AI & Healthcare News ・ 💚 Chronic disease self-management

AI-driven multi-horizon risk stratification for heart failure hospitalization in UA with HFpEF: a Chinese multi-center cohort study

Nature · 11/05 18:13 UTC

The multicenter retrospective cohort enrolled 4367 patients with unstable angina (UA) and heart failure with preserved ejection fraction (HFpEF). An ensemble feature selection pipeline combining LASSO, SVM-RFE and Boruta identified predictors, and twelve machine learning algorithms were then trained to estimate risk. The study addresses the high risk of recurrent heart failure hospitalization in these patients, for which AI tools for multi-horizon risk assessment remain limited.

Read the original (Nature)

See it in the digest → ・ See this issue →