Estimating Blood Pressure with a Camera: An Exploratory Study of Ambulatory Patients with Cardiovascular Disease

2025-03-02

AI Summary

Hypertension management is hindered by limited accessibility and poor adherence to conventional cuff-based blood pressure (BP) measurement. Although remote photoplethysmography (rPPG) enables contactless BP monitoring, prior studies excluded patients with cardiovascular disease (CVD) or arrhythmias—raising concerns about clinical generalizability. Method: This study is the first to prospectively enroll high-risk outpatients—including those with confirmed CVD and atrial fibrillation—in a real-world cardiology clinic. Facial rPPG was captured via smartphone cameras and fused with fingertip PPG, ECG, and vital signs to train a deep learning model; pulse wave analysis further extracted time-domain and morphological features. Contribution/Results: rPPG signal quality matched that of contact PPG. For systolic BP ≥130 mmHg classification, the model achieved a positive predictive value of 71% (baseline prevalence: 48.3%), with performance non-inferior to that in sinus rhythm patients. This work overcomes prior exclusions of high-risk populations and demonstrates rPPG’s reliability and practical potential in complex clinical settings.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: Voting

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Hypertension is a leading cause of morbidity and mortality worldwide. The ability to diagnose and treat hypertension in the ambulatory population is hindered by limited access and poor adherence to current methods of monitoring blood pressure (BP), specifically, cuff-based devices. Remote photoplethysmography (rPPG) evaluates an individual's pulse waveform through a standard camera without physical contact. Cameras are readily available to the majority of the global population via embedded technologies such as smartphones, thus rPPG is a scalable and promising non-invasive method of BP monitoring. The few studies investigating rPPG for BP measurement have excluded high-risk populations, including those with cardiovascular disease (CVD) or its risk factors, as well as subjects in active cardiac arrhythmia. The impact of arrhythmia, like atrial fibrillation, on the prediction of BP using rPPG is currently uncertain. We performed a study to better understand the relationship between rPPG and BP in a real-world sample of ambulatory patients from a cardiology clinic with established CVD or risk factors for CVD. We collected simultaneous rPPG, PPG, BP, ECG, and other vital signs data from 143 subjects while at rest, and used this data plus demographics to train a deep learning model to predict BP. We report that facial rPPG yields a signal that is comparable to finger PPG. Pulse wave analysis (PWA)-based BP estimates on this cohort performed comparably to studies on healthier subjects, and notably, the accuracy of BP prediction in subjects with atrial fibrillation was not inferior to subjects with normal sinus rhythm. In a binary classification task, the rPPG model identified subjects with systolic BP $geq$ 130 mm Hg with a positive predictive value of 71% (baseline prevalence 48.3%), highlighting the potential of rPPG for hypertension monitoring.

Problem

• Explores non-invasive BP monitoring using camera-based rPPG technology.
• Assesses rPPG's accuracy in CVD patients and those with arrhythmias.
• Develops deep learning model for BP prediction from rPPG data.

Innovation

• Uses remote photoplethysmography for BP monitoring
• Deep learning model predicts blood pressure
• Effective in patients with cardiovascular disease