Improving the efficacy of Deep Learning models for Heart Beat detection on heterogeneous datasets

TL;DR

This paper investigates the challenges of applying deep learning models for heart beat detection across heterogeneous ECG datasets and demonstrates that transfer learning can improve model generalization to diverse populations and devices.

Contribution

The study highlights the limitations of DL models trained on homogeneous data and shows how transfer learning enhances performance on varied ECG datasets, promoting better generalizability.

Findings

Transfer learning improves ECG heartbeat detection across different datasets.

Models trained on healthy subjects perform poorly on patients with cardiac conditions.

Using transfer learning with small datasets still yields significant performance gains.

Abstract

Deep Learning (DL) have greatly contributed to bioelectric signals processing, in particular to extract physiological markers. However, the efficacy and applicability of the results proposed in the literature is often constrained to the population represented by the data used to train the models. In this study, we investigate the issues related to applying a DL model on heterogeneous datasets. In particular, by focusing on heart beat detection from Electrocardiogram signals (ECG), we show that the performance of a model trained on data from healthy subjects decreases when applied to patients with cardiac conditions and to signals collected with different devices. We then evaluate the use of Transfer Learning (TL) to adapt the model to the different datasets. In particular, we show that the classification performance is improved, even with datasets with a small sample size. These results suggest that a greater effort should be made towards generalizability of DL models applied on bioelectric signals, in particular by retrieving more representative datasets.