Richter Maike, Emden Daniel, Leenings Ramona, Winter Nils R, Mikolajczyk Rafael, Massag Janka, Zwiky Esther, Borgers Tiana, Redlich Ronny, Koutsouleris Nikolaos, Falguera Renata, Edwin Thanarajah Sharmili, Padberg Frank, Reinhard Matthias A, Back Mitja D, Morina Nexhmedin, Buhlmann Ulrike, Kircher Tilo, Dannlowski Udo, Hahn Tim, Opel Nils
Department of Psychiatry and Psychotherapy, Jena University Hospital, Jena, Germany.
Institute for Translational Psychiatry, University of Münster, Münster, Germany.
Mol Psychiatry. 2025 Mar 19. doi: 10.1038/s41380-025-02950-0.
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, M = 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.
人们对机器学习模型在心理健康领域的可推广性存在担忧，部分原因是研究队列与现实世界人群之间的抽样效应和数据差异。我们旨在研究仅基于易于获取且低成本的临床数据训练的机器学习模型，能否在来自各种研究和现实世界临床环境的未见独立数据集中预测抑郁症状的严重程度。这项观察性多队列研究纳入了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M = 36.27岁，范围15 - 81岁），所有参与者均被诊断为情感障碍。我们首先使用76个临床和社会人口统计学变量，比较了来自同一治疗中心的研究型和现实世界中的住院患者。然后应用具有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）开发一个用于预测抑郁严重程度的稀疏机器学习模型。在九个外部样本上测试了模型的可推广性。该模型在所有样本中均可靠地预测了抑郁严重程度（r = 0.60，标准差SD = 0.089，p < 0.0001），并且在每个单独的外部样本中也能预测，预测性能范围从现实世界普通人群样本中的r = 0.48到现实世界住院患者样本中的r = 0.73。这些结果表明，基于稀疏临床数据训练的机器学习模型有潜力在不同环境中预测疾病严重程度，为开发更具可推广性的工具以用于常规精神科数据分析提供了见解。
