April 13, 2021Open Access

Development and Validation of Machine Learning–Based Race-Specific Models to Predict 10-Year Risk of Heart Failure: A Multicohort Analysis

MSMatthew W. SegarElectrophysiology BJByron C. JaegerPreventive Cardiology KPKershaw V. PatelPreventive Cardiology

Structured PICO

Do machine learning-based race-specific models improve the prediction of 10-year heart failure risk compared to traditional and non-race-specific models?

Population

Individuals in a multicohort analysis for predicting 10-year risk of heart failure

Intervention

Machine learning-based race-specific models integrating clinical, laboratory, and biomarker data

Comparator

Traditional heart failure risk models and non-race-specific machine learning models

Outcome

Model performance for predicting 10-year risk of heart failure

Race-specific machine learning models integrating clinical and biomarker data provide superior 10-year heart failure risk prediction compared to traditional models.

Abstract

Race-specific and ML-based HF risk models that integrate clinical, laboratory, and biomarker data demonstrated superior performance compared with traditional HF risk and non-race-specific ML models. This approach identifies distinct race-specific contributors of HF.

Ask AI

Helpful

Bookmark

View Full Paper