology, IIS-Fundación Jiménez Díaz UAM, Madrid, Spain" "etiqueta" => "c" "identificador" => "aff0015" ] 3 => array:3 [ "entidad" => "Thoracic Surgery Department, Sanchinarro University Hospital, HM Hospitals Group, Madrid, Spain" "etiqueta" => "d" "identificador" => "aff0020" ] 4 => array:3 [ "entidad" => "ITC Ingeniería y Técnicas Clínicas, CIBER de Enfermedades Respiratorias (CIBERES), Madrid, Spain" "etiqueta" => "e" "identificador" => "aff0025" ] 5 => array:3 [ "entidad" => "Civil Engineering, Soletanche-Bachy, Paris, France" "etiqueta" => "f" "identificador" => "aff0030" ] ] "correspondencia" => array:1 [ 0 => array:3 [ "identificador" => "cor0005" "etiqueta" => "⁎" "correspondencia" => "Corresponding authors." ] ] ] ] "titulosAlternativos" => array:1 [ "es" => array:1 [ "titulo" => "El manejo del paciente asistido por una red neuronal disminuye la mortalidad en una unidad de cuidados intermedios" ] ] "resumenGrafico" => array:2 [ "original" => 1 "multimedia" => array:5 [ "identificador" => "fig0035" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => false "mostrarDisplay" => true "figura" => array:1 [ 0 => array:4 [ "imagen" => "fx1.jpeg" "Alto" => 904 "Ancho" => 1333 "Tamanyo" => 84897 ] ] ] ] "textoCompleto" => "<span class="elsevierStyleSections"><span id="sec0005" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0070">Introduction</span><p id="par0005" class="elsevierStylePara elsevierViewall">Respiratory diseases are the leading cause of mortality in general hospitals.<a class="elsevierStyleCrossRef" href="#bib0205"><span class="elsevierStyleSup">1</span></a> Severely ill patients with acute respiratory failure (ARF), acute exacerbation of chronic obstructive pulmonary disease (AECOPD), weaning procedures or community-acquired pneumonia (CAP) have been historically admitted to Intensive Care Units (ICUs). However, due to the limited availability and high cost of ICU beds, these patients are often admitted primarily to other units, chiefly in Intermediate Respiratory Care Units (IRCUs).</p><p id="par0010" class="elsevierStylePara elsevierViewall">One of the most relevant outcomes of IRCUs is patient mortality. Indeed, several studies focus on independent factors related to mortality in patients receiving noninvasive ventilation in various diseases, such as COPD,<a class="elsevierStyleCrossRefs" href="#bib0210"><span class="elsevierStyleSup">2–4</span></a> pneumonia,<a class="elsevierStyleCrossRefs" href="#bib0225"><span class="elsevierStyleSup">5,6</span></a> cardiac failure,<a class="elsevierStyleCrossRef" href="#bib0235"><span class="elsevierStyleSup">7</span></a> Acute Respiratory Distress Syndrome,<a class="elsevierStyleCrossRef" href="#bib0240"><span class="elsevierStyleSup">8</span></a> asthma,<a class="elsevierStyleCrossRef" href="#bib0245"><span class="elsevierStyleSup">9</span></a> immunocompromised patients,<a class="elsevierStyleCrossRefs" href="#bib0250"><span class="elsevierStyleSup">10,11</span></a> elderly patients,<a class="elsevierStyleCrossRef" href="#bib0260"><span class="elsevierStyleSup">12</span></a> and interstitial lung diseases.<a class="elsevierStyleCrossRef" href="#bib0415"><span class="elsevierStyleSup">13</span></a></p><p id="par0015" class="elsevierStylePara elsevierViewall">IRCUs have traditionally used various scoring systems for predicting mortality inherited from ICUs, such as the APACHE system,<a class="elsevierStyleCrossRef" href="#bib0270"><span class="elsevierStyleSup">14</span></a> the Acute Physiology Score (APS) III,<a class="elsevierStyleCrossRef" href="#bib0420"><span class="elsevierStyleSup">15</span></a> Simplified Acute Physiology Score (SAPS),<a class="elsevierStyleCrossRef" href="#bib0425"><span class="elsevierStyleSup">16</span></a> SAPS II,<a class="elsevierStyleCrossRef" href="#bib0285"><span class="elsevierStyleSup">17</span></a> the Sequential Organ Failure Assessment (SOFA) score,<a class="elsevierStyleCrossRef" href="#bib0430"><span class="elsevierStyleSup">18</span></a> the Logistic Organ Dysfunction Score (LODS),<a class="elsevierStyleCrossRef" href="#bib0435"><span class="elsevierStyleSup">19</span></a> and the Oxford Acute Severity of Illness Score (OASIS).<a class="elsevierStyleCrossRef" href="#bib0300"><span class="elsevierStyleSup">20</span></a> It has been generally accepted that these models tend to lack sufficient calibration to be used on an individual level,<a class="elsevierStyleCrossRef" href="#bib0305"><span class="elsevierStyleSup">21</span></a> and research goals shifted to quantify ICU and hospital performance in aggregate.</p><p id="par0020" class="elsevierStylePara elsevierViewall">Predictive tools can be developed using a variety of techniques from clinical judgment to statistical modeling,<a class="elsevierStyleCrossRefs" href="#bib0440"><span class="elsevierStyleSup">22,23</span></a> including some based on machine-learning algorithms such as Neural Networks (NN).<a class="elsevierStyleCrossRefs" href="#bib0320"><span class="elsevierStyleSup">24,25</span></a> The ability to predict the risk of mortality for ICU and IRCU patients could facilitate optimal allocation of staff and resources to high-risk patients and ensure timely interventions.</p><p id="par0025" class="elsevierStylePara elsevierViewall">We aimed to build a statistical framework able to adapt to specific features of a hospital in order to identify and classify mortality predictors of an IRCU.</p></span><span id="sec0010" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0075">Material and Methods</span><span id="sec0015" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0080">Study Population</span><p id="par0030" class="elsevierStylePara elsevierViewall">The IRCU of University Hospital fundacion Jimenez Diaz is a high complexity unit with 15% of patients requiring complicated postoperative weaning procedures, while vasoactive treatment prevalence is approximately 26%. The unit has 5 beds (1:5 patient nurse ratio), being able to reach 8 in the periods of greatest need for care (1:4 patient nurse ratio in this scenario). Our unit is an open room to guarantee the global supervision of the patients that are completely telemonitorized. <a class="elsevierStyleCrossRef" href="#sec0115">Supplementary Figures 1–3</a> describe the material and human resources, as well as its complexity according to the average GRD value of the unit. The study was aproved by our Ethic Committee. De-identified medical records were confidentially collected from a total of 1966 patients admitted to the FJD-Hospital IRCU (Madrid, Spain) from January 2007 to December 2017. A second cohort of 230 new patients with confidential records recruited from October 2018 to September 2019 in the same IRCU, were used to measure the performance of the new IRCU protocol based on the conclusions of this work. This is an observational and retrospective study. All the patients admitted to our IRCU were selected for the study and no exclusión criteria was imposed.</p></span><span id="sec0020" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0085">Data Collection and Variables Included in the Study</span><p id="par0035" class="elsevierStylePara elsevierViewall">Vital signs of patients were recorded upon arrival at the hospital, before being admitted to the IRCU: respiratory rate (RR), temperature (T), systolic blood pressure (SBP), and diastolic blood pressure (DBP). Laboratory findings including hemoglobin (Hb), platelets (PL), leucocytes (Leucos), the International Normalized Ratio (INR), blood glucose (GLU), blood potassium (K), sodium (NA) and creatinine (CREAT) were also registered. Blood gases at the time of hospital admission were recorded (Fi02 21%), including partial oxygen pressure (P02), partial carbon dioxide pressure (PC02), PH, bicarbonates (SBC) and base excess (BE). Age and individual mortality or survival upon discharge from the IRCU was extracted from medical histories. The data was collected following standard protocols by the same personnel over the whole time period and in the two cohorts included in the study.</p></span><span id="sec0025" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0090">Missing Data Imputation</span><p id="par0040" class="elsevierStylePara elsevierViewall">A criteria for variable exclusion was defined in order to avoid introduction of statistical noise that may introduce bias in final results. Parameters with a high percentage (>25%) of missing values were excluded from the analysis. For the rest of the parameters we perform the K-nearest neighbors (KNN) imputation method implemented in the DMwR R package.</p></span><span id="sec0030" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0095">Principal Component Analysis</span><p id="par0045" class="elsevierStylePara elsevierViewall">Principal component analysis (PCA) was performed on the matrix with missing data imputation, using the pca3d R library.</p></span><span id="sec0035" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0100">Sample Classification Based on Variables, Cut-off Values and Logistic Regression Model</span><p id="par0050" class="elsevierStylePara elsevierViewall">Using ROC curves and Youden's J statistic we obtained the cut-off point that best discriminates the mortality status for each of the parameters. Based on these cut-off points we defined a binary classification for each parameter (<span class="elsevierStyleItalic">P</span>-value <.2) to feed a multivariate logistic regression model. Area Under the Curve (AUC), sensitivity and specificity were calculated using a ROC curve. An internal validation of the model was performed by bootstrap method to correct for optimistic prediction. A total of 1000 bootstrap samples with replacement were generated, and the differences in AUC on the bootstrap samples and the original sample were calculated. The goodness of fit of the model was evaluated by the Hosmer and Lemeshow test.