Key result
Transfer learning improves deep learning ECG heartbeat detection across heterogeneous datasets, even with small samples.
Why the study?
The efficacy and applicability of deep-learning models for bioelectric signal processing are often constrained to the population used for training.
Transfer learning can improve the generalizability and performance of deep learning models for ECG heart beat detection across diverse patient populations and devices.
May improve DL-based ECG analysis across heterogeneous datasets with limited data; leaves open prospective clinical validation before adoption.
Deep learning (DL) has greatly contributed to bioelectric signal 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 the generalizability of DL models applied on bioelectric signals, in particular, by retrieving more representative datasets.
No takes yet. Share an insight, caveat, or question.
Andrea Bizzego (2021) studied Heart beat detection from ECG. Transfer learning (TL) vs. Model trained on healthy subjects was evaluated on Classification performance. Transfer learning improved the classification performance of deep learning models for heart beat detection on heterogeneous ECG datasets, even with small sample sizes.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: