Improving the Efficacy of Deep-Learning Models for Heart Beat Detection on Heterogeneous Datasets
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 t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/8/12/193 |
| _version_ | 1827674067891650560 |
|---|---|
| author | Andrea Bizzego Giulio Gabrieli Michelle Jin Yee Neoh Gianluca Esposito |
| author_facet | Andrea Bizzego Giulio Gabrieli Michelle Jin Yee Neoh Gianluca Esposito |
| author_sort | Andrea Bizzego |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T04:34:26Z |
| format | Article |
| id | doaj.art-22f018aadbcc41aea945b709a68c8292 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-10T04:34:26Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-22f018aadbcc41aea945b709a68c82922023-11-23T03:52:07ZengMDPI AGBioengineering2306-53542021-11-0181219310.3390/bioengineering8120193Improving the Efficacy of Deep-Learning Models for Heart Beat Detection on Heterogeneous DatasetsAndrea Bizzego0Giulio Gabrieli1Michelle Jin Yee Neoh2Gianluca Esposito3Department of Psychology and Cognitive Science, University of Trento, 38068 Trento, ItalyPsychology Program, Nanyang Technological University, Singapore 639818, SingaporePsychology Program, Nanyang Technological University, Singapore 639818, SingaporeDepartment of Psychology and Cognitive Science, University of Trento, 38068 Trento, ItalyDeep 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.https://www.mdpi.com/2306-5354/8/12/193ECGdeep neural networkstransfer learning |
| spellingShingle | Andrea Bizzego Giulio Gabrieli Michelle Jin Yee Neoh Gianluca Esposito Improving the Efficacy of Deep-Learning Models for Heart Beat Detection on Heterogeneous Datasets Bioengineering ECG deep neural networks transfer learning |
| title | Improving the Efficacy of Deep-Learning Models for Heart Beat Detection on Heterogeneous Datasets |
| title_full | Improving the Efficacy of Deep-Learning Models for Heart Beat Detection on Heterogeneous Datasets |
| title_fullStr | Improving the Efficacy of Deep-Learning Models for Heart Beat Detection on Heterogeneous Datasets |
| title_full_unstemmed | Improving the Efficacy of Deep-Learning Models for Heart Beat Detection on Heterogeneous Datasets |
| title_short | Improving the Efficacy of Deep-Learning Models for Heart Beat Detection on Heterogeneous Datasets |
| title_sort | improving the efficacy of deep learning models for heart beat detection on heterogeneous datasets |
| topic | ECG deep neural networks transfer learning |
| url | https://www.mdpi.com/2306-5354/8/12/193 |
| work_keys_str_mv | AT andreabizzego improvingtheefficacyofdeeplearningmodelsforheartbeatdetectiononheterogeneousdatasets AT giuliogabrieli improvingtheefficacyofdeeplearningmodelsforheartbeatdetectiononheterogeneousdatasets AT michellejinyeeneoh improvingtheefficacyofdeeplearningmodelsforheartbeatdetectiononheterogeneousdatasets AT gianlucaesposito improvingtheefficacyofdeeplearningmodelsforheartbeatdetectiononheterogeneousdatasets |