[공지사항]을 빙자한 안부와 근황 
Show more

Daily Arxiv

This is a page that curates AI-related papers published worldwide.
All content here is summarized using Google Gemini and operated on a non-profit basis.
Copyright for each paper belongs to the authors and their institutions; please make sure to credit the source when sharing.

Detecting PTSD in Clinical Interviews: A Comparative Analysis of NLP Methods and Large Language Models

Created by
  • Haebom

Author

Feng Chen, Dror Ben-Zeev, Gillian Sparks, Arya Kadakia, Trevor Cohen

Outline

This study evaluated natural language processing approaches for automated detection of underdiagnosed posttraumatic stress disorder (PTSD) in clinical settings. Using the DAIC-WOZ dataset, we compared general and mental health-specific Transformer models (BERT/RoBERTa), embedding-based methods (SentenceBERT/LLaMA), and large-scale language model prompting strategies (zero-shot/few-shot/thoughtchaining). The mental health-specific end-to-end model significantly outperformed the general model (Mental-RoBERTa AUPRC=0.675+/-0.084 vs. RoBERTa-base 0.599+/-0.145), with SentenceBERT embedding using neural networks achieving the highest overall performance (AUPRC=0.758+/-0.128). Few-shot prompting using DSM-5 criteria also showed competitive results (AUPRC=0.737) with only two examples. Performance varied significantly across symptom severity and depressive comorbidity status, with higher accuracy in patients with severe PTSD and those with depressive comorbidity. These results highlight the potential of domain-adaptive embedding and LLM for scalable screening, but also highlight the need for improved detection of subtle symptom manifestations and the development of clinically actionable AI tools for PTSD assessment.

Takeaways, Limitations

Takeaways:
We demonstrate the potential of domain-specific embeddings and large-scale language models (LLMs) to effectively screen for PTSD. In particular, SentenceBERT embeddings and few-shot prompting techniques demonstrate superior performance.
We found that the severity of PTSD and the presence of comorbid disorders such as depression affected the accuracy of PTSD diagnosis.
This study provides important insights for the development of clinically applicable PTSD assessment AI tools.
Limitations:
Improved detection performance for subtle PTSD symptom expressions is needed.
Further research is needed to determine whether performance differs by symptom severity and comorbidities.
Generalizability needs to be considered due to dependence on the DAIC-WOZ dataset.
👍