<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>1405-9940</journal-id>
<journal-title><![CDATA[Archivos de cardiología de México]]></journal-title>
<abbrev-journal-title><![CDATA[Arch. Cardiol. Méx.]]></abbrev-journal-title>
<issn>1405-9940</issn>
<publisher>
<publisher-name><![CDATA[Instituto Nacional de Cardiología Ignacio Chávez]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S1405-99402021000100058</article-id>
<article-id pub-id-type="doi">10.24875/acm.20000011</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Treatment of individual predictors with neural network algorithms improves Global Registry of Acute Coronary Events score discrimination]]></article-title>
<article-title xml:lang="es"><![CDATA[El tratamiento con redes neuronales de las variables del Global Registry of Acute Coronary mejora la discriminación del score]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Borracci]]></surname>
<given-names><![CDATA[Raul A.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Higa]]></surname>
<given-names><![CDATA[Claudio C.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Ciambrone]]></surname>
<given-names><![CDATA[Graciana]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Gambarte]]></surname>
<given-names><![CDATA[Jimena]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Austral University School of Medicine ]]></institution>
<addr-line><![CDATA[Buenos Aires ]]></addr-line>
<country>Argentina</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Hospital Alemán Department of Cardiology ]]></institution>
<addr-line><![CDATA[Buenos Aires ]]></addr-line>
<country>Argentina</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>03</month>
<year>2021</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>03</month>
<year>2021</year>
</pub-date>
<volume>91</volume>
<numero>1</numero>
<fpage>58</fpage>
<lpage>65</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_arttext&amp;pid=S1405-99402021000100058&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_abstract&amp;pid=S1405-99402021000100058&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_pdf&amp;pid=S1405-99402021000100058&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract  Objective: The aim of this study was to develop, train, and test different neural network (NN) algorithm-based models to improve the Global Registry of Acute Coronary Events (GRACE) score performance to predict in-hospital mortality after an acute coronary syndrome.  Methods: We analyzed a prospective database, including 40 admission variables of 1255 patients admitted with the acute coronary syndrome in a community hospital. Individual predictors included in GRACE score were used to train and test three NN algorithm-based models (guided models), namely: one- and two-hidden layer multilayer perceptron and a radial basis function network. Three extra NNs were built using the 40 admission variables of the entire database (unguided models). Expected mortality according to GRACE score was calculated using the logistic regression equation.  Results: In terms of receiver operating characteristic area and negative predictive value (NPV), almost all NN algorithms outperformed logistic regression. Only radial basis function models obtained a better accuracy level based on NPV improvement, at the expense of positive predictive value (PPV) reduction. The independent normalized importance of variables for the best unguided NN was: creatinine 100%, Killip class 61%, ejection fraction 52%, age 44%, maximum creatine-kinase level 41%, glycemia 40%, left bundle branch block 35%, and weight 33%, among the top 8 predictors.  Conclusions: Treatment of individual predictors of GRACE score with NN algorithms improved accuracy and discrimination power in all models with respect to the traditional logistic regression approach; nevertheless, PPV was only marginally enhanced. Unguided variable selection would be able to achieve better results in PPV terms.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[Resumen  Objetivo: El objetivo fue desarrollar, entrenar y probar diferentes modelos basados en algoritmos de redes neuronales (RN) para mejorar el rendimiento del score del Registro Global de Eventos Coronarios Agudos (GRACE) para predecir la mortalidad hospitalaria después de un síndrome coronario agudo.  Métodos: Analizamos una base de datos prospectiva que incluía 40 variables de ingreso de 1255 pacientes con síndrome coronario agudo en un hospital comunitario. Las variables incluidas en la puntuación GRACE se usaron para entrenar y probar tres algoritmos basados en RN (modelos guiados), a saber: perceptrones multicapa de una y dos capas ocultas y una red de función de base radial. Se construyeron tres RN adicionales utilizando las 40 variables de admisión de toda la base de datos (modelos no guiados). La mortalidad esperada según el GRACE se calculó usando la ecuación de regresión logística.  Resultados: En términos del área ROC y valor predictivo negativo (VPN), casi todos los algoritmos RN superaron la regresión logística. Solo los modelos de función de base radial obtuvieron un mejor nivel de precisión basado en la mejora del VPN, pero a expensas de la reducción del valor predictivo positivo (VPP). La importancia normalizada de las variables incluidas en la mejor RN no guiada fue: creatinina 100%, clase Killip 61%, fracción de eyección 52%, edad 44%, nivel máximo de creatina quinasa 41%, glucemia 40%, bloqueo de rama izquierda 35%, y peso 33%, entre los 8 predictores principales.  Conclusiones: El tratamiento de las variables del score GRACE mediante algoritmos de RN mejoró la precisión y la discriminación en todos los modelos con respecto al enfoque tradicional de regresión logística; sin embargo, el VPP solo mejoró marginalmente. La selección no guiada de variables podría mejorar los resultados en términos de PPV.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[Acute coronary syndrome]]></kwd>
