Remote Health Monitoring Outcome Success Prediction Using Baseline and First Month Intervention Data

Area of Science:

• Cardiology
• Digital Health
• Health Informatics

Background:

• Remote health monitoring (RHM) systems are increasingly adopted to improve patient care and reduce healthcare costs.
• The Women's Heart Health Study (WHHS) utilized a smartphone-based RHM system, Wanda-cardiovascular disease (CVD), for lifestyle intervention.
• Variability in participant success with RHM necessitates predictive tools to optimize resource allocation.

Purpose of the Study:

• To develop a framework for classifying participants based on RHM success.
• To identify early intervention behaviors and features that predict successful outcomes in RHM.
• To create a prediction tool for clinicians to identify patients likely to benefit from RHM.

Main Methods:

• Analysis of baseline features and first-month intervention data (activity, blood pressure, questionnaires) from the Wanda-CVD system.
• Development of a classification scheme to predict RHM outcome success.
• Evaluation of prediction accuracy using an F-measure.

Main Results:

• The classification scheme achieved a 91.9% F-measure for predicting RHM outcome success.
• Intervention-based smartphone data significantly improved prediction accuracy.
• Specific dietary factors, such as nut, bean, and seed consumption in the first month, were identified as predictors of success.

Conclusions:

• A predictive framework using early intervention data can identify patients likely to succeed with RHM.
• Targeted RHM interventions can optimize healthcare costs and participant time.
• The study highlights the importance of early behavioral and dietary responses in predicting cardiovascular disease RHM success in young Black women.