Aligning Large Language Models for Enhancing Psychiatric Interviews Through Symptom Delineation and Summarization: Pilot Study
LLMs, using either (1) appropriate prompting techniques or (2) fine-tuning methods with data labeled by mental health experts, achieved an accuracy of over 0.8 for the symptom delineation task when measured across all segments in the transcript. Additionally, they attained a G-Eval score of over 4.6 for coherence in the summarization task. This research contributes to the emerging field of applying LLMs in psychiatric interviews and demonstrates their potential effectiveness in assisting mental health practitioners.
Authors
- Junho Na (ORCID: https://orcid.org/0009-0004-1054-1975)
- Jy-yong Sohn (ORCID: https://orcid.org/0000-0002-8741-1405)
- Sang Hui Chu (ORCID: https://orcid.org/0000-0001-6877-5599)
- JiYeon Choi (ORCID: https://orcid.org/0000-0003-1947-7952)
- Byung-Hoon Kim (ORCID: https://orcid.org/0000-0003-2501-038X)
- Eunji Kim (ORCID: https://orcid.org/0009-0008-2175-4043)
- Joonhwan Chang
- Jae-hee So (ORCID: https://orcid.org/0009-0007-2659-5371)
Institutions
- Yonsei University (KR)
Publication Details
- Journal
- JMIR Formative Research
- Published
- 2024-10-03
- DOI
- https://doi.org/10.2196/58418
- Citations
- 13
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.52
Funders
- National Research Foundation
- National Research Foundation of Korea
- Ministry of Science and ICT, South Korea
- Institute for Information and Communications Technology Promotion