<kwd lng="en"><![CDATA[Risk stratification]]></kwd>
<kwd lng="en"><![CDATA[Predictors]]></kwd>
<kwd lng="en"><![CDATA[Artificial neural networks]]></kwd>
<kwd lng="es"><![CDATA[Síndrome coronario agudo]]></kwd>
<kwd lng="es"><![CDATA[Estratificación del riesgo]]></kwd>
<kwd lng="es"><![CDATA[Predictores]]></kwd>
<kwd lng="es"><![CDATA[Redes neuronales artificiales]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<label>1</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Granger]]></surname>
<given-names><![CDATA[CB]]></given-names>
</name>
<name>
<surname><![CDATA[Goldberg]]></surname>
<given-names><![CDATA[RJ]]></given-names>
</name>
<name>
<surname><![CDATA[Dabbous]]></surname>
<given-names><![CDATA[O]]></given-names>
</name>
<name>
<surname><![CDATA[Pieper]]></surname>
<given-names><![CDATA[KS]]></given-names>
</name>
<name>
<surname><![CDATA[Eagle]]></surname>
<given-names><![CDATA[KA]]></given-names>
</name>
<name>
<surname><![CDATA[Cannon]]></surname>
<given-names><![CDATA[CP]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Global registry of acute coronary events investigators. Predictors of hospital mortality in the global registry of acute coronary events]]></article-title>
<source><![CDATA[Arch Intern Med]]></source>
<year>2003</year>
<volume>163</volume>
<page-range>2345-53</page-range></nlm-citation>
</ref>
<ref id="B2">
<label>2</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Poldervaart]]></surname>
<given-names><![CDATA[JM]]></given-names>
</name>
<name>
<surname><![CDATA[Langedijk]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Backus]]></surname>
<given-names><![CDATA[BE]]></given-names>
</name>
<name>
<surname><![CDATA[Dekker]]></surname>
<given-names><![CDATA[IM]]></given-names>
</name>
<name>
<surname><![CDATA[Six]]></surname>
<given-names><![CDATA[AJ]]></given-names>
</name>
<name>
<surname><![CDATA[Doevendans]]></surname>
<given-names><![CDATA[PA]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Comparison of the GRACE, HEART and TIMI score to predict major adverse cardiac events in chest pain patients at the emergency department]]></article-title>
<source><![CDATA[Int J Cardiol]]></source>
<year>2017</year>
<volume>227</volume>
<page-range>656-61</page-range></nlm-citation>
</ref>
<ref id="B3">
<label>3</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Jakimov]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Mrdovi&#263;]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
<name>
<surname><![CDATA[Filipovi&#263;]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Zdravkovi&#263;]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Djokovi&#263;]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Hini&#263;]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Comparison of RISK-PCI, GRACE, TIMI risk scores for prediction of major adverse cardiac events in patients with acute coronary syndrome]]></article-title>
<source><![CDATA[Croat Med J]]></source>
<year>2017</year>
<volume>58</volume>
<page-range>406-15</page-range></nlm-citation>
</ref>
<ref id="B4">
<label>4</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhu]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Xue]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Zhou]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Tian]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Risk stratification and prognostic value of GRACE and TIMI risk scores for female patients with non-ST segment elevation acute coronary syndrome]]></article-title>
<source><![CDATA[Minerva Cardioangiol]]></source>
<year>2015</year>
<volume>63</volume>
<page-range>171-8</page-range></nlm-citation>
</ref>
<ref id="B5">
<label>5</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[D'Ascenzo]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Biondi-Zoccai]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Moretti]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Bollati]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Omedè]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Sciuto]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[TIMI, GRACE and alternative risk scores in acute coronary syndromes:a meta-analysis of 40 derivation studies on 216,552 patients and of 42 validation studies on 31,625 patients]]></article-title>
<source><![CDATA[Contemp Clin Trials]]></source>
<year>2012</year>
<volume>33</volume>
<page-range>507-14</page-range></nlm-citation>
</ref>
<ref id="B6">
<label>6</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Freeman]]></surname>
<given-names><![CDATA[RV]]></given-names>
</name>
<name>
<surname><![CDATA[Eagle]]></surname>
<given-names><![CDATA[KA]]></given-names>
</name>
<name>
<surname><![CDATA[Bates]]></surname>
<given-names><![CDATA[ER]]></given-names>
</name>
<name>
<surname><![CDATA[Werns]]></surname>
<given-names><![CDATA[SW]]></given-names>
</name>
<name>
<surname><![CDATA[Kline-Rogers]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Karavite]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Comparison of artificial neural networks with logistic regression in prediction of in-hospital death after percutaneous transluminal coronary angioplasty]]></article-title>
<source><![CDATA[Am Heart J]]></source>
<year>2000</year>
<volume>140</volume>
<page-range>511-20</page-range></nlm-citation>
</ref>
<ref id="B7">
<label>7</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mansoor]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Elgendy]]></surname>
<given-names><![CDATA[IY]]></given-names>
</name>
<name>
<surname><![CDATA[Segal]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Bavry]]></surname>
<given-names><![CDATA[AA]]></given-names>
