The art of selecting the ECG input in neural networks to classify heart diseases: a dual focus on maximizing information and reducing redundancy
For the first time, this research has quantified the redundancy present in the input by validating various redundancy reduction techniques using a CNN. This discovery paves the way for advancing biomedical signal processing research, simplifying model complexity, and enhancing diagnostic performance in cardiovascular medicine within reduced lead systems, such as Holter monitors or wearables.
Authors
- José Millet (ORCID: https://orcid.org/0000-0002-8879-003X)
- Samuel Ruiperez-Campillo
- Elisa Ramírez (ORCID: https://orcid.org/0000-0001-9644-2011)
- Julia E. Vogt (ORCID: https://orcid.org/0000-0002-6004-7770)
- Francisco Castells (ORCID: https://orcid.org/0000-0001-5044-3545)
- Rubén Casado-Arroyo (ORCID: https://orcid.org/0000-0002-3876-6074)
- José Luís Merino (ORCID: https://orcid.org/0000-0002-1737-1903)
Institutions
- Université Libre de Bruxelles (BE)
- Hospital Universitario La Paz (ES)
- Erasmus Hospital (BE)
- ETH Zurich (CH)
- Universitat Politècnica de València (ES)
Publication Details
- Journal
- Frontiers in Physiology
- Published
- 2024-10-07
- DOI
- https://doi.org/10.3389/fphys.2024.1452829
- Citations
- 3
- Primary Topic
- ECG Monitoring and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 1.21
Funders
- Ministerio de Ciencia e Innovación
- Centro de Investigación Biomédica en Red Enfermedades Cardiovasculares
- Instituto de Salud Carlos III