High-dimensional machine learning models for prediction of heart failure in more than 400 000 men and women from the UK Biobank.

ABSTRACT:

Aims

We aimed to compare performances of conventional survival models with machine learning (ML) survival models for incident heart failure (HF) in men and women without prevalent HF, cardiomyopathy (CM) or ischaemic heart disease (IHD), and to identify potential high-risk precursors overlooked by conventional survival models.

Methods and results

We predicted 10-year risk of incident HF in 266 306 women (2894 events) and 212 061 men (4213 events). We constructed multivariable Cox models, first using ∼ 400 baseline characteristics, and subsequently only those remaining after LASSO stability selection. We also used Random Survival Forest (RSF) and eXtreme Gradient Survival Boosting (XGBoost). Performances were assessed using internal cross validation and hold-out sets, with C-

SUBMITTER: Kok TF 

PROVIDER: S-EPMC12629653 | biostudies-literature | 2025 Nov

REPOSITORIES: biostudies-literature