Accurate Blood Pressure Estimation during Activities of Daily Living: A Wearable Cuffless Solution.

摘要: The objective is to develop a cuffless method that accurately estimates blood pressure (BP) during activities of daily living. User-specific nonlinear autoregressive models with exogenous inputs (NARX) are implemented using artificial neural networks estimate the BP waveforms from electrocardiography and photoplethysmography signals. To broaden range in training data, subjects followed short procedure consisting sitting, standing, walking, Valsalva maneuvers, static handgrip exercises. was performed before after six-hour testing phase wherein five participants went about their normal living activities. Data were further collected at four-month time point for two again six months one two. performance three different NARX compared pulse arrival (PAT) models. demonstrate superior accuracy correlation ground truth systolic diastolic measures PAT clear advantage estimating large BP. Preliminary results show can even apart training. suggests it robust against variabilities due sensor placement. This establishes estimation be used continuous monitoring acute hypotension hypertension detection.