Ensemble machine learning for personalized antihypertensive treatment

Due to its prevalence and association with cardiovascular diseases premature death, hypertension is a major public health challenge. Proper prevention management measures are needed effectively reduce the pervasiveness of condition. Current clinical guidelines for provide physicians general suggestions first-line pharmacologic treatment, but do not consider patient-specific characteristics. In this study, longitudinal electronic record data utilized develop personalized predictions prescription recommendations hypertensive patients. We demonstrate that both binary classification regression algorithms can be used accurately predict patient's future status. then present prescriptive framework determine optimal antihypertensive treatment patient using their individual characteristics Given observational nature data, we address potential confounding through generalized propensity score evaluation matching. For patients whom algorithm recommendation differs from standard care, an approximate 15.87% decrease in next blood pressure based on predicted outcome under recommended treatment. An interactive dashboard has been developed by as support tool.