Domain generalization for voice-based cognitive impairment detection
The adapted DDAIG framework effectively reduced center-specific learning, enhancing the model's ability to generalize cognitive impairment classifications across different centers. These findings suggest the role of domain generalization in developing reliable AI diagnostic tools for cognitive disorder detection.
Authors
- SangYun Kim (ORCID: https://orcid.org/0000-0002-9101-5704)
- YongSoo Shim (ORCID: https://orcid.org/0000-0001-5642-5401)
- Young Chul Youn (ORCID: https://orcid.org/0000-0002-2742-1759)
- Nayoung Ryoo (ORCID: https://orcid.org/0000-0001-5145-115X)
- Hunboc Lee
- Hyunjoo Choi (ORCID: https://orcid.org/0000-0003-4654-3206)
- Ho Tae Jeong (ORCID: https://orcid.org/0000-0001-9228-6912)
- Yugwon Won (ORCID: https://orcid.org/0000-0001-9419-9986)
- Minsoo Kim (ORCID: https://orcid.org/0000-0002-2228-5874)
- Gihyun Yun (ORCID: https://orcid.org/0009-0008-4522-5189)
Institutions
- Korea Nazarene University (KR)
- Seoul National University Bundang Hospital (KR)
- Re-shaping Development Institute (KR)
- Chung-Ang University Hospital (KR)
- Chung-Ang University (KR)
- Catholic University of Korea (KR)
Publication Details
- Journal
- BMC Medical Informatics and Decision Making
- Published
- 2025-11-24
- DOI
- https://doi.org/10.1186/s12911-025-03268-1
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00