MultiFusionNet: Atrial Fibrillation Detection With Deep Neural Networks.

• Type of Material: Article
• Authors: Luan Tran, University of Southern California, Los Angeles, CA, USA.; Yanfang Li, University of Southern California, Los Angeles, CA, USA.; Luciano Nocera, University of Southern California, Los Angeles, CA, USA.; Cyrus Shahabi, University of Southern California, Los Angeles, CA, USA.; Li Xiong, Emory University
• Language: English
• Date: 2020
• Publisher: AMIA
• Publication Version: Final Published Version
• Copyright Statement: ©2020 AMIA - All rights reserved.
• Title of Journal or Parent Work: AMIA Joint Summits on Translational Science
• Volume: 2020
• Start Page: 654
• End Page: 663
• Grant/Funding Information: This work has been supported in part by the National Institutes of Health (NIH) CTSA Award UL1TR002378, the USC Integrated Media Systems Center, and unrestricted cash gifts from Oracle and Google.
• Keywords: Cardiovascular System & Cardiology; Detection; Neural network; Coronary artery disease; Atrial fibrillation
• Research Categories: Biology, Bioinformatics; Health Sciences, Public Health; Biology, Neuroscience; Health Sciences, Health Care Management

Abstract

Atrial fibrillation (AF) is the most common cardiac arrhythmia as well as a significant risk factor in heart failure and coronary artery disease. AF can be detected by using a short ECG recording. However, discriminating atrial fibrillation from normal sinus rhythm, other arrhythmia and strong noise, given a short ECG recording, is challenging. Towards this end, we propose MultiFusionNet, a deep learning network that uses a multiplicative fusion method to combine two deep neural networks trained on different sources of knowledge, i.e., extracted features and raw data. Thus, MultiFusionNet can exploit the relevant extracted features to improve upon the utilization of the deep learning model on the raw data. Our experiments show that this approach offers the most accurate AF classification and outperforms recently published algorithms that either use extracted features or raw data separately. Finally, we show that our multiplicative fusion method for combining the two sub-networks outperforms several other combining methods.