Improving the efficacy of Deep Learning models for Heart Beat detection on heterogeneous datasets
This addresses the generalizability issue in deep learning for bioelectric signal processing, particularly for ECG analysis, but is incremental as it applies existing transfer learning methods to new data scenarios.
The study tackled the problem of deep learning models for heart beat detection performing poorly on heterogeneous datasets, such as those from patients with cardiac conditions or different devices, and found that using transfer learning improved classification performance even with small sample sizes.
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.