Exploring deep features and ECG attributes to detect cardiac rhythm classes

作者：

Highlights：

• Both clinical ECG features and features obtained from deep learning model layers are used for detection cardiac rhythms.

• A big ECG dataset containing more than 10,000 subject records was used.

• Lead-II ECG signals from individual subjects grouped into four rhythm classes were analyzed.

• The random forest (RF) classifier yielded a patient-level arrhythmia classification accuracy of 98% ± 0.64 using the fused features.

摘要

•Both clinical ECG features and features obtained from deep learning model layers are used for detection cardiac rhythms.•A big ECG dataset containing more than 10,000 subject records was used.•Lead-II ECG signals from individual subjects grouped into four rhythm classes were analyzed.•The random forest (RF) classifier yielded a patient-level arrhythmia classification accuracy of 98% ± 0.64 using the fused features.

论文关键词：Deep learning,ECG signals,Cardiac rhythm,Feature extraction

论文评审过程：Received 15 March 2021, Revised 20 July 2021, Accepted 7 September 2021, Available online 10 September 2021, Version of Record 24 September 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.107473