Passive Heart Rate Monitoring During Smartphone Use in Everyday Life

2025-03-04

AI Summary

This work addresses the limited accessibility of cardiovascular health monitoring in the absence of wearable devices. We propose a passive, smartphone front-camera-based algorithm for estimating heart rate (HR) and resting heart rate (RHR) from facial videos. The method integrates remote photoplethysmography (rPPG) signal extraction, cross-device HR calibration, and a lightweight deep learning model to enable seamless, contactless, and user-invisible continuous monitoring in real-world settings. We present the first mobile passive HR system rigorously validated across large-scale, diverse scenarios—including varying illumination, head poses, and skin tones. Crucially, it demonstrates no statistically significant performance disparity across three Fitzpatrick skin-type groups (mean absolute percentage error <10%), achieves daily RHR estimation error <5 bpm, exhibits strong agreement with clinical-grade wearables (Pearson’s *r* > 0.95), and shows significant associations with established cardiovascular risk factors—thereby advancing equitable, convenient, and high-accuracy remote HR monitoring.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Intelligent Robots: State Estimation
• Humans and AI: AI for Accessibility

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Resting heart rate (RHR) is an important biomarker of cardiovascular health and mortality, but tracking it longitudinally generally requires a wearable device, limiting its availability. We present PHRM, a deep learning system for passive heart rate (HR) and RHR measurements during everyday smartphone use, using facial video-based photoplethysmography. Our system was developed using 225,773 videos from 495 participants and validated on 185,970 videos from 205 participants in laboratory and free-living conditions, representing the largest validation study of its kind. Compared to reference electrocardiogram, PHRM achieved a mean absolute percentage error (MAPE)<10% for HR measurements across three skin tone groups of light, medium and dark pigmentation; MAPE for each skin tone group was non-inferior versus the others. Daily RHR measured by PHRM had a mean absolute error<5 bpm compared to a wearable HR tracker, and was associated with known risk factors. These results highlight the potential of smartphones to enable passive and equitable heart health monitoring.

Problem

• Passive heart rate monitoring without wearables
• Accurate heart rate measurement via smartphone video
• Equitable heart health monitoring across skin tones

Innovation

• Deep learning system for passive heart rate monitoring
• Facial video-based photoplethysmography technology
• Validated across diverse skin tones and conditions