Machine learning for prediction of 30-day mortality after ST elevation myocardial infraction: An Acute Coronary Syndrome Israeli Survey data mining study
Machine learning for prediction of 30-day mortality after ST elevation myocardial infraction: An Acute Coronary Syndrome Israeli Survey data mining study
复制标题
DOI：
10.1016/j.ijcard.2017.05.067
复制
发表时间：
2017-11-01
影响因子：
3.5
通讯作者：
Beigel, Roy
中科院分区：
文献类型：
--
作者：
Shouval, Roni;Hadanny, Amir;Beigel, Roy
背景资料：使用传统统计方法开发了ST段抬高型心肌梗死（STEMI）后30天死亡率预测的风险评分：Objective：评估一系列机器学习（ML）算法预测STEMI患者30天死亡率，并将其与传统验证的风险评分进行比较。方法：这是一项回顾性、监督学习、数据挖掘研究。在以色列急性冠脉综合征调查（ACSIS）登记的13，422例患者中，2782例患者符合纳入标准，考虑了54个变量。使用6ML算法建立STEMI后30天总死亡率的预测模型。Modelswere compared to each other and to the Global Registry of Acute Coronary Events（GRACE）and Thrombolysis In Myocardial Infarction（TIMI）scores.Results：Depending on the algorithm，using all available variables，prediction models' performance measured in a area under the receiver operating characteristic curve（AUC）ranged from 0.64 to 0.91.最佳模型的表现与全球急性冠脉事件登记处（GRACE）评分相似（0.87 SD 0.06），优于心肌梗死溶栓（TIMI）评分（0.82 SD 0.06，p < 0.05）。当引入15个变量时，大多数算法的性能趋于稳定。其中最重要的预测因素是肌酐，Killip类入院，血压，血糖水平，和again.Conclusions：我们提出了一个数据挖掘方法预测ST段抬高心肌梗死后的死亡率。所选算法在越来越多的变量中显示出预测能力。ML可用于复杂心脏病环境中的结局预测。(C)2017爱思唯尔B.V.保留所有权利。
Background: Risk scores for prediction of mortality 30-days following a ST-segment elevation myocardial infarction (STEMI) have been developed using a conventional statistical approach.Objective: To evaluate an array of machine learning (ML) algorithms for prediction of mortality at 30-days in STEMI patients and to compare these to the conventional validated risk scores.Methods: This was a retrospective, supervised learning, datamining study. Out of a cohort of 13,422 patients from the Acute Coronary Syndrome Israeli Survey (ACSIS) registry, 2782 patients fulfilled inclusion criteria and 54 variables were considered. Prediction models for overall mortality 30 days after STEMIwere developed using 6ML algorithms. Modelswere compared to each other and to the Global Registry of Acute Coronary Events (GRACE) and Thrombolysis InMyocardial Infarction (TIMI) scores.Results: Depending on the algorithm, using all available variables, prediction models' performance measured in an area under the receiver operating characteristic curve (AUC) ranged from 0.64 to 0.91. The best models performed similarly to theGlobal Registry of Acute Coronary Events (GRACE) score (0.87 SD 0.06) and outperformed the Thrombolysis InMyocardial Infarction (TIMI) score (0.82 SD 0.06, p < 0.05). Performance ofmost algorithms plateaued when introduced with 15 variables. Among the top predictors were creatinine, Killip class on admission, blood pressure, glucose level, and age.Conclusions: We present a data mining approach for prediction of mortality post-ST-segment elevation myocardial infarction. The algorithms selected showed competence in prediction across an increasing number of variables. ML may be used for outcome prediction in complex cardiology settings. (C) 2017 Elsevier B.V. All rights reserved.