Automated Speech Analysis for Screening and Monitoring Bipolar Depression: Machine Learning Model Development and Interpretation Study
Between- and within-person comparisons of speech markers can be leveraged in detecting and monitoring bipolar depression. We demonstrate the feasibility of applying Linguistic Inquiry and Word Count-based psycholinguistic analysis to machine-transcribed and translated speech, supporting the replicability of this approach across languages. Automated multimodal voice analysis can be integrated into digital health platforms, providing a scalable and effective approach for accessing mental health monitoring and care.
Authors
- Tae-Sung Yeum (ORCID: https://orcid.org/0000-0002-9623-5861)
- Sooyeon Min (ORCID: https://orcid.org/0000-0002-9414-5635)
- Yong Min Ahn (ORCID: https://orcid.org/0000-0002-4458-797X)
- Sang Jin Rhee (ORCID: https://orcid.org/0000-0001-6221-5953)
- Daun Shin (ORCID: https://orcid.org/0000-0002-0953-6245)
- Hyunju Lee (ORCID: https://orcid.org/0000-0002-4237-070X)
- Seongmin Park (ORCID: https://orcid.org/0000-0002-9828-7972)
- Han-Sung Lee (ORCID: https://orcid.org/0000-0001-5391-6723)
- Jihwa Lee (ORCID: https://orcid.org/0009-0002-1927-8785)
Institutions
- Seoul National University (KR)
- Korea University Medical Center (KR)
- Seoul National University Hospital (KR)
- Research for Action (US)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-11-03
- DOI
- https://doi.org/10.2196/79093
- Primary Topic
- Mental Health via Writing
- Type
- article
- Field-Weighted Citation Impact
- 0.00