Effects of lead position, cardiac rhythm variation and drug-induced QT prolongation on performance of machine learning methods for ECG processing

TL;DR

This study investigates how lead placement, heart rhythm variability, and drug effects influence machine learning performance in ECG analysis, emphasizing the need for diverse training data for real-world applications.

Contribution

It provides a preliminary analysis of physiological factors affecting ECG machine learning models, highlighting the importance of dataset diversity for improved accuracy.

Findings

Lead choice impacts model performance

Physiological variability affects ECG analysis accuracy

Dataset enrichment with condition-specific ECG signals improves results

Abstract

Machine learning shows great performance in various problems of electrocardiography (ECG) signal analysis. However, collecting a dataset for biomedical engineering is a very difficult task. Any dataset for ECG processing contains from 100 to 10,000 times fewer cases than datasets for image or text analysis. This issue is especially important because of physiological phenomena that can significantly change the morphology of heartbeats in ECG signals. In this preliminary study, we analyze the effects of lead choice from the standard ECG recordings, variation of ECG during 24-hours, and the effects of QT-prolongation agents on the performance of machine learning methods for ECG processing. We choose the problem of subject identification for analysis, because this problem may be solved for almost any available dataset of ECG data. In a discussion, we compare our findings with observations from other works that use machine learning for ECG processing with different problem statements. Our results show the importance of training dataset enrichment with ECG signals acquired in specific physiological conditions for obtaining good performance of ECG processing for real applications.