使用大语言模型对儿童青少年精神病理学进行维度化测量
本研究利用符合《健康保险可携性与责任法案》的大语言模型(gpt-4-1106-preview),从2008年11月至2015年3月一家大型学术医学中心精神科急诊就诊的≤18岁个体(3059人)的叙事临床笔记中提取6个研究领域标准(RDoC)维度评分,并与既往验证的基于词元的方法比较;结果发现除感觉运动域外,各维度评分越高与住院可能性越高相关,且不同种族间积极效价评分存在差异。
要点
- 大语言模型可解释地提取6个RDoC维度评分,且与临床结局(住院)相关。
- 除感觉运动域外,所有RDoC维度评分越高,住院可能性越高(校正后p<.001)。
- 不同种族间积极效价评分存在轻微但统计学显著的差异(p<.05)。
核心结论
- 大语言模型可解释地提取了6个RDoC维度评分,这些评分与临床结局相关。
- 该方法可为基于维度精神病理学的新一代预测模型或生物学研究做出贡献。
研究设计与样本
- 研究为队列研究,使用2008年11月至2015年3月一家大型学术医学中心精神科急诊就诊的≤18岁个体的健康记录。
- RDoC维度评分使用符合《健康保险可携性与责任法案》的大语言模型(gpt-4-1106-preview)估计,并与既往验证的基于词元的方法比较。
- 结局为住院和急诊停留时长。
主要发现
- 队列共纳入3059人,中位年龄16岁(四分位距13-18),女性1580人(52%),男性1479人(48%),其中1695人(55%)被收住院。
- 大语言模型提取的RDoC评分与基于词元的评分相关性为小到中等(Kendall's tau 0.14-0.22)。
- 在调整社会人口学和临床特征的逻辑回归模型中,除感觉运动域外,所有维度评分越高,住院可能性越高(所有校正关联p<.001);感觉运动域与住院可能性呈反向关联。
- 偏倚检验提示不同种族间积极效价评分存在轻微但统计学显著的差异(亚洲人、黑人和西班牙裔个体p<.05)。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: To enable greater use of National Institute of Mental Health Research Domain Criteria (RDoC) in real-world settings, we applied large language models (LLMs) to estimate dimensional psychopathology from narrative clinical notes. METHODS: We conducted a cohort study using health records from individuals age ≤18 years evaluated in the psychiatric emergency department of a large academic medical center between November 2008 and March 2015. Outcomes were hospital admission and length of emergency department stay. RDoC domains were estimated using a Health Insurance Portability and Accountability Act-compliant LLM (gpt-4-1106-preview) and compared with a previously validated token-based approach. RESULTS: The cohort included 3059 individuals (median age 16 years [interquartile range, 13-18]; 1580 [52%] female, 1479 [48%] male; 105 [3.4%] identified as Asian, 329 [11%] as Black, 288 [9.4%] as Hispanic, 474 [15%] as other race, and 1863 [61%] as White), of whom 1695 (55%) were admitted. Correlation between LLM-extracted RDoC scores and the token-based scores ranged from small to medium as assessed by Kendall's tau (0.14-0.22). In logistic regression models adjusting for sociodemographic and clinical features, admission likelihood was associated with greater scores on all domains, with the exception of the sensorimotor domain, which was inversely associated (p < .001 for all adjusted associations). Tests for bias suggested modest but statistically significant differences in positive valence scores by race (p < .05 for Asian, Black, and Hispanic individuals). CONCLUSIONS: An LLM extracted estimates of 6 RDoC domains in an explainable manner, which were associated with clinical outcomes. This approach can contribute to a new generation of prediction models or biological investigations based on dimensional psychopathology.
引用
- McCoy TH, Perlis RH. Dimensional Measures of Psychopathology in Children and Adolescents Using Large Language Models. Biol Psychiatry. 2024. PMID: 38866172. doi:10.1016/j.biopsych.2024.05.008
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。