基于问题的计算语言方法在区分焦虑和抑郁时优于评分尺度
Mona Tabesh1, Mariam Mirström2, Rebecca Astrid Böhme2
1University of Milan-Bicocca, Italy.
Journal of anxiety disorders
|April 25, 2025
概括
基于问题的计算语言评估 (QCLA) 在诊断抑郁和焦虑方面表现有前途. 自传叙述和描述性关键词可以在识别这些精神健康状况时优于传统的评级表.
科学领域:
- 计算语言学计算语言学
- 心理健康评估 心理健康评估
- 自然语言处理 (NLP) 是一种自然语言处理.
背景情况:
- 重度抑郁症 (MD) 和一般焦虑症 (GAD) 是普遍存在的心理健康状况.
- 目前的评估依赖于诸如PHQ-9和GAD-7之类的定量评级尺度.
- 在NLP和ML的进步使新的方法,如基于问题的计算语言评估 (QCLA).
研究的目的:
- 用开放式问题调查QCLA的准确性,以区分自我报告的抑郁症,焦虑症和健康对照患者.
- 为了比较QCLA措施 (描述性关键词,自传叙事) 与传统评级尺度 (PHQ-9,GAD-7) 的有效性.
主要方法:
- 利用开放式问题,包括描述性关键词和自传叙事,进行基于语言的评估.
- 使用机器学习 (ML) 来分析QCLA数据和PHQ-9和GAD-7等级表中的单个项目.
- 计算的歧视措施 (phi系数,φ) 来评估不同评估方法的性能.
主要成果:
- 自传叙述表明,健康个体与焦虑 (φ = 1.58) 和抑郁 (φ = 1.38) 的人之间的歧视最高.
- 描述性关键词和叙述经常超过GAD-7和PHQ-9的总分 (φ=0.80).
- 单个尺度项的ML分析显示了强烈的歧视 (PHQ-9: φ=0.86,GAD-7: φ=0.91),组合尺度进一步改善了歧视 (φ=1.39).
结论:
- QCLA测量,特别是自传叙事,显示出评估抑郁和焦虑的巨大潜力.
- 虽然QCLA可以优于传统的尺度,但单个尺度项和组合尺度方法的ML分析也产生了高度的歧视.
- 这些发现表明,QCLA为现有的心理健康评估工具提供了有价值的,有时更有效的替代方案或补充.
相关概念视频
Generalized Anxiety Disorder
Generalized Anxiety Disorder (GAD) is a chronic condition characterized by excessive and uncontrollable worry that persists for at least six months, significantly interfering with daily functioning. Unlike situational anxiety, which arises in response to specific stressors, GAD often occurs without a clear cause. Individuals may experience disproportionate worry about work, health, or relationships. For instance, a person might continuously fear poor health despite normal medical evaluations or...
Self-Discrepancy and Its Effects
Self-discrepancy theory explains how people compare their actual self to their ideal and ought selves and how mismatches between these self-guides can lead to emotional distress. Developed by E. Tory Higgins, the theory distinguishes among three components of self-concept: the actual self, the ideal self, and the ought self. These refer respectively to how individuals perceive themselves, how they aspire to be, and how they believe they are obligated to be. Emotional well-being, self-esteem,...