</p></span><span id="sec0040" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0105">Neural Network Implementation and Data Re-sampling</span><p id="par0055" class="elsevierStylePara elsevierViewall">A NN model was applied using the caret R package. Data matrix was normalized using the min-max scale method. Ten re-sampled matrices were calculated having samples with mortality<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>1 and a random selection of the same number of samples with mortality<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>0. Every re-sampled matrix is then subject to a 10-fold cross validation process (90% training and 10% testing). Thus, a total of 100 neural network models are performed using “nnet” method with automatic selection of: (i) the optimal number of units per hidden layer between 1 and 5, and (ii) the optimal value for the regularization parameter (between 0.1 and 0.5 with increments of 0.1). The “twoClassSummary” method was used to compute sensitivity, specificity and the AUC. A ROC curve is calculated for the set of predictions and real values within the loop, using the 10-fold cross validation process. The final AUC, accuracy, sensitivity and specificity were calculated as the mean of the 100 neural network models performed in total. Our R script is available at <a href="https://github.com/pminguez/MachineLearning4UnbalancedData">https://github.com/pminguez/MachineLearning4UnbalancedData</a>.</p><p id="par0060" class="elsevierStylePara elsevierViewall">Using the KNN data matrix, we calculate the Spearman correlation between every pair of variables. In order to build the network, we select the pairs that have a correlation coefficient >±0.3 and a <span class="elsevierStyleItalic">P</span>-value <.01. The selected pairs of variables represent the edges of the correlation network.</p></span><span id="sec0045" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0110">Comparison of Failure</span><p id="par0065" class="elsevierStylePara elsevierViewall">In order to compare the failure before and after the new criteria to detect high risk patients was implemented, we fit Poisson regression models to calculate the annual trend of failure risk in the two periods. The relatives risks (RR) were compared using the Wald test, taking the coefficients of the models (logarithm of RR) and its standard errors.</p></span></span><span id="sec0050" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0115">Results</span><span id="sec0055" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0120">Cohort and Dataset Description</span><p id="par0070" class="elsevierStylePara elsevierViewall">A total of 1966 patients were included in the analysis having a global local IRCU mortality rate of 1.68% (33 patients) and a global failure (IRCU mortality<span class="elsevierStyleHsp" style=""></span>+<span class="elsevierStyleHsp" style=""></span>ICU transfer<span class="elsevierStyleHsp" style=""></span>+<span class="elsevierStyleHsp" style=""></span>outside IRCU delayed mortality) of about 5.39% (106 patients). <a class="elsevierStyleCrossRef" href="#tbl0005">Table 1</a> describes the study population with epidemiologic data and treatment used and <a class="elsevierStyleCrossRef" href="#tbl0010">Table 2</a> shows mean and standard deviation values for each of the variable used (INR was excluded). A PCA of the patients’ features did not show observable differences between patient's classifications according to mortality status (<a class="elsevierStyleCrossRef" href="#fig0005">Fig. 1</a>).</p><elsevierMultimedia ident="tbl0005"></elsevierMultimedia><elsevierMultimedia ident="tbl0010"></elsevierMultimedia><elsevierMultimedia ident="fig0005"></elsevierMultimedia></span><span id="sec0060" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0125">Physiological Explanation of Related Variables</span><p id="par0075" class="elsevierStylePara elsevierViewall">To understand how the selected variables are physiologically linked, we calculated their paired correlations between all pairs of variables. <a class="elsevierStyleCrossRef" href="#fig0010">Fig. 2</a> shows the pairs of variables with a significant correlation score (rho <0.3 and <span class="elsevierStyleItalic">P</span>-value <.01). Interestingly, we found that potassium levels (K) and acidosis (PH) were closely associated, but not with other parameters related to renal failure. The correlation network shows consistency between acid base variables (PC0<span class="elsevierStyleInf">2</span>, SBC and BE). It also presents independent relationships in hemodynamics and blood cell series.</p><elsevierMultimedia ident="fig0010"></elsevierMultimedia></span><span id="sec0065" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0130">Low Mortality Rate Masks the Real Performance of the Prediction</span><p id="par0080" class="elsevierStylePara elsevierViewall">Our dataset has a mortality ratio below 2%. In <a class="elsevierStyleCrossRef" href="#fig0015">Fig. 3</a> we show the performance of our NN algorithm over the dataset. Despite an acceptable area under the curve (AUC) and the extremely high accuracy value (0.98), it displays a very low specificity (0.5) which reflects that working with the whole dataset introduces a strong bias toward the learning of features that favor alive over death. In order to avoid the imbalanced class distribution bias, we introduced a re-sampling step (see Methods) where the dataset is down-sampled to have the same number of dead and alive events. <a class="elsevierStyleCrossRef" href="#fig0020">Fig. 4</a>A shows the NN performance over a set of re-sampled matrices that have a balanced class distribution. Although the behavior of the model in terms of accuracy does not improve the performance using the unbalanced dataset, we observe and increase in AUC (0.71), sensitivity (0.59) and specificity (0.59) values. This model was employed for further analysis.</p><elsevierMultimedia ident="fig0015"></elsevierMultimedia><elsevierMultimedia ident="fig0020"></elsevierMultimedia></span><span id="sec0070" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0135">Parameter Selection in the Prediction of Patient Death</span><p id="par0085" class="elsevierStylePara elsevierViewall">The NN classification using the balanced data strategy shows that thrombocytopenia (PL), metabolic acidosis (SBC and PH), anemia (Hb), tachypnea (RR), age (AGE), sodium levels (NA), hypoxemia (PO2), leukocytopenia (LEUCOS), and hyperkalemia (K) are the most relevant parameters associated with mortality (<a class="elsevierStyleCrossRef" href="#fig0020">Fig. 4</a>B). The combination of these parameters reflects potential respiratory sepsis associated with hypoxemia and secondary pancytopenia or a primary oncohaemathologic disorder with associated septic respiratory distress. These results agree with our own experience when we have reviewed our IRCU's behavior in previous years.</p></span><span id="sec0075" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0140">Rapid Decisions Based on Parameters’ Cut-off Values</span><p id="par0090" class="elsevierStylePara elsevierViewall">In order to provide a complementary decision tool for risk prediction, we calculated the cut-off value (Youden J index) that best discriminated between dead and alive cases for every variable considered in the NN model (<a class="elsevierStyleCrossRef" href="#sec0115">Supplementary Table 1</a>) and a univariate logistic regression models was performed (<a class="elsevierStyleCrossRef" href="#sec0115">Supplementary Table 2</a>). We observed that from the top 10 variables most weighted in the NN model, six were a <span class="elsevierStyleItalic">P</span>-value <.05 and eight <0.1. In a multivariate logistic regression analysis, we found RR, LEUCOS, Hb, K and PH as the best combination of variables that best discriminate between classes (<a class="elsevierStyleCrossRef" href="#tbl0015">Table 3</a>). This whole set of predictors is also found amongst the top 10 variables when sorted by importance in the NN model, again suggesting an overlapping signal coming from independent methods. The AUC for the logistic model was 0.75 (<a class="elsevierStyleCrossRef" href="#fig0025">Fig. 5</a>), and the bootstrap internal validation indicated an optimism of 0.016, which reflects the robustness of the model.</p><elsevierMultimedia ident="tbl0015"></elsevierMultimedia><elsevierMultimedia ident="fig0025"></elsevierMultimedia></span><span id="sec0080" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0145">An Algorithm for Patient Management in Our IRCU</span><p id="par0095" class="elsevierStylePara elsevierViewall">By combining both analyses, we built a decision algorithm based on the variable classification provided. In order of importance the algorithm ranks the variables as: (1) PL<span class="elsevierStyleHsp" style=""></span><<span class="elsevierStyleHsp" style=""></span>266, (2) SBC<span class="elsevierStyleHsp" style=""></span><<span class="elsevierStyleHsp" style=""></span>26.4, (3) PH<span class="elsevierStyleHsp" style=""></span><<span class="elsevierStyleHsp" style=""></span>7.33, (4) Hb<span class="elsevierStyleHsp" style=""></span><<span class="elsevierStyleHsp" style=""></span>10.4, (5) RR<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>24.5, (6) age<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>63, (7) NA<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>140, (8) P02<span class="elsevierStyleHsp" style=""></span><<span class="elsevierStyleHsp" style=""></span>68<span class="elsevierStyleHsp" style=""></span>mm, (9) LEUCOS<span class="elsevierStyleHsp" style=""></span><<span class="elsevierStyleHsp" style=""></span>3.230, and (10) K<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>3.68.</p><p id="par0100" class="elsevierStylePara elsevierViewall">The new criteria for identification of high risk patients consider the following decisions: (1) Patients with more than 63 years, more than two cytopenias, metabolic acidosis, hypoxemia and hypernatremia with a background of infectious disease received a vigorous antibiotic treatment, and early and aggressive resuscitation of hemodynamic, respiratory and internal environment at the time of arrival regardless of the location of the patient before entering the unit. Management then would be the same but with precocity, on arrival (2) Patients with hypoxemia and metabolic acidosis received enhanced high-flow oxygen therapy either tan NIV immediately after admission in the emergency department to improve their P02/FI02<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>150<span class="elsevierStyleHsp" style=""></span>mmHg after one hour. Metabolic acidosis was urgently counterbalanced with bicarbonates and/or haemodinamic early ressucitation procedures. If they failed to achieve this oxygenation in one hour they should be referred to the intensive care unit. (3) Oncohematological patients who met 80% or more of the criteria and for which we were consulted, were advised to enter directly into the intensive care unit for invasive management.