Non-contact Atrial Fibrillation Detection from Face Videos by Learning Systolic Peaks

TL;DR

This paper introduces a non-contact method for atrial fibrillation detection using face videos, leveraging deep learning to extract systolic peaks and classify AF with high accuracy, enabling remote health monitoring.

Contribution

It presents a novel approach combining 3D CNNs and a Wasserstein loss to detect systolic peaks from face videos for AF diagnosis, which is a new non-contact technique.

Findings

Achieved 96% accuracy in healthy vs. AF classification.

Achieved 95.23% accuracy in sinus rhythm vs. AF classification.

Demonstrated feasibility of non-contact atrial flutter detection.

Abstract

Objective: We propose a non-contact approach for atrial fibrillation (AF) detection from face videos. Methods: Face videos, electrocardiography (ECG), and contact photoplethysmography (PPG) from 100 healthy subjects and 100 AF patients are recorded. Data recordings from healthy subjects are all labeled as healthy. Two cardiologists evaluated ECG recordings of patients and labeled each recording as AF, sinus rhythm (SR), or atrial flutter (AFL). We use the 3D convolutional neural network for remote PPG monitoring and propose a novel loss function (Wasserstein distance) to use the timing of systolic peaks from contact PPG as the label for our model training. Then a set of heart rate variability (HRV) features are calculated from the inter-beat intervals, and a support vector machine (SVM) classifier is trained with HRV features. Results: Our proposed method can accurately extract systolic peaks from face videos for AF detection. The proposed method is trained with subject-independent 10-fold cross-validation with 30s video clips and tested on two tasks. 1) Classification of healthy versus AF: the accuracy, sensitivity, and specificity are 96.00%, 95.36%, and 96.12%. 2) Classification of SR versus AF: the accuracy, sensitivity, and specificity are 95.23%, 98.53%, and 91.12%. In addition, we also demonstrate the feasibility of non-contact AFL detection. Conclusion: We achieve good performance of non-contact AF detection by learning systolic peaks. Significance: non-contact AF detection can be used for self-screening of AF symptoms for suspectable populations at home or self-monitoring of AF recurrence after treatment for chronic patients.