Machine learning and the electrocardiogram over two decades: Time series and meta-analysis of the algorithms, evaluation metrics and applications

作者：

Highlights：

• From 2018, DL has appeared and used for ECG classification with promising results.

• ML outperformed physicians in detecting some arrhythmias such as AF.

• SVM has since been the trend and the most frequently used ML algorithm

• Accuracy has been trending upwards significantly for evaluating ML algorithms.

摘要

•From 2018, DL has appeared and used for ECG classification with promising results.•ML outperformed physicians in detecting some arrhythmias such as AF.•SVM has since been the trend and the most frequently used ML algorithm•Accuracy has been trending upwards significantly for evaluating ML algorithms.

论文关键词：Machine learning,Deep learning,Electrocardiogram,Artificial intelligence

论文评审过程：Received 6 November 2020, Revised 2 August 2022, Accepted 19 August 2022, Available online 27 August 2022, Version of Record 2 September 2022.

论文官网地址：https://doi.org/10.1016/j.artmed.2022.102381