</p></span><span id="sec0085" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0150">The New Patient Stratification Criteria Reduces Mortality in Our IRCU</span><p id="par0105" class="elsevierStylePara elsevierViewall">The algorithm was implemented in our IRCU from October 2018 to September 2019 (230 patients, features shown in <a class="elsevierStyleCrossRef" href="#sec0115">Supplementary Tables 3 and 4</a>). In September 2019 we retrospectively analyzed this cohort. A total of 23 patients received vigorous treatment (decision 1), one of them not recovering and transferred to the ICU surviving. Decision 2 was applied to 33 patients, no patient required transfer to the ICU and there was no deceased. Five patients were subject of decision 3 and 1 was referred to the ICU in such conditions and survived. In total, 61 patients of the cohort were handled differently from how we previously did (26.52%).</p><p id="par0110" class="elsevierStylePara elsevierViewall">In this second cohort we had 3 deceased and a mortality rate of 1.30%. The previous historical average being 1.68% (33patients), which shows more than a 20% of decrease (50% considering only last 7 years). In a wider perspective, the rate of failures (deaths and transfers to ICU) after the algorithm implementation was 3.0% (4 transfers, 3 of them for reasons related to the NN variables selected and the fourth due to refractory hypercapnic ventilatory failure). In order to compare this ratio with the whole series and avoiding the time bias we used Poisson regression models to calculate the annual trend of failure risk in the two periods. The relative risks (RR) were 0.94 and 0.41 from 2004–2017 and 2018–2019 respectively. Both RR being statistically different (Wald test, <span class="elsevierStyleItalic">P</span>-value<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>.065), see <a class="elsevierStyleCrossRef" href="#fig0030">Fig. 6</a> to see global trend over the years.</p><elsevierMultimedia ident="fig0030"></elsevierMultimedia></span></span><span id="sec0090" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0155">Discussion</span><p id="par0115" class="elsevierStylePara elsevierViewall">Big Data is producing a revolution in the management of patients in hospitals and machine-learning methods have been applied to different diseases and conditions.<a class="elsevierStyleCrossRefs" href="#bib0330"><span class="elsevierStyleSup">26–30</span></a> In this sense, ICUs have a long term experience in the analysis of mortality-related factors<a class="elsevierStyleCrossRefs" href="#bib0445"><span class="elsevierStyleSup">31–34</span></a> that have been historically applied also to IRCUs. However, IRCUs have their own specific features, being by definition very inclusive and have criteria, qualities and peculiarities that differ even between centers. Thus, it is difficult to generalize a criteria, as mortality prediction parameters are unit-specific, illustrating the need to personalize the model. Still, a common challenge faced by IRCUs is that mortality is usually much lower than survival as compared to ICUs.<a class="elsevierStyleCrossRefs" href="#bib0375"><span class="elsevierStyleSup">35–37</span></a> However, merging cohorts in order to rise up the number of failure events is not a solution as the results will not be suitable to any of the hospitals if essential differences exist between them. In any case, the variables and their range of values introduced in the machine learning algorithm must be carefully analyzed in order to avoid confounding factors. Other statistical limitations are applied here, for example Youden index might be calculating cut off points below detection threshold. Also, machine learning methods usually need complete data matrices, so imputation methods must be carefully applied in order to reduce statistical noise.</p><p id="par0120" class="elsevierStylePara elsevierViewall">With these aspects in mind, here we present a machine learning model prepared to deal with misbalanced outcomes, that can be applied to any IRCU giving custom predictions of mortality important factors. For our unit we scored an AUC of 0.71 and 0.75 (NN and multivariate logistic regression models respectively) that are comparable or higher to those described previously.<a class="elsevierStyleCrossRef" href="#bib0375"><span class="elsevierStyleSup">35</span></a> The NN results were confirmed by the multivariate regression analysis that also added the cutoffs values for decision making that we included in the final protocol for our IRCU patient management.</p><p id="par0125" class="elsevierStylePara elsevierViewall">In general terms, our study indicates that the factors most related to survival are those associated with hypoxemic respiratory sepsis and secondary pancytopenia or a primary oncohaemathologic disorder with septic respiratory distress, followed by other factors related to respiratory status (hypercapnia), another organ failure (renal failure) or hemodynamic impairment. These results indeed differ from similar studies made in other ICUs<a class="elsevierStyleCrossRefs" href="#bib0390"><span class="elsevierStyleSup">38–40</span></a> where the seven most important features identified were a cumulative sum of urine output, mean, last, minimum and maximum values of BUN, mean value of HCO3 and age. This discrepancy illustrates the differences between IRCUs and ICUs.</p><p id="par0130" class="elsevierStylePara elsevierViewall">Our final criteria (<a class="elsevierStyleCrossRef" href="#tbl0015">Table 3</a>) is closely associated with sepsis. Tachypnea (RR<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>24.5) is universally related with ARF and/or metabolic acidosis, whilst acidosis or potassium levels >3.68 are frequently related to renal failure in these patients (no toxic intake of potassium or medications able to increase these levels were detected). A network correlation analysis (<a class="elsevierStyleCrossRef" href="#fig0010">Fig. 2</a>) gave us the variables dependencies, being hyperkaliemia correlated with acidosis and hemoglobin related to the patient's respiratory status. Leucocytes and platelets are independently and mutually related confirming our observation in patients with severe sepsis associated with bone marrow depression, in primary haematologic malignancies or in onco-haematologic patients receiving cytostatic treatments. High sodium levels may reflect a septic instead of a cardiogenic status.</p><p id="par0135" class="elsevierStylePara elsevierViewall">Our results lead to an interesting interpretation: patients with respiratory sepsis, hypoxemia and secondary haematologic disorders or primary onco-haematologic patients suffering from respiratory failure, must be promptly redirected to the Intensive Care Unit for rigorous management in case of poor initial progress. In any case, priority surveillance must be implemented first for this subgroup of patients followed by those patients presenting factors related to hypercapnic respiratory status, renal failure or hemodynamic impairment.</p><p id="par0140" class="elsevierStylePara elsevierViewall">We show here that the development of a reliable risk-stratification tool in the IRCU is feasible. We have generated a neural network capable of identifying and classifying mortality predictors in the IRCU of a general hospital. When combined with multivariate regression analysis, it has provided us with an extremely useful tool for the real-time monitoring of patients in order to detect specific mortality risks. Our model is supported by a drastic decrease in IRCU failure during the first year of implementation. In addition, our approach has the advantage of being able to improve its performance in the future with the addition of more patients to the cohort. The overall algorithm can be scaled to any type of unit in the world offering personalized results adapted to the particular environment of the unit analyzed.</p></span><span id="sec0095" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0160">Ethics Approval and Consent to Participate</span><p id="par0145" class="elsevierStylePara elsevierViewall">The survey is a retrospective study with de-identified medical record data. No patients management protocols have been altered due to the study. The study was evaluated by our Ethics Committee (act n° 10/19) and approved with n° EO104-19_FJD.</p></span><span id="sec0100" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0165">Funding</span><p id="par0150" class="elsevierStylePara elsevierViewall">The study has no specific funding. ASO has a <span class="elsevierStyleGrantSponsor" id="gs1">Marie Sklodowska-Curie</span> grant (<span class="elsevierStyleGrantNumber" refid="gs1">#796721</span>). PM has a Miguel Servet contract funded by the <span class="elsevierStyleGrantNumber" refid="gs1">ISCIII</span> (<span class="elsevierStyleGrantNumber" refid="gs1">CP16/00116</span>).</p></span><span id="sec0105" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0170">Author Contributions</span><p id="par0155" class="elsevierStylePara elsevierViewall">SHF contributed to the conception and design of the work, did the acquisition, analysis, interpretation of data and wrote the manuscript; PM designed the NN algorithm, performed the analysis and wrote the manuscript; IMF performed the statistical analysis; LJH did a critical revision of intellectual content and language editing; ASO, DH, MPCM and IFO contributed with a critical revision of intellectual content; LAS, ANP, NGM and GPBR critically revised and drafted final manuscript. All authors approved the final version of the manuscript.</p></span><span id="sec0110" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0175">Conflict of Interests</span><p id="par0160" class="elsevierStylePara elsevierViewall">The authors declare no conflict of interest.