Research Area:  Machine Learning

Abstract:

Electrocardiographic (ECG) monitors have been widely used for diagnosing cardiac arrhythmias for decades. However, accurate analysis of ECG signals is difficult and time-consuming work because large amounts of beats need to be inspected. In order to enhance ECG beat classification, machine learning and deep learning methods have been studied. However, existing studies have limitations in model rigidity, model complexity, and inference speed. To classify ECG beats effectively and efficiently, we propose a baseline model with recurrent neural networks (RNNs). Furthermore, we also propose a lightweight model with fused RNN for speeding up the prediction time on central processing units (CPUs). We used 48 ECGs from the MIT-BIH (Massachusetts Institute of Technology-Beth Israel Hospital) Arrhythmia Database, and 76 ECGs were collected with S-Patch devices developed by Samsung SDS. We developed both baseline and lightweight models on the MXNet framework. We trained both models on graphics processing units and measured both models inference times on CPUs.

Keywords:  
Path-type ECG sensor system
ECG classification
Deep learning
Recurrent neural network
Fused recurrent neural network

Author(s) Name:  Eunjoo Jeon, Kyusam Oh, Soonhwan Kwon, HyeongGwan Son, Yongkeun Yun, Eun-Soo Jung, Min Soo Kim

Publisher name:  JMIR

DOI:  10.2196/17037

Volume Information:   Volume 8

Paper Link:   https://medinform.jmir.org/2020/3/e17037/