Mobile Personal Healthcare System for Non-Invasive, Pervasive and Continuous Blood Pressure Monitoring: A Feasibility Study (Preprint)

BACKGROUND Smartphone-based blood pressure (BP) monitor using photoplethysmogram (PPG) technology has emerged as a promising approach to empower users with self-monitoring for effective diagnosis and control of hypertension (HT). OBJECTIVE This study aimed to develop a mobile personal healthcare system for non-invasive, pervasive, and continuous estimation of BP level and variability to be user-friendly to elderly. METHODS The proposed approach was integrated by a self-designed cuffless, calibration-free, wireless and wearable PPG-only sensor, and a native purposely-designed smartphone application using multilayer perceptron machine learning techniques from raw signals. We performed a feasibility study with three elder adults (mean age 61.3 ± 1.5 years; 66% women) to test usability and accuracy of the smartphone-based BP monitor. RESULTS The employed artificial neural network (ANN) model performed with good average accuracy >90% and very strong correlation >0.90 (P < .0001) to predict the reference BP values of our validation sample (n=150). Bland-Altman plots showed that most of the errors for BP prediction were less than 10 mmHg. However, according to Association for the Advancement of Medical Instrumentation (AAMI) and British Hypertension Society (BHS) standards, only DBP prediction met the clinically accepted accuracy thresholds. CONCLUSIONS With further development and validation, the proposed system could provide a cost-effective strategy to improve the quality and coverage of healthcare, particularly in rural zones, areas lacking physicians, and solitary elderly populations.