</p></span></span>" "textoCompletoSecciones" => array:1 [ "secciones" => array:15 [ 0 => array:3 [ "identificador" => "xres1386454" "titulo" => "Graphical abstract" "secciones" => array:1 [ 0 => array:1 [ "identificador" => "abst0005" ] ] ] 1 => array:3 [ "identificador" => "xres1386455" "titulo" => "Abstract" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0010" "titulo" => "Introduction" ] 1 => array:2 [ "identificador" => "abst0015" "titulo" => "Methods" ] 2 => array:2 [ "identificador" => "abst0020" "titulo" => "Results" ] 3 => array:2 [ "identificador" => "abst0025" "titulo" => "Conclusions" ] ] ] 2 => array:2 [ "identificador" => "xpalclavsec1272225" "titulo" => "Keywords" ] 3 => array:3 [ "identificador" => "xres1386453" "titulo" => "Resumen" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0030" "titulo" => "Introducción" ] 1 => array:2 [ "identificador" => "abst0035" "titulo" => "Métodos" ] 2 => array:2 [ "identificador" => "abst0040" "titulo" => "Resultados" ] 3 => array:2 [ "identificador" => "abst0045" "titulo" => "Conclusiones" ] ] ] 4 => array:2 [ "identificador" => "xpalclavsec1272224" "titulo" => "Palabras clave" ] 5 => array:2 [ "identificador" => "sec0005" "titulo" => "Introduction" ] 6 => array:3 [ "identificador" => "sec0010" "titulo" => "Material and Methods" "secciones" => array:7 [ 0 => array:2 [ "identificador" => "sec0015" "titulo" => "Study Population" ] 1 => array:2 [ "identificador" => "sec0020" "titulo" => "Data Collection and Variables Included in the Study" ] 2 => array:2 [ "identificador" => "sec0025" "titulo" => "Missing Data Imputation" ] 3 => array:2 [ "identificador" => "sec0030" "titulo" => "Principal Component Analysis" ] 4 => array:2 [ "identificador" => "sec0035" "titulo" => "Sample Classification Based on Variables, Cut-off Values and Logistic Regression Model" ] 5 => array:2 [ "identificador" => "sec0040" "titulo" => "Neural Network Implementation and Data Re-sampling" ] 6 => array:2 [ "identificador" => "sec0045" "titulo" => "Comparison of Failure" ] ] ] 7 => array:3 [ "identificador" => "sec0050" "titulo" => "Results" "secciones" => array:7 [ 0 => array:2 [ "identificador" => "sec0055" "titulo" => "Cohort and Dataset Description" ] 1 => array:2 [ "identificador" => "sec0060" "titulo" => "Physiological Explanation of Related Variables" ] 2 => array:2 [ "identificador" => "sec0065" "titulo" => "Low Mortality Rate Masks the Real Performance of the Prediction" ] 3 => array:2 [ "identificador" => "sec0070" "titulo" => "Parameter Selection in the Prediction of Patient Death" ] 4 => array:2 [ "identificador" => "sec0075" "titulo" => "Rapid Decisions Based on Parameters’ Cut-off Values" ] 5 => array:2 [ "identificador" => "sec0080" "titulo" => "An Algorithm for Patient Management in Our IRCU" ] 6 => array:2 [ "identificador" => "sec0085" "titulo" => "The New Patient Stratification Criteria Reduces Mortality in Our IRCU" ] ] ] 8 => array:2 [ "identificador" => "sec0090" "titulo" => "Discussion" ] 9 => array:2 [ "identificador" => "sec0095" "titulo" => "Ethics Approval and Consent to Participate" ] 10 => array:2 [ "identificador" => "sec0100" "titulo" => "Funding" ] 11 => array:2 [ "identificador" => "sec0105" "titulo" => "Author Contributions" ] 12 => array:2 [ "identificador" => "sec0110" "titulo" => "Conflict of Interests" ] 13 => array:2 [ "identificador" => "xack481891" "titulo" => "Acknowledgements" ] 14 => array:1 [ "titulo" => "References" ] ] ] "pdfFichero" => "main.pdf" "tienePdf" => true "fechaRecibido" => "2019-07-25" "fechaAceptado" => "2019-11-03" "PalabrasClave" => array:2 [ "en" => array:1 [ 0 => array:4 [ "clase" => "keyword" "titulo" => "Keywords" "identificador" => "xpalclavsec1272225" "palabras" => array:5 [ 0 => "Intermediate Respiratory Care Unit" 1 => "Neural network" 2 => "Mortality prediction model" 3 => "Artificial intelligence" 4 => "Machine learning" ] ] ] "es" => array:1 [ 0 => array:4 [ "clase" => "keyword" "titulo" => "Palabras clave" "identificador" => "xpalclavsec1272224" "palabras" => array:5 [ 0 => "Unidad de cuidados respiratorios intermedios" 1 => "Red neuronal" 2 => "Modelo de predicción de mortalidad" 3 => "Inteligencia artificial" 4 => "Aprendizaje automático" ] ] ] ] "tieneResumen" => true "resumen" => array:2 [ "en" => array:3 [ "titulo" => "Abstract" "resumen" => "<span id="abst0010" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0015">Introduction</span><p id="spar0010" class="elsevierStyleSimplePara elsevierViewall">Mortality risk prediction for Intermediate Respiratory Care Unit's (IRCU) patients can facilitate optimal treatment in high-risk patients. While Intensive Care Units (ICUs) have a long term experience in using algorithms for this purpose, due to the special features of the IRCUs, the same strategics are not applicable. The aim of this study is to develop an IRCU specific mortality predictor tool using machine learning methods.</p></span> <span id="abst0015" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0020">Methods</span><p id="spar0015" class="elsevierStyleSimplePara elsevierViewall">Vital signs of patients were recorded from 1966 patients admitted from 2007 to 2017 in the Jiménez Díaz Foundation University Hospital's IRCU. A neural network was used to select the variables that better predict mortality status. Multivariate logistic regression provided us cut-off points that best discriminated the mortality status for each of the parameters. A new guideline for risk assessment was applied and mortality was recorded during one year.</p></span> <span id="abst0020" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0025">Results</span><p id="spar0020" class="elsevierStyleSimplePara elsevierViewall">Our algorithm shows that thrombocytopenia, metabolic acidosis, anemia, tachypnea, age, sodium levels, hypoxemia, leukocytopenia and hyperkalemia are the most relevant parameters associated with mortality. First year with this decision scene showed a decrease in failure rate of a 50%.</p></span> <span id="abst0025" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0030">Conclusions</span><p id="spar0025" class="elsevierStyleSimplePara elsevierViewall">We have generated a neural network model capable of identifying and classifying mortality predictors in the IRCU of a general hospital. Combined with multivariate regression analysis, it has provided us with an useful tool for the real-time monitoring of patients to detect specific mortality risks. The overall algorithm can be scaled to any type of unit offering personalized results and will increase accuracy over time when more patients are included to the cohorts.</p></span>" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0010" "titulo" => "Introduction" ] 1 => array:2 [ "identificador" => "abst0015" "titulo" => "Methods" ] 2 => array:2 [ "identificador" => "abst0020" "titulo" => "Results" ] 3 => array:2 [ "identificador" => "abst0025" "titulo" => "Conclusions" ] ] ] "es" => array:3 [ "titulo" => "Resumen" "resumen" => "<span id="abst0030" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0040">Introducción</span><p id="spar0030" class="elsevierStyleSimplePara elsevierViewall">La predicción del riesgo de mortalidad de los pacientes en la unidad de cuidados respiratorios intermedios (UCRI) puede facilitar un tratamiento óptimo en pacientes de alto riesgo. Si bien las unidades de cuidados intensivos (UCI) tienen una experiencia a largo plazo en el uso de algoritmos para este propósito, debido a las características especiales de las UCRI, no se pueden aplicar las mismas estrategias. El objetivo de este estudio es desarrollar una herramienta de predicción de mortalidad específica para la UCRI utilizando métodos de aprendizaje automático.</p></span> <span id="abst0035" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0045">Métodos</span><p id="spar0035" class="elsevierStyleSimplePara elsevierViewall">Se registraron los signos vitales de 1.966 pacientes ingresados entre 2007 y 2017 en la UCRI del Hospital Universitario de la Fundación Jiménez Díaz. Se utilizó una red neuronal para seleccionar las variables que mejor predijeran el estado de mortalidad. La regresión logística multivariante nos proporcionó los puntos de corte que discriminaban mejor el estado de la mortalidad para cada uno de los parámetros. Se aplicó una nueva guía para la evaluación de riesgos, y se registró la mortalidad durante un año.</p></span> <span id="abst0040" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0050">Resultados</span><p id="spar0040" class="elsevierStyleSimplePara elsevierViewall">Nuestro algoritmo muestra que la trombocitopenia, la acidosis metabólica, la anemia, la taquipnea, la edad, los niveles de sodio, la hipoxemia, la leucocitopenia y la hipercalemia son los parámetros más relevantes asociados con la mortalidad. En el primer año con este escenario de decisión se mostró una disminución en la tasa de fracaso de un 50%.</p></span> <span id="abst0045" class="elsevierStyleSection elsevierViewall"><span class="elsevierStyleSectionTitle" id="sect0055">Conclusiones</span><p id="spar0045" class="elsevierStyleSimplePara elsevierViewall">Hemos generado un modelo de red neuronal capaz de identificar y clasificar predictores de mortalidad en la UCRI de un hospital general. Combinado con el análisis de regresión multivariante, nos ha proporcionado una herramienta útil para la monitorización en tiempo real de pacientes para detectar riesgos de mortalidad específicos. El algoritmo general se puede modificar a escala para cualquier tipo de unidad, lo que ofrecerá resultados personalizados, y su precisión aumentará con el tiempo, según se incluyan más pacientes en las cohortes.</p></span>" "secciones" => array:4 [ 0 => array:2 [ "identificador" => "abst0030" "titulo" => "Introducción" ] 1 => array:2 [ "identificador" => "abst0035" "titulo" => "Métodos" ] 2 => array:2 [ "identificador" => "abst0040" "titulo" => "Resultados" ] 3 => array:2 [ "identificador" => "abst0045" "titulo" => "Conclusiones" ] ] ] ] "apendice" => array:1 [ 0 => array:1 [ "seccion" => array:1 [ 0 => array:4 [ "apendice" => "<p id="par0175" class="elsevierStylePara elsevierViewall">The following are the supplementary data to this article:<elsevierMultimedia ident="upi0005"></elsevierMultimedia></p>" "etiqueta" => "Appendix A" "titulo" => "Supplementary Data" "identificador" => "sec0120" ] ] ] ] "multimedia" => array:11 [ 0 => array:7 [ "identificador" => "fig0005" "etiqueta" => "Fig. 1" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr1.jpeg" "Alto" => 1328 "Ancho" => 1262 "Tamanyo" => 67191 ] ] "descripcion" => array:1 [ "en" => "<p id="spar0050" class="elsevierStyleSimplePara elsevierViewall">Principal component analysis of the dataset after missing value imputation.</p>" ] ] 1 => array:7 [ "identificador" => "fig0010" "etiqueta" => "Fig. 2" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr2.jpeg" "Alto" => 988 "Ancho" => 1258 "Tamanyo" => 63866 ] ] "descripcion" => array:1 [ "en" => "<p id="spar0055" class="elsevierStyleSimplePara elsevierViewall">Correlation between binary variables affecting an internal physiological relationship. Significant correlations are established when rho<span class="elsevierStyleHsp" style=""></span><<span class="elsevierStyleHsp" style=""></span>0.3 and <span class="elsevierStyleItalic">P</span>-value<span class="elsevierStyleHsp" style=""></span><<span class="elsevierStyleHsp" style=""></span>0.01.