A Wearable Electrocardiogram Telemonitoring System for Atrial Fibrillation Detection.

Minggang Shao,Yanping Bai,Shuicai Wu,Guangyu Bin,Zhuhuang Zhou

doi:10.3390/s20030606

Minggang Shao, Yanping Bai + Show 3 more

Open Access

https://doi.org/10.3390/s20030606

Copy DOI

Abstract

In this paper we proposed a wearable electrocardiogram (ECG) telemonitoring system for atrial fibrillation (AF) detection based on a smartphone and cloud computing. A wearable ECG patch was designed to collect ECG signals and send the signals to an Android smartphone via Bluetooth. An Android APP was developed to display the ECG waveforms in real time and transmit every 30 s ECG data to a remote cloud server. A machine learning (CatBoost)-based ECG classification method was proposed to detect AF in the cloud server. In case of detected AF, the cloud server pushed the ECG data and classification results to the web browser of a doctor. Finally, the Android APP displayed the doctor’s diagnosis for the ECG signals. Experimental results showed the proposed CatBoost classifier trained with 17 selected features achieved an overall F1 score of 0.92 on the test set (n = 7270). The proposed wearable ECG monitoring system may potentially be useful for long-term ECG telemonitoring for AF detection.

Highlights

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, affecting about33.5 million people worldwide in 2010 [1]
Guidelines from several professional associations recommend screening for AF by prolonged electrocardiogram (ECG) monitoring [4]
The ECG waveforms displayed on the Android APP were consistent with the parameters of FLUKE MPS450, and with the ECG waveforms displayed on the doctor’s web browser. These results demonstrated that ECG signal collection and transmission were reliable

Summary

Introduction

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, affecting about. 33.5 million people worldwide in 2010 [1]. There is growing evidence that AF is associated with sudden cardiac death, stroke, and congestive heart failure, etc. Detection of AF is of critical importance. AF detection is still challenging due to the fact that AF may be atypical or asymptomatic, especially in the elderly. Guidelines from several professional associations recommend screening for AF by prolonged electrocardiogram (ECG) monitoring [4]. Traditional monitoring strategies with 12-lead ECG or Holter have a low detection rate due to the limited duration of the recording

Results

Discussion

Conclusion