Deep learning-based stress detection from RR intervals in major depressive disorder, panic disorder, and healthy individuals
Deep learning on raw RRIs detects acute cognitive stress across psychiatric and healthy cohorts without feature engineering. Five-minute windows still yield the best performance, yet 1-min epochs still achieve accuracies of approximately 0.80, demonstrating feasibility for integration into real-time monitoring tools for relapse prevention and personalized care in psychiatry.
Authors
- Ah Young Kim (ORCID: https://orcid.org/0000-0001-6852-663X)
- Kyung Hyun Lee (ORCID: https://orcid.org/0000-0002-7010-5284)
- Sangwon Byun (ORCID: https://orcid.org/0000-0002-5094-8372)
- Chul‐Hyun Cho (ORCID: https://orcid.org/0000-0002-1663-9680)
- Hong Jin Jeon
Institutions
- Electronics and Telecommunications Research Institute (KR)
- Incheon National University (KR)
- Korea University (KR)
- Samsung Medical Center (KR)
- Sungkyunkwan University (KR)
Publication Details
- Journal
- Frontiers in Psychiatry
- Published
- 2025-09-25
- DOI
- https://doi.org/10.3389/fpsyt.2025.1672260
- Primary Topic
- Heart Rate Variability and Autonomic Control
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Incheon National University
- Ministry of Science and ICT, South Korea
- Institute for Information and Communications Technology Promotion