</p>" ] ] 2 => array:7 [ "identificador" => "fig0015" "etiqueta" => "Fig. 3" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr3.jpeg" "Alto" => 1119 "Ancho" => 2311 "Tamanyo" => 130615 ] ] "descripcion" => array:1 [ "en" => "<p id="spar0060" class="elsevierStyleSimplePara elsevierViewall">A. Shows the ROC curve and AUC, accuracy, sensitivity and specificity metrics for the NN model with unbalanced classes. B. Shows the importance of the variables in that NN model.</p>" ] ] 3 => array:7 [ "identificador" => "fig0020" "etiqueta" => "Fig. 4" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr4.jpeg" "Alto" => 1175 "Ancho" => 2318 "Tamanyo" => 157902 ] ] "descripcion" => array:1 [ "en" => "<p id="spar0065" class="elsevierStyleSimplePara elsevierViewall">A. shows the ROC curve and AUC, accuracy, sensitivity and specificity metrics for the NN model with balanced classes. B. Shows the importance of the variables in that NN model.</p>" ] ] 4 => array:7 [ "identificador" => "fig0025" "etiqueta" => "Fig. 5" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr5.jpeg" "Alto" => 1191 "Ancho" => 1347 "Tamanyo" => 55931 ] ] "descripcion" => array:1 [ "en" => "<p id="spar0070" class="elsevierStyleSimplePara elsevierViewall">Uni and Multi-variate logistic regression model, ROC curve, AUC, sensitivity and specificity values are shown.</p>" ] ] 5 => array:7 [ "identificador" => "fig0030" "etiqueta" => "Fig. 6" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => true "mostrarDisplay" => false "figura" => array:1 [ 0 => array:4 [ "imagen" => "gr6.jpeg" "Alto" => 1072 "Ancho" => 1525 "Tamanyo" => 120373 ] ] "descripcion" => array:1 [ "en" => "<p id="spar0075" class="elsevierStyleSimplePara elsevierViewall">Failure rate in our IRCU over the years with available records.</p>" ] ] 6 => 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:1 [ "tablatextoimagen" => array:1 [ 0 => array:2 [ "tabla" => array:1 [ 0 => """ <table border="0" frame="\n \t\t\t\t\tvoid\n \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n \t\t\t\t\ttable-head\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Features \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">Threshold \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">Years of study \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 \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 patients \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1966 \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">Mortality rate (%) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.68 \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 (mean) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">75<span class="elsevierStyleHsp" style=""></span>±<span class="elsevierStyleHsp" style=""></span>14 \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">Gender ratio (male %/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">57/63 \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">NIV treatment (%) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">83 \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">HFO treatment (%) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">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">Weaning procedures (%) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 \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">Vasoactive drugs (%) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\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 \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab2379898.png" ] ] ] ] "descripcion" => array:1 [ "en" => "<p id="spar0080" class="elsevierStyleSimplePara elsevierViewall">Global Profile of the Cohort Included in the Study. NIV Means Non Invasive Ventilation; HFO Means High Flow Oxygen Treatment.</p>" ] ] 7 => 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:1 [ "tablatextoimagen" => array:1 [ 0 => array:2 [ "tabla" => array:1 [ 0 => """ <table border="0" frame="\n \t\t\t\t\tvoid\n \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n \t\t\t\t\ttable-head\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Variable \t\t\t\t\t\t\n \t\t\t\t\t\t</th><th class="td" title="\n \t\t\t\t\ttable-head\n \t\t\t\t " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t" scope="col" style="border-bottom: 2px solid black">Mean \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">SD \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">%NA \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">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="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">75.3 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">14.8 \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="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">7.38 \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">SBP \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">127.43 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">20.35 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">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">DBP \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">70.42 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">23.19 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">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">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="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">37.34 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.54 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">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">RR \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">19.41 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">2.38 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">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">LEUCOS \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">12.25 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">9.79 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.15 \t\t\t\t\t\t\n \t\t\t\t</td></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">Hb \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">12.14 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">2.66 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.15 \t\t\t\t\t\t\n \t\t\t\t</td></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">PL \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">258.37 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">130.19 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.20 \t\t\t\t\t\t\n \t\t\t\t</td></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">INR \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.55 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.32 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">40.18 \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">CREA \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.01 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.57 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.15 \t\t\t\t\t\t\n \t\t\t\t</td></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">NA \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">138.35 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">5.43 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.15 \t\t\t\t\t\t\n \t\t\t\t</td></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">K \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">4.34 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.92 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.31 \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">PH \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">7.23 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.47 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.66 \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">PCO2 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">59.34 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">22.00 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.66 \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">PO2 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">58.33 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">33.14 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.66 \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">BE \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">4.38 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">7.10 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.92 \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">SBC \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">28.48 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">6.04 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.92 \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab2379896.png" ] ] ] ] "descripcion" => array:1 [ "en" => "<p id="spar0085" class="elsevierStyleSimplePara elsevierViewall">Description of the Variables and Their Values Introduced in the Analysis. Percentage of NAs (Not Available Value) Indicates the Missing Values of Every Variable.