Generating an Explainable ECG Beat Space With Variational Auto-Encoders

TL;DR

This paper introduces a variational auto-encoder approach to create an interpretable ECG beat space, enhancing explainability in heart beat classification models for clinical use.

Contribution

It proposes a novel use of variational auto-encoders with dense networks to generate human-interpretable ECG embeddings, addressing the black-box issue.

Findings

Generated ECG beat space with characteristic base beats

Enhanced interpretability of ECG classification models

Demonstrated potential for clinical application

Abstract

Electrocardiogram signals are omnipresent in medicine. A vital aspect in the analysis of this data is the identification and classification of heart beat types which is often done through automated algorithms. Advancements in neural networks and deep learning have led to a high classification accuracy. However, the final adoption of these models into clinical practice is limited due to the black-box nature of the methods. In this work, we explore the use of variational auto-encoders based on linear dense networks to learn human interpretable beat embeddings in time-series data. We demonstrate that using this method, an interpretable and explainable ECG beat space can be generated, set up by characteristic base beats.