用于自动化精神科评估的 LLM 问卷填写
LLM Questionnaire Completion for Automatic Psychiatric Assessment
AI总结:
本文提出用 LLM 扮演受访者,将非结构化心理访谈转成结构化问卷并编码特征,再以 Random Forest 预测 PHQ-8 与 PCL-C,提升了诊断准确性。
摘要:
我们采用大型语言模型(LLM),将非结构化心理访谈转换为涵盖多个精神科和人格领域的结构化问卷。该 LLM 被提示通过扮演受访者来回答这些问卷。所得答案被编码为特征,并使用 Random Forest 回归器预测抑郁症(PHQ-8)和 PTSD(PCL-C)的标准化精神科测量指标。结果表明,与多个基线相比,我们的方法提高了诊断准确性。因此,它建立了一个解释非结构化心理访谈的新颖框架,弥合了心理健康评估中叙事驱动方法与数据驱动方法之间的差距。
英文摘要:
We employ a Large Language Model (LLM) to convert unstructured psychological interviews into structured questionnaires spanning various psychiatric and personality domains. The LLM is prompted to answer these questionnaires by impersonating the interviewee. The obtained answers are coded as features, which are used to predict standardized psychiatric measures of depression (PHQ-8) and PTSD (PCL-C), using a Random Forest regressor. Our approach is shown to enhance diagnostic accuracy compared to multiple baselines. It thus establishes a novel framework for interpreting unstructured psychological interviews, bridging the gap between narrative-driven and data-driven approaches for mental health assessment.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。