Medication history, not clinical profiles, predicts antihypertensive treatment persistence across health systems

Background. Hypertension control remains poor worldwide, in large part because patients discontinue antihypertensive treatment. Machine-learning (ML) prediction models for medication persistence are typically single-country and cross-sectional, rarely compared with simple clinical information, and lack external validation across health systems. Methods. We harmonized three prospective aging cohorts -- the China Health and Retirement Longitudinal Study (CHARLS), the Survey of Health, Ageing and Retirement in Europe (SHARE), and the US Health and Retirement Study (HRS) -- including adults aged >

This content is for informational purposes only and is not medical advice. It is not intended to diagnose, treat, cure, or prevent any disease. Consult a healthcare professional before starting any supplement, treatment, or program: especially if you are pregnant, nursing, taking medication, or managing a health condition.