Observer-Independent Assessment of Content Overlap in Mental Health Questionnaires: Large Language Model–Based Study
These findings demonstrate the feasibility of using LLMs to objectively assess content overlap in diagnostic questionnaires. Notably, the GPT-based approach showed particular promise in aligning with expert-derived symptom structures.
Authors
- M Chakraborty
- Lana Kambeitz‐Ilankovic (ORCID: https://orcid.org/0000-0002-8218-0425)
- Julian Koenig (ORCID: https://orcid.org/0000-0003-1009-9625)
- Kai Vogeley (ORCID: https://orcid.org/0000-0002-5891-5831)
- Theresa Lichtenstein (ORCID: https://orcid.org/0000-0001-5573-1212)
- Jasper Vöckel (ORCID: https://orcid.org/0000-0002-6306-3346)
- David H. V. Vogel (ORCID: https://orcid.org/0000-0003-0645-9034)
- Joseph Kambeitz (ORCID: https://orcid.org/0000-0002-8988-3959)
- Luise Baumeister-Lingens (ORCID: https://orcid.org/0000-0002-5070-2137)
- Annkathrin Böke (ORCID: https://orcid.org/0009-0006-8016-5703)
- H. Häcker
Institutions
- Forschungszentrum Jülich (DE)
- University of Cologne (DE)
- University Hospital Bonn (DE)
- University Hospital Cologne (DE)
Publication Details
- Journal
- JMIR AI
- Published
- 2025-10-24
- DOI
- https://doi.org/10.2196/79868
- Primary Topic
- Mental Health Research Topics
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Universität zu Köln