Risk Prediction in Patients With Heart Failure With Preserved Ejection Fraction Using Gene Expression Data and Machine Learning

Frontiers in Genetics

Hongmei Yao¹  Zhi Li²  Yuehua Cui³  Bijue Wang⁴  Zhifei Guo⁴  Liye Zhou⁴  Haitao Yang⁵  Yongqing Wu⁶  Ruiling Fang⁶  Hongyan Cao⁷ 

[1] Department of Cardiology, First Hospital of Shanxi Medical University, Taiyuan, China;Department of Hematology, Taiyuan Central Hospital of Shanxi Medical University, Taiyuan, China;Department of Statistics and Probability, Michigan State University, East Lansing, MI, United States;Division of Health Management, School of Management, Shanxi Medical University, Taiyuan, China;Division of Health Statistics, School of Public Health, Hebei Medical University, Shijiazhuang, China;Division of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, China;Key Laboratory of Major Disease Risk Assessment, Shanxi Medical University, Taiyuan, China;

关键词: risk prediction;    kernel partial least squares;    genetic algorithm;    heart failure with preserved ejection fraction;    machine learning;   

DOI  :  10.3389/fgene.2021.652315

来源: DOAJ

【 摘 要 】

Heart failure with preserved ejection fraction (HFpEF) has become a major health issue because of its high mortality, high heterogeneity, and poor prognosis. Using genomic data to classify patients into different risk groups is a promising method to facilitate the identification of high-risk groups for further precision treatment. Here, we applied six machine learning models, namely kernel partial least squares with the genetic algorithm (GA-KPLS), the least absolute shrinkage and selection operator (LASSO), random forest, ridge regression, support vector machine, and the conventional logistic regression model, to predict HFpEF risk and to identify subgroups at high risk of death based on gene expression data. The model performance was evaluated using various criteria. Our analysis was focused on 149 HFpEF patients from the Framingham Heart Study cohort who were classified into good-outcome and poor-outcome groups based on their 3-year survival outcome. The results showed that the GA-KPLS model exhibited the best performance in predicting patient risk. We further identified 116 differentially expressed genes (DEGs) between the two groups, thus providing novel therapeutic targets for HFpEF. Additionally, the DEGs were enriched in Gene Ontology terms and Kyoto Encyclopedia of Genes and Genomes pathways related to HFpEF. The GA-KPLS-based HFpEF model is a powerful method for risk stratification of 3-year mortality in HFpEF patients.

【 授权许可】

Unknown