</name>
<name>
<surname><![CDATA[Bian]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Risk prediction model for in-hospital mortality in women with ST-elevation myocardial infarction:a machine learning approach]]></article-title>
<source><![CDATA[Heart Lung]]></source>
<year>2017</year>
<volume>46</volume>
<page-range>405-11</page-range></nlm-citation>
</ref>
<ref id="B8">
<label>8</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ennis]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Hinton]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Naylor]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Revow]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Tibshirani]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A comparison of statistical learning methods on the GUSTO database]]></article-title>
<source><![CDATA[Stat Med]]></source>
<year>1998</year>
<volume>17</volume>
<page-range>2501-8</page-range></nlm-citation>
</ref>
<ref id="B9">
<label>9</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bigi]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Gregori]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Cortigiani]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Desideri]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Chiarotto]]></surname>
<given-names><![CDATA[FA]]></given-names>
</name>
<name>
<surname><![CDATA[Toffolo]]></surname>
<given-names><![CDATA[GM]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Artificial neural networks and robust Bayesian classifiers for risk stratification following uncomplicated myocardial infarction]]></article-title>
<source><![CDATA[Int J Cardiol]]></source>
<year>2005</year>
<volume>101</volume>
<page-range>481-7</page-range></nlm-citation>
</ref>
<ref id="B10">
<label>10</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Myers]]></surname>
<given-names><![CDATA[PD]]></given-names>
</name>
<name>
<surname><![CDATA[Scirica]]></surname>
<given-names><![CDATA[BM]]></given-names>
</name>
<name>
<surname><![CDATA[Stultz]]></surname>
<given-names><![CDATA[CM]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Machine learning improves risk stratification after acute coronary syndrome]]></article-title>
<source><![CDATA[Sci Rep]]></source>
<year>2017</year>
<volume>7</volume>
</nlm-citation>
</ref>
<ref id="B11">
<label>11</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Isma'eel]]></surname>
<given-names><![CDATA[HA]]></given-names>
</name>
<name>
<surname><![CDATA[Cremer]]></surname>
<given-names><![CDATA[PC]]></given-names>
</name>
<name>
<surname><![CDATA[Khalaf]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Almedawar]]></surname>
<given-names><![CDATA[MM]]></given-names>
</name>
<name>
<surname><![CDATA[Elhajj]]></surname>
<given-names><![CDATA[IH]]></given-names>
</name>
<name>
<surname><![CDATA[Sakr]]></surname>
<given-names><![CDATA[GE]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Artificial neural network modeling enhances risk stratification and can reduce downstream testing for patients with suspected acute coronary syndromes, negative cardiac biomarkers, and normal ECGs]]></article-title>
<source><![CDATA[Int J Cardiovasc Imaging]]></source>
<year>2016</year>
<volume>32</volume>
<page-range>687-96</page-range></nlm-citation>
</ref>
<ref id="B12">
<label>12</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mirian]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
<name>
<surname><![CDATA[Sedehi]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Kheiri]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Ahmadi]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A hybrid ANN-GA model to prediction of bivariate binary responses:application to joint prediction of occurrence of heart block and death in patients with myocardial infarction]]></article-title>
<source><![CDATA[J Res Health Sci]]></source>
<year>2016</year>
<volume>16</volume>
<page-range>190-4</page-range></nlm-citation>
</ref>
<ref id="B13">
<label>13</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Scirica]]></surname>
<given-names><![CDATA[BM]]></given-names>
</name>
<name>
<surname><![CDATA[Stultz]]></surname>
<given-names><![CDATA[CM]]></given-names>
</name>
<name>
<surname><![CDATA[Guttag]]></surname>
<given-names><![CDATA[JV]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Beatquency domain and machine learning improve prediction of cardiovascular death after acute coronary syndrome]]></article-title>
<source><![CDATA[Sci Rep]]></source>
<year>2016</year>
<volume>6</volume>
</nlm-citation>
</ref>
<ref id="B14">
<label>14</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wallert]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Tomasoni]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Madison]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Held]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Predicting two-year survival versus non-survival after first myocardial infarction using machine learning and Swedish national register data]]></article-title>
<source><![CDATA[BMC Med Inform Decis Mak]]></source>
<year>2017</year>
<volume>17</volume>
<page-range>99</page-range></nlm-citation>
</ref>
<ref id="B15">
<label>15</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tapak]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Hamidi]]></surname>
<given-names><![CDATA[O]]></given-names>
</name>
<name>
<surname><![CDATA[Amini]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Poorolajal]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Prediction of kidney graft rejection using artificial neural network]]></article-title>
<source><![CDATA[Healthc Inform Res]]></source>
<year>2017</year>
<volume>23</volume>
<page-range>277-84</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