</p>" ] ] 8 => array:8 [ "identificador" => "tbl0015" "etiqueta" => "Table 3" "tipo" => "MULTIMEDIATABLA" "mostrarFloat" => true "mostrarDisplay" => false "detalles" => array:1 [ 0 => array:3 [ "identificador" => "at3" "detalle" => "Table " "rol" => "short" ] ] "tabla" => array:1 [ "tablatextoimagen" => array:1 [ 0 => array:2 [ "tabla" => array:1 [ 0 => """ <table border="0" frame="\n \t\t\t\t\tvoid\n \t\t\t\t" class=""><thead title="thead"><tr title="table-row"><th class="td" title="\n \t\t\t\t\ttable-head\n \t\t\t\t " align="" 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">Coef. \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">OR \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">(IC 95%) \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"><span class="elsevierStyleItalic">P</span> \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">Constant \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">−2.333 \t\t\t\t\t\t\n \t\t\t\t</td><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="" 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="" valign="\n \t\t\t\t\ttop\n \t\t\t\t"> \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">RR<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>24.5 \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="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.704 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">5.498 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">(1.981, 13.44) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">.002 \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">LEUCOS<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>3.23 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">−2.687 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.068 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">(0.024, 0.215) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t"><.001 \t\t\t\t\t\t\n \t\t\t\t</td></tr><tr title="table-row"><td class="td-with-role" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t ; entry_with_role_rowhead " align="left" valign="\n \t\t\t\t\ttop\n \t\t\t\t">Hb<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>10.4 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">−1.171 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.310 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">(0.146, 0.655) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">.002 \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">K<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>3.68 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">1.850 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">6.361 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">(1.307, 115.0) \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="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">.017 \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">PH<span class="elsevierStyleHsp" style=""></span>><span class="elsevierStyleHsp" style=""></span>7.33 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">−0.817 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">0.442 \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">(0.201, 0.933) \t\t\t\t\t\t\n \t\t\t\t</td><td class="td" title="\n \t\t\t\t\ttable-entry\n \t\t\t\t " align="char" valign="\n \t\t\t\t\ttop\n \t\t\t\t">.032 \t\t\t\t\t\t\n \t\t\t\t</td></tr></tbody></table> """ ] "imagenFichero" => array:1 [ 0 => "xTab2379897.png" ] ] ] ] "descripcion" => array:1 [ "en" => "<p id="spar0090" class="elsevierStyleSimplePara elsevierViewall">Multivariate Logistic Regression Model. Hosmer and Lemeshow Test: Chi-square<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>4.008, df<span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>8, <span class="elsevierStyleItalic">P</span><span class="elsevierStyleHsp" style=""></span>=<span class="elsevierStyleHsp" style=""></span>.856.</p>" ] ] 9 => array:5 [ "identificador" => "upi0005" "tipo" => "MULTIMEDIAECOMPONENTE" "mostrarFloat" => false "mostrarDisplay" => true "Ecomponente" => array:2 [ "fichero" => "mmc1.pdf" "ficheroTamanyo" => 307601 ] ] 10 => array:5 [ "identificador" => "fig0035" "tipo" => "MULTIMEDIAFIGURA" "mostrarFloat" => false "mostrarDisplay" => true "figura" => array:1 [ 0 => array:4 [ "imagen" => "fx1.jpeg" "Alto" => 904 "Ancho" => 1333 "Tamanyo" => 84897 ] ] ] ] "bibliografia" => array:2 [ "titulo" => "References" "seccion" => array:1 [ 0 => array:2 [ "identificador" => "bibs0015" "bibliografiaReferencia" => array:40 [ 0 => array:3 [ "identificador" => "bib0205" "etiqueta" => "1" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Trends in inpatient hospital deaths: National Hospital Discharge Survey, 2000–2010" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "M.J. Hall" 1 => "S. Levant" 2 => "C.J. DeFrances" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:5 [ "tituloSerie" => "NCHS Data Brief" "fecha" => "2013" "paginaInicial" => "1" "paginaFinal" => "8" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25030411" "web" => "Medline" ] ] ] ] ] ] ] ] 1 => array:3 [ "identificador" => "bib0210" "etiqueta" => "2" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Outcomes associated with invasive and noninvasive ventilation among patients hospitalized with exacerbations of chronic obstructive pulmonary disease" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:6 [ 0 => "P.K. Lindenauer" 1 => "M.S. Stefan" 2 => "M.-S. Shieh" 3 => "P.S. Pekow" 4 => "M.B. Rothberg" 5 => "N.S. Hill" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1001/jamainternmed.2014.5430" "Revista" => array:5 [ "tituloSerie" => "JAMA Intern Med" "fecha" => "2014" "volumen" => "174" "paginaInicial" => "1982" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25347545" "web" => "Medline" ] ] ] ] ] ] ] ] 2 => array:3 [ "identificador" => "bib0400" "etiqueta" => "3" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Reversal of acute exacerbations of chronic obstructive lung disease by inspiratory assistance with a face mask" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "L. Brochard" 1 => "D. Isabey" 2 => "J. Piquet" 3 => "P. Amaro" 4 => "J. Mancebo" 5 => "A.A. Messadi" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1056/NEJM199011293232204" "Revista" => array:6 [ "tituloSerie" => "N Engl J Med." "fecha" => "1990" "volumen" => "323" "paginaInicial" => "1523" "paginaFinal" => "1530" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/2122253" "web" => "Medline" ] ] ] ] ] ] ] ] 3 => array:3 [ "identificador" => "bib0405" "etiqueta" => "4" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A chart of failure risk for noninvasive ventilation in patients with COPD exacerbation" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "M. Confalonieri" 1 => "G. Garuti" 2 => "M.S. Cattaruzza" 3 => "J.F. Osborn" 4 => "M. Antonelli" 5 => "G. Conti" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1183/09031936.05.00085304" "Revista" => array:5 [ "tituloSerie" => "Eur Respir J." "fecha" => "2005" "volumen" => "25" "paginaInicial" => "348" "paginaFinal" => "355" ] ] ] ] ] ] 4 => array:3 [ "identificador" => "bib0225" "etiqueta" => "5" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Non-invasive mechanical ventilation and mortality in elderly immunocompromised patients hospitalized with pneumonia: a retrospective cohort study" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:5 [ 0 => "C.S. Johnson" 1 => "C.R. Frei" 2 => "M.L. Metersky" 3 => "A.R. Anzueto" 4 => "E.M. Mortensen" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1186/1471-2466-14-7" "Revista" => array:5 [ "tituloSerie" => "BMC Pulm Med" "fecha" => "2014" "volumen" => "14" "paginaInicial" => "7" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/24468062" "web" => "Medline" ] ] ] ] ] ] ] ] 5 => array:3 [ "identificador" => "bib0410" "etiqueta" => "6" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Non-invasive ventilation in community-acquired pneumonia and severe acute respiratory failure" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "A. Carrillo" 1 => "G. Gonzalez-Diaz" 2 => "M. Ferrer" 3 => "M.E. Martinez-Quintana" 4 => "A. Lopez-Martinez" 5 => "N. Llamas" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/s00134-012-2475-6" "Revista" => array:6 [ "tituloSerie" => "Intensive Care Med." "fecha" => "2012" "volumen" => "38" "paginaInicial" => "458" "paginaFinal" => "466" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/22318634" "web" => "Medline" ] ] ] ] ] ] ] ] 6 => array:3 [ "identificador" => "bib0235" "etiqueta" => "7" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Non-invasive mechanical ventilation in the treatment of acute heart failure" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "J.A. Megido" 1 => "Á.G. Franco" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/S0025-7753(14) 70084-3" "Revista" => array:5 [ "tituloSerie" => "Med Clin (Barc)" "fecha" => "2014" "volumen" => "142" "paginaInicial" => "55" "paginaFinal" => "58" ] ] ] ] ] ] 7 => array:3 [ "identificador" => "bib0240" "etiqueta" => "8" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Non-invasive ventilation for acute hypoxemic respiratory failure: intubation rate and risk factors" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:6 [ 0 => "A.W. Thille" 1 => "D. Contou" 2 => "C. Fragnoli" 3 => "A. Córdoba-Izquierdo" 4 => "F. Boissier" 5 => "C. Brun-Buisson" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1186/cc13103" "Revista" => array:5 [ "tituloSerie" => "Crit Care" "fecha" => "2013" "volumen" => "17" "paginaInicial" => "R269" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/24215648" "web" => "Medline" ] ] ] ] ] ] ] ] 8 => array:3 [ "identificador" => "bib0245" "etiqueta" => "9" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Is non-invasive ventilation safe in acute severe asthma?" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "M. Pallin" 1 => "M. Hew" 2 => "M.T. Naughton" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1111/resp.12428" "Revista" => array:6 [ "tituloSerie" => "Respirology" "fecha" => "2015" "volumen" => "20" "paginaInicial" => "251" "paginaFinal" => "257" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25376643" "web" => "Medline" ] ] ] ] ] ] ] ] 9 => array:3 [ "identificador" => "bib0250" "etiqueta" => "10" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Non-invasive ventilation in patients with hematologic malignancy: a new prospective" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "V. Squadrone" 1 => "G. Ferreyra" 2 => "V.M. Ranieri" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:6 [ "tituloSerie" => "Minerva Anestesiol" "fecha" => "2015" "volumen" => "81" "paginaInicial" => "1118" "paginaFinal" => "1126" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25592488" "web" => "Medline" ] ] ] ] ] ] ] ] 10 => array:3 [ "identificador" => "bib0255" "etiqueta" => "11" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Study Group for Respiratory Intensive Care in Malignancies Groupe de Recherche en Réanimation Respiratoire du patient d’Onco-Hématologie Early non-invasive ventilation for acute respiratory failure in immunocompromised patients (IVNIctus): study protocol for a multicenter randomized controlled trial" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "V. Lemiale" 1 => "M. Resche-Rigon" 2 => "E. Azoulay" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1186/1745-6215-15-372" "Revista" => array:5 [ "tituloSerie" => "Trials" "fecha" => "2014" "volumen" => "15" "paginaInicial" => "372" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25257210" "web" => "Medline" ] ] ] ] ] ] ] ] 