Raw photoplethysmogram waveforms versus peak-to-peak intervals for machine learning detection of atrial fibrillation: Does waveform matter?
PPG-derived peak-to-peak intervals and PPG waveforms were equivalent as input signals to neural networks in terms of accurate AF detection. The reduced computational requirements of the interval model make it a more suitable option for deployment on digital end-user devices such as smartphones.
Authors
- Caroline Lind (ORCID: https://orcid.org/0009-0002-2165-9544)
- Astrid N L Hermans (ORCID: https://orcid.org/0000-0002-9034-1479)
- Konstanze Betz (ORCID: https://orcid.org/0000-0002-3943-3896)
- Thomas Jespersen (ORCID: https://orcid.org/0000-0001-6575-360X)
- Ulrich Schotten (ORCID: https://orcid.org/0000-0003-1532-3315)
- Kevin Vernooy (ORCID: https://orcid.org/0000-0002-8818-5964)
- Jonas L. Isaksen (ORCID: https://orcid.org/0000-0003-3227-1131)
- Jørgen K. Kanters (ORCID: https://orcid.org/0000-0002-3267-4910)
- Dominik Linz (ORCID: https://orcid.org/0000-0003-4893-0824)
- Malene Nørregaard
- Bolette Arildsen
Institutions
- University of Copenhagen (DK)
- University of California, San Francisco (US)
- Maastricht University Medical Centre (NL)
- Maastricht University (NL)
Publication Details
- Journal
- Computer Methods and Programs in Biomedicine
- Published
- 2024-11-28
- DOI
- https://doi.org/10.1016/j.cmpb.2024.108537
- Citations
- 2
- Primary Topic
- Non-Invasive Vital Sign Monitoring
- Type
- article
- Field-Weighted Citation Impact
- 0.37