Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death
Feature selection and transformation by machine learning reduce variable numbers and improve prediction for heart failure readmission or death
复制标题
DOI：
10.1371/journal.pone.0218760
复制
发表时间：
2019-06-26
期刊：
影响因子：
3.7
通讯作者：
Dwivedi, Girish
中科院分区：
文献类型：
--
作者：
Awan, Saqib E.;Bennamoun, Mohammed;Dwivedi, Girish
心力衰竭（HF）出院后再入院或死亡的预测仍然是一个重大挑战。现代医疗系统、电子健康记录和机器学习（ML）技术使我们能够挖掘数据，以选择最重要的变量（允许减少变量数量），而不会影响用于预测再入院和死亡的模型的性能。此外，ML方法的基础上变换的变量可能会进一步提高performance. Objectives使用ML技术，以确定最相关的，也转换变量为预测30天的再入院或死亡在HF patients.MethodsWe确定了所有西澳大利亚州的患者年龄在65岁及以上承认HF之间的2003-2008年在关联的行政数据。我们使用标准统计学和基于ML的选择技术评估了与HF再入院或死亡相关的变量。我们还测试了由原始变量转换产生的新变量。我们开发了多层感知器预测模型，并比较其预测性能指标，如面积下的接收器工作特征曲线（AUC），灵敏度和specificity. Resultsafter出院，30天再入院或死亡的比例为23.7%，在我们的队列10,757 HF患者。我们使用较小的变量集（n = 8）开发的预测模型具有与传统模型（n = 47，AUC 0.62）相当的性能（AUC 0.62）。对原有的47个变量进行了进一步改进（p
BackgroundThe prediction of readmission or death after a hospital discharge for heart failure (HF) remains a major challenge. Modern healthcare systems, electronic health records, and machine learning (ML) techniques allow us to mine data to select the most significant variables (allowing for reduction in the number of variables) without compromising the performance of models used for prediction of readmission and death. Moreover, ML methods based on transformation of variables may potentially further improve the performance.ObjectiveTo use ML techniques to determine the most relevant and also transform variables for the prediction of 30-day readmission or death in HF patients.MethodsWe identified all Western Australian patients aged 65 years and above admitted for HF between 2003-2008 in linked administrative data. We evaluated variables associated with HF readmission or death using standard statistical and ML based selection techniques. We also tested the new variables produced by transformation of the original variables. We developed multi-layer perceptron prediction models and compared their predictive performance using metrics such as Area Under the receiver operating characteristic Curve (AUC), sensitivity and specificity.ResultsFollowing hospital discharge, the proportion of 30-day readmissions or death was 23.7% in our cohort of 10,757 HF patients. The prediction model developed by us using a smaller set of variables (n = 8) had comparable performance (AUC 0.62) to the traditional model (n = 47, AUC 0.62). Transformation of the original 47 variables further improved (p