11 => array:3 [ "identificador" => "bib0260" "etiqueta" => "12" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "The use of non-invasive ventilation in very old patients with hypercapnic acute respiratory failure because of COPD exacerbation" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:6 [ 0 => "A. Nicolini" 1 => "M. Santo" 2 => "L. Ferrera" 3 => "M. Ferrari-Bravo" 4 => "C. Barlascini" 5 => "A. Perazzo" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1111/ijcp.12484" "Revista" => array:6 [ "tituloSerie" => "Int J Clin Pract" "fecha" => "2014" "volumen" => "68" "paginaInicial" => "1523" "paginaFinal" => "1529" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25283150" "web" => "Medline" ] ] ] ] ] ] ] ] 12 => array:3 [ "identificador" => "bib0415" "etiqueta" => "13" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Non-invasive mechanical ventilation in patients with diffuse interstitial lung diseases" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "S. Aliberti" 1 => "G. Messinesi" 2 => "S. Gamberini" 3 => "S. Maggiolini" 4 => "D. Visca" 5 => "V. Galavotti" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1186/1471-2466-14-194" "Revista" => array:5 [ "tituloSerie" => "BMC Pulm Med." "fecha" => "2014" "volumen" => "14" "paginaInicial" => "194" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25476922" "web" => "Medline" ] ] ] ] ] ] ] ] 13 => array:3 [ "identificador" => "bib0270" "etiqueta" => "14" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "APACHE-acute physiology and chronic health evaluation: a physiologically based classification system" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:5 [ 0 => "W.A. Knaus" 1 => "J.E. Zimmerman" 2 => "D.P. Wagner" 3 => "E.A. Draper" 4 => "D.E. Lawrence" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1097/00003246-198108000-00008" "Revista" => array:6 [ "tituloSerie" => "Crit Care Med" "fecha" => "1981" "volumen" => "9" "paginaInicial" => "591" "paginaFinal" => "597" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/7261642" "web" => "Medline" ] ] ] ] ] ] ] ] 14 => array:3 [ "identificador" => "bib0420" "etiqueta" => "15" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "The APACHE III prognostic system" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "W.A. Knaus" 1 => "D.P. Wagner" 2 => "E.A. Draper" 3 => "J.E. Zimmerman" 4 => "M. Bergner" 5 => "P.G. Bastos" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1378/chest.100.6.1619" "Revista" => array:6 [ "tituloSerie" => "Risk prediction of hospital mortality for critically ill hospitalized adults. Chest." "fecha" => "1991" "volumen" => "100" "paginaInicial" => "1619" "paginaFinal" => "1636" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/1959406" "web" => "Medline" ] ] ] ] ] ] ] ] 15 => array:3 [ "identificador" => "bib0425" "etiqueta" => "16" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Use of a severity index in 8 multidisciplinary resuscitation centers" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "J.R. Le Gall" 1 => "P. Loirat" 2 => "F. Nicolas" 3 => "C. Granthil" 4 => "F. Wattel" 5 => "R. Thomas" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:6 [ "tituloSerie" => "Presse Med." "fecha" => "1983" "volumen" => "12" "paginaInicial" => "1757" "paginaFinal" => "1761" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/6224179" "web" => "Medline" ] ] ] ] ] ] ] ] 16 => array:3 [ "identificador" => "bib0285" "etiqueta" => "17" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter study" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "J.R.Le Gall" 1 => "S. Lemeshow" 2 => "F. Saulnier" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1001/jama.270.24.2957" "Revista" => array:6 [ "tituloSerie" => "JAMA" "fecha" => "1993" "volumen" => "270" "paginaInicial" => "2957" "paginaFinal" => "2963" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/8254858" "web" => "Medline" ] ] ] ] ] ] ] ] 17 => array:3 [ "identificador" => "bib0430" "etiqueta" => "18" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure" "autores" => array:1 [ 0 => array:3 [ "colaboracion" => "On behalf of the Working Group on Sepsis-Related Problems of the European Society of Intensive Care Medicine" "etal" => true "autores" => array:6 [ 0 => "J.L. Vincent" 1 => "R. Moreno" 2 => "J. Takala" 3 => "S. Willatts" 4 => "A. De Mendonça" 5 => "H. Bruining" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/bf01709751" "Revista" => array:6 [ "tituloSerie" => "Intensive Care Med." "fecha" => "1996" "volumen" => "22" "paginaInicial" => "707" "paginaFinal" => "710" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/8844239" "web" => "Medline" ] ] ] ] ] ] ] ] 18 => array:3 [ "identificador" => "bib0435" "etiqueta" => "19" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "The Logistic Organ Dysfunction system. A new way to assess organ dysfunction in the intensive care unit" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "J.R. Le Gall" 1 => "J. Klar" 2 => "S. Lemeshow" 3 => "F. Saulnier" 4 => "C. Alberti" 5 => "A. Artigas" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1001/jama.276.10.802" "Revista" => array:6 [ "tituloSerie" => "ICU Scoring Group. JAMA." "fecha" => "1996" "volumen" => "276" "paginaInicial" => "802" "paginaFinal" => "810" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/8769590" "web" => "Medline" ] ] ] ] ] ] ] ] 19 => array:3 [ "identificador" => "bib0300" "etiqueta" => "20" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A new severity of illness scale using a subset of acute physiology and chronic health evaluation data elements shows comparable predictive accuracy" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "A.E.W. Johnson" 1 => "A.A. Kramer" 2 => "G.D. Clifford" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1097/CCM.0b013e31828a24fe" "Revista" => array:5 [ "tituloSerie" => "Crit Care Med" "fecha" => "2013" "volumen" => "41" "paginaInicial" => "1711" "paginaFinal" => "1718" ] ] ] ] ] ] 20 => array:3 [ "identificador" => "bib0305" "etiqueta" => "21" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "APACHE 1978-2001: the development of a quality assurance system based on prognosis: milestones and personal reflections" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:1 [ 0 => "W.A. Knaus" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1001/archsurg.137.1.37" "Revista" => array:6 [ "tituloSerie" => "Arch Surg" "fecha" => "2002" "volumen" => "137" "paginaInicial" => "37" "paginaFinal" => "41" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/11772212" "web" => "Medline" ] ] ] ] ] ] ] ] 21 => array:3 [ "identificador" => "bib0440" "etiqueta" => "22" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A Decision Theoretic Methodology for Seventy Index Development" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "D.H. Gustafson" 1 => "D.G. Fryback" 2 => "J.H. Rose" 3 => "V. Yick" 4 => "C.T. Prokop" 5 => "D.E. Detmer" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1177/0272989X8600600106" "Revista" => array:5 [ "tituloSerie" => "Med Decis Mak." "fecha" => "1986" "volumen" => "6" "paginaInicial" => "27" "paginaFinal" => "35" ] ] ] ] ] ] 22 => array:3 [ "identificador" => "bib0315" "etiqueta" => "23" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Clinical prediction rules" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "J.H. Wasson" 1 => "H.C. Sox" 2 => "R.K. Neff" 3 => "L. Goldman" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1056/NEJM198509263131306" "Revista" => array:6 [ "tituloSerie" => "N Engl J Med" "fecha" => "1985" "volumen" => "313" "paginaInicial" => "793" "paginaFinal" => "799" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/3897864" "web" => "Medline" ] ] ] ] ] ] ] ] 23 => array:3 [ "identificador" => "bib0320" "etiqueta" => "24" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Computing in cardiology 2012. Volume 39: September 9–12, 2012, Kraków, Poland. Computing in Cardiology 2012" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "H. Xia" 1 => "B.J. Daley" 2 => "A. Petrie" 3 => "Z. Xiaopeng" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Libro" => array:5 [ "fecha" => "2012" "paginaInicial" => "261" "paginaFinal" => "264" "editorial" => "IEEE" "editorialLocalizacion" => "Krakow" ] ] ] ] ] ] 24 => array:3 [ "identificador" => "bib0325" "etiqueta" => "25" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Using an Artificial Neural Networks (ANNs) model for prediction of Intensive Care Unit (ICU) outcome and length of stay at hospital in traumatic patients" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:4 [ 0 => "C. Gholipour" 1 => "F. Rahim" 2 => "A. Fakhree" 3 => "B. Ziapour" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.7860/JCDR/2015/9467.5828" "Revista" => array:7 [ "tituloSerie" => "J Clin Diagn Res" "fecha" => "2015" "volumen" => "9" "paginaInicial" => "OC19" "paginaFinal" => "OC23" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/26266149" "web" => "Medline" ] ] "itemHostRev" => array:3 [ "pii" => "S0001731014700146" "estado" => "S300" "issn" => "00017310" ] ] ] ] ] ] ] 25 => array:3 [ "identificador" => "bib0330" "etiqueta" => "26" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Developing and using expert systems and neural networks in medicine: a review on benefits and challenges" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "A. Sheikhtaheri" 1 => "F. Sadoughi" 2 => "Z. Hashemi Dehaghi" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1007/s10916-014-0110-5" "Revista" => array:5 [ "tituloSerie" => "J Med Syst" "fecha" => "2014" "volumen" => "38" "paginaInicial" => "110" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25027017" "web" => "Medline" ] ] ] ] ] ] ] ] 26 => array:3 [ "identificador" => "bib0335" "etiqueta" => "27" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Use of artificial neural networks in applying methodology for allocating health resources" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "M.A. Rosas" 1 => "A.F.B. Bezerra" 2 => "P.J. Duarte-Neto" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/s0140-6736(95)91804-3" "Revista" => array:6 [ "tituloSerie" => "Rev Saude Publica" "fecha" => "2013" "volumen" => "47" "paginaInicial" => "128" "paginaFinal" => "136" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/23703139" "web" => "Medline" ] ] ] ] ] ] ] ] 27 => array:3 [ "identificador" => "bib0340" "etiqueta" => "28" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Comparation of artificial neural network and logistic regression models for predicting clinically relevant outcome" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "S. Lukić" 1 => "Z. Cojbašić" 2 => "Z. Milošević" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.wneu.2012.07.005" "Revista" => array:6 [ "tituloSerie" => "World Neurosurg" "fecha" => "2014" "volumen" => "82" "paginaInicial" => "e377" "paginaFinal" => "e378" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/22796393" "web" => "Medline" ] ] ] ] ] ] ] ] 28 => array:3 [ "identificador" => "bib0345" "etiqueta" => "29" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Lung cancer risk prediction method based on feature selection and artificial neural network" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "N.