Deep neural network-based analysis of voice biomarkers for monitoring treatment response in adolescent major depressive disorder
These findings suggest that machine learning models and individual acoustic features may not sufficiently capture treatment-related changes in MDD patients. This study underscores the value of deep learning models using the DVDSA method, addressing the limitations of pre- and post-treatment classification and highlighting their potential to advance personalized treatment strategies for adolescent MDD.
Authors
- Yanghyun Lee
- 김대진 (ORCID: https://orcid.org/0000-0001-6675-5607)
- Seong-Eun Moon (ORCID: https://orcid.org/0000-0001-7891-6930)
- Chan-Mo Yang (ORCID: https://orcid.org/0000-0002-4959-7595)
- June-Woo Kim (ORCID: https://orcid.org/0000-0003-0111-300X)
- Byung‐Soo Kim (ORCID: https://orcid.org/0000-0001-5210-7430)
- Haram Yoon
- Yera Choi
Institutions
- Seoul National University (KR)
- Gwangju Institute of Science and Technology (KR)
- Naver (South Korea) (KR)
- Wonkwang University (KR)
Publication Details
- Journal
- Communications Medicine
- Published
- 2026-02-04
- DOI
- https://doi.org/10.1038/s43856-025-01326-3
- Primary Topic
- Mental Health via Writing
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Ministry of Trade, Industry and Energy
- Korea Health Industry Development Institute