发表机构
Sharif University of Technology; University of Southern California（伊朗德黑兰谢里夫理工大学; 美国南加州大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究可解释机器学习应用于心理健康结果时构建重叠问题，通过弹性网络管道及多组数据验证，发现特质焦虑和健康满意度占主导，经残差化实验揭示机制，指出残差化协议可用于相关XAI研究避免误判。
AI 中文摘要
可解释机器学习（XML）管道应用于综合心理健康结果时，可能会产生看似稳健、跨人群稳定的风险层次结构，但很大程度上是结果构建方式的产物。我们通过应用于洛桑大学886名医学生（主要队列，2022年）的弹性网络管道进行了演示，该管道在三个时间点的2580个纵向观察数据以及来自八个院系的701名非医学生中得到验证；所有三个数据集使用相同的工具。管道产生了一个层次结构，其中特质焦虑和健康满意度在任何测量结果的地方都占主导地位，在所有五个评估集中前两位的肯德尔τ系数为1.0，且具有一致的转移性能（R²：0.41 - 0.49）。两个残差化实验揭示了机制：当特质焦虑（STAI-T）相对于共同包含的抑郁子量表（CES-D，r = 0.72）进行残差化时，模型R²从0.41降至0.16，STAI-T从排名第1降至第6；当倦怠子量表相对于CES-D进行残差化时，R²降至0.016。预测区间在0 - 100量表上平均为35.4单位（2.4个结果标准差），独立排除了个体层面的部署。残差化协议是本文可转移的贡献：任何结合相关预测变量和结果构建的XAI研究在将明显的稳定性解释为发现之前都应应用此检查。
英文摘要
Explainable machine learning (XML) pipelines applied to composite mental health outcomes can produce apparently-robust, cross-population-stable risk hierarchies that are largely artefacts of how the outcome was constructed. We demonstrate this using an ElasticNet pipeline applied to 886 medical students at the University of Lausanne (primary cohort, 2022), validated across 2,580 longitudinal observations at three time points and 701 non-medical students from eight faculties; all three datasets share identical instruments. The pipeline produces a hierarchy in which trait anxiety and health satisfaction dominate wherever the outcome is measured, with Kendall $τ= 1.0$ for the top-two positions across all five evaluation sets and consistent transfer performance ($R^2$: 0.41-0.49). Two residualization experiments, which isolate shared variance between correlated variables via regression, reveal the mechanism: when trait anxiety (STAI-T) is residualized against the co-included depression subscale (CES-D, $r = 0.72$), model $R^2$ drops from 0.41 to 0.16 and STAI-T falls from rank 1 to rank 6; when burnout subscales are residualized against CES-D, $R^2$ collapses to 0.016. Prediction intervals average 35.4 units on a 0-100 scale (2.4 outcome standard deviations), independently ruling out individual-level deployment. The residualization protocol is the paper's transferable contribution: any XAI study combining correlated predictor and outcome constructs should apply this check before interpreting apparent stability as a finding.
