精神卫生领域临床预测模型的泛化性
这项观察性多队列研究纳入十个欧洲研究和临床机构的3021名情感障碍患者,用弹性网络算法基于五个特征建立稀疏机器学习模型预测抑郁严重度,模型在所有样本中可靠预测抑郁严重度(r=0.60,标准差=0.089,p<0.0001),各外部样本中r从0.48到0.73。
要点
- 模型仅用五个特征预测抑郁严重度,在所有样本中r=0.60(标准差=0.089,p<0.0001)。
- 各外部样本预测性能r从0.48(真实世界一般人群样本)到0.73(真实世界住院患者)。
- 基于稀疏临床数据的机器学习模型有潜力跨不同场景预测疾病严重度。
核心结论
- 基于稀疏临床数据训练的机器学习模型有潜力跨不同场景预测疾病严重度,可为开发更通用的常规精神科数据分析工具提供启示。
研究设计与样本
- 观察性多队列研究,纳入来自十个欧洲研究和临床机构的3021名参与者(女性占62.03%,平均年龄36.27岁,范围15-81岁),均诊断为情感障碍。
- 首先用76个临床和社会人口学变量比较同一治疗中心的研究住院患者与真实世界住院患者。
- 随后应用十折交叉验证的弹性网络算法,基于排名前五的特征(整体功能、外向性、神经质、童年期情感虐待和躯体化)开发稀疏机器学习模型预测抑郁严重度。
- 在九个外部样本中检验模型泛化性。
主要发现
- 模型在所有样本中可靠预测抑郁严重度(r=0.60,标准差=0.089,p<0.0001)。
- 模型在每个独立外部样本中均能预测抑郁严重度,性能从真实世界一般人群样本的r=0.48到真实世界住院患者的r=0.73。
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
Concerns about the generalizability of machine learning models in mental health arise, partly due to sampling effects and data disparities between research cohorts and real-world populations. We aimed to investigate whether a machine learning model trained solely on easily accessible and low-cost clinical data can predict depressive symptom severity in unseen, independent datasets from various research and real-world clinical contexts. This observational multi-cohort study included 3021 participants (62.03% females, MAge = 36.27 years, range 15-81) from ten European research and clinical settings, all diagnosed with an affective disorder. We firstly compared research and real-world inpatients from the same treatment center using 76 clinical and sociodemographic variables. An elastic net algorithm with ten-fold cross-validation was then applied to develop a sparse machine learning model for predicting depression severity based on the top five features (global functioning, extraversion, neuroticism, emotional abuse in childhood, and somatization). Model generalizability was tested across nine external samples. The model reliably predicted depression severity across all samples (r = 0.60, SD = 0.089, p < 0.0001) and in each individual external sample, ranging in performance from r = 0.48 in a real-world general population sample to r = 0.73 in real-world inpatients. These results suggest that machine learning models trained on sparse clinical data have the potential to predict illness severity across diverse settings, offering insights that could inform the development of more generalizable tools for use in routine psychiatric data analysis.
引用
- Richter M, Emden D, Leenings R, et al. Generalizability of clinical prediction models in mental health. Mol Psychiatry. 2025. PMID: 40108256. doi:10.1038/s41380-025-02950-0
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。