A Deep Learning Approach to Monitoring and Detecting Atrial Fibrillation using Wearable Technology

Supreeth Prajwal Shashikumar1, Amit Shah2, Qiao Li3, Gari Clifford, Shamim Nemati2

  • 1Georgia Institute of Technology
  • 2Emory University School of Medicine
  • 3Emory University School Of Medicine

Details

09:05 - 09:55 | Fri 17 Feb | Ballroom D | FrRAF.11

Session: Rapid Fire Session 03: Sensor Informatics II

Abstract

Atrial Fibrillation (AF) is the most common cardiac arrhythmia in clinical practice, with a prevalence of 2% in the community. Not only it is associated with reduced quality of life, but also increased risk of stroke and myocardial infarction. Unfortunately, many cases of AF are clinically silent and undiagnosed, but long-term monitoring is difficult. Wearables have enormous potential to provide low-risk and low-cost long-term monitoring of AF, but signals from such devices suffer from significant movement related noise that resembles AF. Pulsatile photoplethysmographic data and triaxial accelerometry from 98 subjects (45 with AF and 53 with other rhythms) were captured using a multichannel wrist-worn device. A single channel electrocardiogram (for rhythm verification only) was recorded simultaneously. A novel deep neural network approach to classify AF from wrist-worn PPG signals was developed on this data. A continuous wavelet transform was applied to the PPG data and a convolutional neural network was trained on the derived spectrograms to detect AF. Combining the output of the CNN with features calculated based on beat-to-beat variability and signal quality provided a significant accuracy boost. Leave-one-out cross validation resulted in a pooled AUC of 0.95 (Accuracy=91.8%). The proposed approach resulted in a novel robust and accurate algorithm for detection of AF from PPG data, which is scalable and likely to improve in accuracy as the dataset size continues to expand.