Evaluation of a machine learning-based metabolic marker for coronary artery disease in the UK Biobank.

ABSTRACT:

Background and aims

An in silico quantitative score of coronary artery disease (ISCAD), built using machine learning and clinical data from electronic health records, has been shown to result in gradations of risk of subclinical atherosclerosis, coronary artery disease (CAD) sequelae, and mortality. Large-scale metabolite biomarker profiling provides increased portability and objectivity in machine learning for disease prediction and gradation. However, these models have not been fully leveraged. We evaluated a quantitative score of CAD derived from probabilities of a machine learning model trained on metabolomic data.

Methods

We developed a CAD-predictive learning model using metabolic data from 93,642 individuals from the UK Biobank (median [IQR] age, 57 [14] years; 39,796

SUBMITTER: Gibson K 

PROVIDER: S-EPMC11798691 | biostudies-literature | 2025 Feb

REPOSITORIES: biostudies-literature