Open access
2026
DSM-Guided Large Language Model Reasoning for Depression and PTSD Assessment From Psychiatric Interview Transcripts
Experiments show that DSM-guided summarization and rationale-augmented reasoning substantially improve transcript-based mental health classification performance and indicate that human validation is indispensable when applying LLMs in psychiatry, even though the process is inherently time-consuming.
June-Woo Kim, Haram Yoon, Dawoon Jung et al.
· IEEE Access · 0 citations