Reading Between the Leads: Local Lead-Attention Based Classification of Electrocardiogram Signals
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Self-attention models have emerged as powerful tools in both computer vision and Natural Language Processing (NLP) domains. However, their application in time-domain Electrocardiogram (ECG) signal analysis has been limited, primarily due to the lesser need for global receptive fields. In this study, we present a novel approach utilizing local self-attention to address multi-class classification tasks using the PhysioNet/Computing in Cardiology Challenge 2021 dataset, encompassing 26 distinct classes across six different datasets. We introduce an innovative concept called 'local lead-attention' to capture features within a single lead and across multiple configurable leads. The proposed architecture achieves an F1 score of 0.521 on the challenge's validation set, marking a 5.67% improvement over the winning solution. Remarkably, our model accomplishes this performance boost with only one-third of the total parameter size, amounting to 2.4 million parameters.
Original language | English |
---|---|
Title of host publication | Computing in Cardiology, CinC 2023 |
Publisher | IEEE Computer Society Press |
Publication date | 2023 |
ISBN (Electronic) | 9798350382525 |
DOIs | |
Publication status | Published - 2023 |
Event | 50th Computing in Cardiology, CinC 2023 - Atlanta, United States Duration: 1 Oct 2023 → 4 Oct 2023 |
Conference
Conference | 50th Computing in Cardiology, CinC 2023 |
---|---|
Land | United States |
By | Atlanta |
Periode | 01/10/2023 → 04/10/2023 |
Series | Computing in Cardiology |
---|---|
ISSN | 2325-8861 |
Bibliographical note
Funding Information:
This project is part of the grant I+D+i PLEC2021-007614, funded by MCIN/AEI/10.13039/501100011033 and by the “European Union NextGenerationEU/PRTR” and by the European Union’s Horizon research and Innovation programme under the Marie Skłodowska-Curie grant agreement No. 860974.
Publisher Copyright:
© 2023 CinC.
ID: 401753296