Frontiers in Digital Health (Nov 2024)

A novel, machine-learning model for prediction of short-term ASCVD risk over 90 and 365 days

  • Tomer Gazit,
  • Hanan Mann,
  • Shiri Gaber,
  • Pavel Adamenko,
  • Granit Pariente,
  • Liron Volsky,
  • Amir Dolev,
  • Helena Lyson,
  • Eyal Zimlichman,
  • Jay A. Pandit,
  • Edo Paz

DOI
https://doi.org/10.3389/fdgth.2024.1485508
Journal volume & issue
Vol. 6

Abstract

Read online

BackgroundCurrent atherosclerotic cardiovascular disease (ASCVD) risk assessment tools like the Pooled Cohort Equations (PCEs) and PREVENT™ scores offer long-term predictions but may not effectively drive behavior change. Short-term risk predictions using mobile health (mHealth) data and electronic health records (EHRs) could enhance clinical decision-making and patient engagement. The aim of this study was to develop a short-term ASCVD risk prediction model for hypertensive individuals using mHealth and EHR data and compare its performance to existing risk assessment tools.MethodsThis is a retrospective cohort study including 51,127 hypertensive participants aged ≥18 years old who enrolled in the Hello Heart CV risk self-management program between January 2015 and January 2024. A machine learning (ML) model was derived from EHR data and mHealth measurements of blood pressure (BP) and heart rate (HR) collected via at-home BP monitors. Its performance was compared to that of PCE and PREVENT.ResultsThe XgBoost model incorporating 291 features outperformed the PCE and PREVENT scores in discriminating ASCVD risk for both prediction periods. For 90-day prediction, mean C-statistics were 0.81 (XgBoost) vs. 0.74 (PCE) and 0.65 (PREVENT). Similar findings were observed for 365-day prediction. mHealth measurements incrementally enhanced 365-day risk prediction (ROC-AUC 0.82 vs. 0.80 without mHealth).ConclusionAn EHR and mHealth-based ML model offers superior short-term ASCVD prediction compared to traditional tools. This approach supports personalized preventive strategies, particularly for populations with incomplete features for PCE or PREVENT. Further research should explore this novel risk prediction framework, and particularly additional mHealth data integration for broader applicability and increased predictive power.

Keywords