-N. Xie" 1 => "L. Hu" 2 => "T.-H. Li" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.7314/apjcp.2014.15.23.10539" "Revista" => array:6 [ "tituloSerie" => "Asian Pac J Cancer Prev" "fecha" => "2014" "volumen" => "15" "paginaInicial" => "10539" "paginaFinal" => "10542" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25556505" "web" => "Medline" ] ] ] ] ] ] ] ] 29 => array:3 [ "identificador" => "bib0350" "etiqueta" => "30" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Application of artificial neural network models in occupational safety and health utilizing ordinal variables" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "F.A. Moayed" 1 => "R.L. Shell" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1093/annhyg/meq079" "Revista" => array:6 [ "tituloSerie" => "Ann Occup Hyg" "fecha" => "2011" "volumen" => "55" "paginaInicial" => "132" "paginaFinal" => "142" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/21187370" "web" => "Medline" ] ] ] ] ] ] ] ] 30 => array:3 [ "identificador" => "bib0445" "etiqueta" => "31" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Performance of SAPS II and SAPS 3 in Intermediate Care" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "J.F. Lucena" 1 => "F. Alegre" 2 => "D. Martinez-Urbistondo" 3 => "M.F. Landecho" 4 => "A. Huerta" 5 => "A. García-Mouriz" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1371/journal.pone.0077229" "Revista" => array:5 [ "tituloSerie" => "PLoS One." "fecha" => "2013" "volumen" => "8" "paginaInicial" => "e77229" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/24130860" "web" => "Medline" ] ] ] ] ] ] ] ] 31 => array:3 [ "identificador" => "bib0360" "etiqueta" => "32" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Simplified acute physiology score II for measuring severity of illness in intermediate care units" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:5 [ 0 => "I. Auriant" 1 => "I. Vinatier" 2 => "F. Thaler" 3 => "M. Tourneur" 4 => "P. Loirat" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1097/00003246-199808000-00023" "Revista" => array:6 [ "tituloSerie" => "Crit Care Med" "fecha" => "1998" "volumen" => "26" "paginaInicial" => "1368" "paginaFinal" => "1371" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/9710096" "web" => "Medline" ] ] ] ] ] ] ] ] 32 => array:3 [ "identificador" => "bib0365" "etiqueta" => "33" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Predicting in-hospital mortality of ICU patients: the physionet/computing in cardiology challenge 2012" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:5 [ 0 => "I. Silva" 1 => "G. Moody" 2 => "D.J. Scott" 3 => "L.A. Celi" 4 => "R.G. Mark" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "Revista" => array:6 [ "tituloSerie" => "Comput Cardiol (2010)" "fecha" => "2012" "volumen" => "39" "paginaInicial" => "245" "paginaFinal" => "248" "itemHostRev" => array:3 [ "pii" => "S019096221401576X" "estado" => "S300" "issn" => "01909622" ] ] ] ] ] ] ] 33 => array:3 [ "identificador" => "bib0450" "etiqueta" => "34" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A simplified acute physiology score for ICU patients" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "J.R. Le Gall" 1 => "P. Loirat" 2 => "A. Alperovitch" 3 => "P. Glaser" 4 => "C. Granthil" 5 => "D. Mathieu" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1097/00003246-198411000-00012" "Revista" => array:6 [ "tituloSerie" => "Crit Care Med." "fecha" => "1984" "volumen" => "12" "paginaInicial" => "975" "paginaFinal" => "977" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/6499483" "web" => "Medline" ] ] ] ] ] ] ] ] 34 => array:3 [ "identificador" => "bib0375" "etiqueta" => "35" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "ICU mortality prediction: a classification algorithm for imbalanced datasets" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:3 [ 0 => "S. Bhattacharya" 1 => "V. Rajan" 2 => "H. Shrivastava" ] ] ] ] ] "host" => array:1 [ 0 => array:1 [ "LibroEditado" => array:3 [ "titulo" => "Proc Thirty-First AAAI" "paginaInicial" => "17" "serieFecha" => "2017" ] ] ] ] ] ] 35 => array:3 [ "identificador" => "bib0455" "etiqueta" => "36" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Hospital mortality of adults admitted to Intensive Care Units in hospitals with and without Intermediate Care Units: a multicentre European cohort study" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "M. Capuzzo" 1 => "C. Volta" 2 => "T. Tassinati" 3 => "R. Moreno" 4 => "A. Valentin" 5 => "B. Guidet" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1186/s13054-014-0551-8" "Revista" => array:5 [ "tituloSerie" => "Crit Care." "fecha" => "2014" "volumen" => "18" "paginaInicial" => "551" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/25664865" "web" => "Medline" ] ] ] ] ] ] ] ] 36 => array:3 [ "identificador" => "bib0460" "etiqueta" => "37" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Costs of the COPD" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "G. Bertolini" 1 => "M. Confalonieri" 2 => "C. Rossi" 3 => "G. Rossi" 4 => "B. Simini" 5 => "M. Gorini" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.rmed.2004.11.014" "Revista" => array:6 [ "tituloSerie" => "Differences between intensive care unit and respiratory intermediate care unit. Respir Med." "fecha" => "2005" "volumen" => "99" "paginaInicial" => "894" "paginaFinal" => "900" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/15939252" "web" => "Medline" ] ] ] ] ] ] ] ] 37 => array:3 [ "identificador" => "bib0390" "etiqueta" => "38" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Mortality assessment in intensive care units via adverse events using artificial neural networks" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:5 [ 0 => "A. Silva" 1 => "P. Cortez" 2 => "M.F. Santos" 3 => "L. Gomes" 4 => "J. Neves" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1016/j.artmed.2005.07.006" "Revista" => array:6 [ "tituloSerie" => "Artif Intell Med" "fecha" => "2006" "volumen" => "36" "paginaInicial" => "223" "paginaFinal" => "234" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/16213693" "web" => "Medline" ] ] ] ] ] ] ] ] 38 => array:3 [ "identificador" => "bib0395" "etiqueta" => "39" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "A comparison of ICU mortality prediction using the APACHE II scoring system and artificial neural networks" "autores" => array:1 [ 0 => array:2 [ "etal" => false "autores" => array:2 [ 0 => "L.S. Wong" 1 => "J.D. Young" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1046/j.1365-2044.1999.01104.x" "Revista" => array:6 [ "tituloSerie" => "Anaesthesia" "fecha" => "1999" "volumen" => "54" "paginaInicial" => "1048" "paginaFinal" => "1054" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/10540093" "web" => "Medline" ] ] ] ] ] ] ] ] 39 => array:3 [ "identificador" => "bib0465" "etiqueta" => "40" "referencia" => array:1 [ 0 => array:2 [ "contribucion" => array:1 [ 0 => array:2 [ "titulo" => "Neural Network Prediction of ICU Length of Stay Following Cardiac Surgery Based on Pre-Incision Variables" "autores" => array:1 [ 0 => array:2 [ "etal" => true "autores" => array:6 [ 0 => "R.J. LaFaro" 1 => "S. Pothula" 2 => "K.P. Kubal" 3 => "M.E. Inchiosa" 4 => "V.M. Pothula" 5 => "S.C. Yuan" ] ] ] ] ] "host" => array:1 [ 0 => array:2 [ "doi" => "10.1371/journal.pone.0145395" "Revista" => array:5 [ "tituloSerie" => "PLoS One." "fecha" => "2015" "volumen" => "10" "paginaInicial" => "e0145395" "link" => array:1 [ 0 => array:2 [ "url" => "https://www.ncbi.nlm.nih.gov/pubmed/26710254" "web" => "Medline" ] ] ] ] ] ] ] ] ] ] ] ] "agradecimientos" => array:1 [ 0 => array:4 [ "identificador" => "xack481891" "titulo" => "Acknowledgements" "texto" => "<p id="par0165" class="elsevierStylePara elsevierViewall">The authors thank the subjects who participated in the study, and the Jiménez Díaz Foundation University Hospital CEO and hospital board directors, the FJD-IIS and the Quality & Innovation Department.</p><p id="par0180" class="elsevierStylePara elsevierViewall">Availability of data and material. The datasets analysed during the current study are available from the corresponding author on reasonable request.</p>" "vista" => "all" ] ] ] "idiomaDefecto" => "en" "url" => "/15792129/0000005600000009/v1_202009150705/S1579212920302226/v1_202009150705/en/main.assets" "Apartado" => array:4 [ "identificador" => "9374" "tipo" => "SECCION" "en" => array:2 [ "titulo" => "Original Articles" "idiomaDefecto" => true ] "idiomaDefecto" => "en" ] "PDF" => "https://static.elsevier.es/multimedia/15792129/0000005600000009/v1_202009150705/S1579212920302226/v1_202009150705/en/main.pdf?idApp=UINPBA00003Z&text.app=https://archbronconeumol.org/" "EPUB" => "https://multimedia.elsevier.es/PublicationsMultimediaV1/item/epub/S1579212920302226?idApp=UINPBA00003Z" ]
Year/Month | Html | Total | |
---|---|---|---|
2024 November | 6 | 2 | 8 |
2024 October | 30 | 16 | 46 |
2024 September | 28 | 18 | 46 |
2024 August | 48 | 31 | 79 |
2024 July | 70 | 19 | 89 |
2024 June | 42 | 23 | 65 |
2024 May | 79 | 30 | 109 |
2024 April | 45 | 28 | 73 |
2024 March | 35 | 18 | 53 |
2024 February | 40 | 20 | 60 |
2024 January | 1 | 0 | 1 |
2023 March | 8 | 5 | 13 |
2023 February | 33 | 13 | 46 |
2023 January | 27 | 27 | 54 |
2022 December | 36 | 29 | 65 |
2022 November | 46 | 16 | 62 |
2022 October | 47 | 27 | 74 |
2022 September | 21 | 17 | 38 |
2022 August | 30 | 32 | 62 |
2022 July | 24 | 30 | 54 |
2022 June | 25 | 29 | 54 |
2022 May | 30 | 26 | 56 |
2022 April | 25 | 17 | 42 |
2022 March | 27 | 38 | 65 |
2022 February | 23 | 17 | 40 |
2020 October | 1 | 0 | 1 |
2020 September | 1 | 0 | 1 |