Predicting Mortality and Hospitalization in Heart Failure With Preserved Ejection Fraction by Using Machine Learning
Chieh-Yu Chang, Chun‐Chi Chen, Ming‐Lung Tsai, Ming‐Jer Hsieh, Tien‐Hsing Chen, Shao-Wei Chen, Shang‐Hung Chang, Pao‐Hsien Chu, I-Chang Hsieh, Ming‐Shien Wen, Dong‐Yi Chen
Abstract
Background: Few studies have incorporated echocardiography and laboratory data to predict clinical outcomes in heart failure with preserved ejection fraction (HFpEF). Objectives: This study aimed to use machine learning to find predictors of heart failure (HF) hospitalization and cardiovascular (CV) death in HFpEF. Methods: From the Chang Gung Research Database in Taiwan, 6,092 HFpEF patients (2,898 derivation, 3,194 validation) identified between 2008 and 2017 were followed until 2019. A random survival forest model, using 58 variables, was developed to predict the composite outcome of HF hospitalization and CV death. Results: ) level of <6% or ≥8%. The random survival forest model demonstrated robust external generalizability with an 86.9% area under curve in validation. Conclusions: Machine learning identified 15 predictors of HF hospitalization and CV death in HFpEF patients, helping doctors identify high-risk individuals for tailored treatment.