Can machine learning improve patient selection for cardiac resynchronization therapy?
Can machine learning improve patient selection for cardiac resynchronization therapy?
复制标题
DOI：
10.1371/journal.pone.0222397
复制
发表时间：
2019-10-03
期刊：
影响因子：
3.7
通讯作者：
Lindvall, Charlotta
中科院分区：
文献类型：
--
作者：
Hu, Szu-Yeu;Santus, Enrico;Lindvall, Charlotta
多个临床试验支持心脏再同步治疗(CRT)的有效性；然而，由于符合临床实践指南的患者之间的治疗差异很大，最佳患者选择仍然具有挑战性。目的应用机器学习来创建一种算法，该算法使用手术前可用的电子健康记录(EHR)数据来预测CRT的结果。方法和结果我们应用机器学习和自然语言处理对2004-2015年间在两家学术医院接受CRT的990名患者的EHR进行了研究。主要结果是CRT收益减少，定义为
RationaleMultiple clinical trials support the effectiveness of cardiac resynchronization therapy (CRT); however, optimal patient selection remains challenging due to substantial treatment heterogeneity among patients who meet the clinical practice guidelines.ObjectiveTo apply machine learning to create an algorithm that predicts CRT outcome using electronic health record (EHR) data avaible before the procedure.Methods and resultsWe applied machine learning and natural language processing to the EHR of 990 patients who received CRT at two academic hospitals between 2004-2015. The primary outcome was reduced CRT benefit, defined as