Abstract

Background: Smartphone-based blood pressure (BP) monitoring using photoplethysmography (PPG) technology has emerged as a promising approach to empower users with self-monitoring for effective diagnosis and control of hypertension. Objective: This study aimed to develop a mobile personal health care system for noninvasive, pervasive, and continuous estimation of BP level and variability, which is user friendly for elderly people. 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 app using multilayer perceptron machine learning techniques from raw signals. We performed a development and usability study with three older adults (mean age 61.3 years, SD 1.5 years; 66% women) to test the usability and accuracy of the smartphone-based BP monitor. Results: The employed artificial neural network model had good average accuracy (>90%) and very strong correlation (>0.90) (P<.001) for predicting 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 the Association for the Advancement of Medical Instrumentation and British Hypertension Society standards, only diastolic blood pressure 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 health care, particularly in rural zones, areas lacking physicians, and areas with solitary elderly populations.