Earlier identification of hypertensive events in a telemonitoring system

Hypertension is a prevalent risk factor for cardiovascular disease and premature mortality. Telemonitoring can be used to provide a communication pipeline between patients and clinicians for diagnosing hypertension and staging early intervention. However, it takes healthcare resources to monitor patients and identify patients at risk of experiencing a hypertensive event. To reduce the burden on the health care system, we present an automated early warning system to predict patients at risk of a hypertensive event. We first construct a fusion model that utilizes a dual stage attention mechanism to determine whether a hypertensive event occurs in the next seven days and compare its performance to XGBoost and logistic regression. Then, we measure its performance in an early warning system to determine whether it can detect the onset of the first hypertensive event for each patient. With the best threshold, the early warning system using this model has an F1 score of 0.61.