用AI分析临床访谈语料，提升创伤后应激障碍的自动识别准确率。
Detecting PTSD in Clinical Interviews: A Comparative Analysis of NLP Methods and Large Language Models
- 采用领域适配的Transformer模型与大模型提示策略对比检测
- 句子嵌入+神经网络方法表现最佳（AUPRC=0.758）
- 对严重症状及共病抑郁者效果更优，适合临床筛查应用
创伤后应激障碍（PTSD）在临床中仍存在大量漏诊，为自动化检测提供了机会。本研究评估了自然语言处理方法在临床访谈转录文本中识别PTSD的性能。比较了通用与心理健康专用的Transformer模型（BERT/RoBERTa）、基于嵌入的方法（SentenceBERT/LLaMA）以及大语言模型提示策略（零样本/少样本/思维链）。领域专用端到端模型显著优于通用模型（Mental-RoBERTa AUPRC=0.675±0.084 vs. RoBERTa-base 0.599±0.145）。SentenceBERT嵌入结合神经网络取得最高整体性能（AUPRC=0.758±0.128）。使用DSM-5标准进行少样本提示（仅两例）也获得良好结果（AUPRC=0.737）。不同症状严重度与共病抑郁状态影响表现，重度PTSD及共病抑郁患者检测准确率更高。研究揭示了领域适配嵌入与大模型在可扩展筛查中的潜力，同时强调需改进对复杂表型的识别，并为开发临床可用的AI辅助评估工具提供依据。
原文摘要 · Abstract (English)
Post-Traumatic Stress Disorder (PTSD) remains underdiagnosed in clinical settings, presenting opportunities for automated detection to identify patients. This study evaluates natural language processing approaches for detecting PTSD from clinical interview transcripts. We compared general and mental health-specific transformer models (BERT/RoBERTa), embedding-based methods (SentenceBERT/LLaMA), and large language model prompting strategies (zero-shot/few-shot/chain-of-thought) using the DAIC-WOZ dataset. Domain-specific end-to-end models significantly outperformed general models (Mental-RoBERTa AUPRC=0.675+/-0.084 vs. RoBERTa-base 0.599+/-0.145). SentenceBERT embeddings with neural networks achieved the highest overall performance (AUPRC=0.758+/-0.128). Few-shot prompting using DSM-5 criteria yielded competitive results with two examples (AUPRC=0.737). Performance varied significantly across symptom severity and comorbidity status with depression, with higher accuracy for severe PTSD cases and patients with comorbid depression. Our findings highlight the potential of domain-adapted embeddings and LLMs for scalable screening while underscoring the need for improved detection of nuanced presentations and offering insights for developing clinically viable AI tools for PTSD assessment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。