High-Throughput, Contact-Free Detection of Atrial Fibrillation From Video With Deep Learning

Bryan P Yan; William H S Lai; Christy K Y Chan; Alex C K Au; Ben Freedman; Yukkee C Poh; Ming-Zher Poh

doi:10.1001/jamacardio.2019.4004

High-Throughput, Contact-Free Detection of Atrial Fibrillation From Video With Deep Learning

JAMA Cardiol. 2020 Jan 1;5(1):105-107. doi: 10.1001/jamacardio.2019.4004.

Authors

Bryan P Yan^{1

2

3}, William H S Lai¹, Christy K Y Chan¹, Alex C K Au², Ben Freedman⁴, Yukkee C Poh⁵, Ming-Zher Poh⁵

Affiliations

¹ Division of Cardiology, Department of Medicine and Therapeutics, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong SAR, China.
² Division of Cardiology, Department of Medicine and Therapeutics, Prince of Wales Hospital, Hong Kong SAR, China.
³ Heart and Vascular Institute, The Chinese University of Hong Kong, Hong Kong SAR, China.
⁴ Heart Research Institute, Charles Perkins Centre, and Concord Hospital Cardiology, University of Sydney, Australia.
⁵ Cardiio Inc, Cambridge, Massachusetts.

Abstract

This study uses video and a pretrained deep convolutional neural network to analyze facial photoplethysmographic signals in detection of atrial fibrillation.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adult
Aged
Aged, 80 and over
Atrial Fibrillation / diagnosis*
Atrial Fibrillation / physiopathology
Case-Control Studies
Deep Learning*
Electrocardiography
Face*
Female
Humans
Male
Middle Aged
Neural Networks, Computer
Photoplethysmography / methods*
Predictive Value of Tests
Proof of Concept Study
Reproducibility of Results
Video Recording*