Aiding Large Language Models Using Clinical Scoresheets for Neurobehavioral Diagnostic Classification From Text: Algorithm Development and Validation
Current LLM-based chatbots, when prompted naively, underperform on psychiatric and behavioral diagnostic tasks compared to specialized machine learning models. Clinical assessment scales might modestly aid chatbot performance, but more sophisticated prompt engineering and domain integration are likely required to reach clinically actionable standards.
Authors
- Abdur Rasool (ORCID: https://orcid.org/0000-0001-5334-9001)
- Dennis P. Wall (ORCID: https://orcid.org/0000-0002-7889-9146)
- Peter Washington (ORCID: https://orcid.org/0000-0003-3276-4411)
- Saimourya Surabhi (ORCID: https://orcid.org/0000-0002-1707-0537)
- Cezmi Mutlu
- H. H. Zhang (ORCID: https://orcid.org/0000-0003-4017-7129)
- Kaiying Lin
Institutions
- University of Hawaiʻi at Mānoa (US)
- University of California, San Francisco (US)
- Institute of Linguistics, Academia Sinica (TW)
- Stanford University (US)
Publication Details
- Journal
- JMIR AI
- Published
- 2025-08-08
- DOI
- https://doi.org/10.2196/75030
- Citations
- 1
- Primary Topic
- Autism Spectrum Disorder Research
- Type
- article
- Field-Weighted Citation Impact
- 1.43