文献速递精神分裂症与精神病性障碍

基于结构脑影像的机器学习判别难治性精神分裂症:多中心概念验证研究

Machine Learning-Based Discrimination of Treatment-Resistant Schizophrenia Using Structural Brain Imaging: A Multi-Site Proof-of-Concept Study.
PubMed 文献 · Biol Psychiatry · 2026-08-22

该多中心概念验证研究纳入加拿大与日本研究的225例精神分裂症患者(122例难治性TRS、103例治疗反应性TxR),用FreeSurfer提取结构MRI特征并结合机器学习判别。泄漏控制下投票集成留出集ROC-AUC仅0.57,全数据集协调后为0.60且解释需谨慎;颞枕叶皮质厚度与脉络丛体积交互项贡献最大。

要点

  • 泄漏控制下结构MRI判别TRS与TxR的留出集ROC-AUC为0.57,判别能力有限。
  • 全数据集协调分析ROC-AUC为0.60,但因数据泄漏只能谨慎解读。
  • 颞枕叶皮质厚度与脉络丛体积交互项对模型贡献最大。

核心结论

  • 结构MRI特征或可支持横断面区分难治性精神分裂症与治疗反应性精神分裂症。
  • 不同协调策略间的差异凸显神经影像中泄漏感知预处理的重要性。
  • 需在独立队列中验证这些特征能否促成更早识别治疗抵抗。

研究设计与样本

  • 多中心概念验证研究,纳入加拿大与日本多站点研究的225名参与者(122例TRS、103例TxR)。
  • 采用T1加权MRI经FreeSurfer提取皮质厚度、脑体积、表面积与内在曲率,并进行特征工程生成体积-皮质厚度交互项。
  • 评估投票集成模型,主分析采用泄漏控制的NeuroComBat协调,次要探索性分析采用全数据集协调。
  • 性能以ROC-AUC、F1分数、精确率与召回率评估。

主要发现

  • 泄漏控制分析中投票集成留出集ROC-AUC为0.57、宏F1为0.56,训练交叉验证ROC-AUC为0.715。
  • 全数据集协调分析ROC-AUC为0.60、宏F1为0.62,因泄漏需谨慎解读。
  • 颞枕叶皮质厚度与脉络丛体积交互项对模型性能贡献最大。

临床怎么用

  • 目前结构MRI机器学习判别性能有限,尚不足以单独用于临床识别TRS。
  • 神经影像预处理须重视数据泄漏控制,避免高估模型性能。
  • TRS识别仍应结合序贯抗精神病药试验等临床评估。

局限性

  • 全数据集协调分析存在数据泄漏,结果只能谨慎解读。
  • 研究为概念验证性质,尚需独立队列验证。
  • 原文未报告其他局限性。

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: Treatment-resistant schizophrenia (TRS) affects 20-30% of individuals with schizophrenia, with persistent symptoms, functional impairment, and reduced quality of life. Clinical identification remains dependent on sequential antipsychotic trials despite reported structural brain differences between TRS and treatment-responsive schizophrenia (TxR). This study evaluated whether structural MRI features could discriminate clinically defined TRS from TxR using machine learning. METHODS: A total of 225 participants (122 TRS, 103 TxR) from multi-site studies in Canada and Japan were included. Cortical thickness, brain volume, surface area, and intrinsic curvature were derived from T1-weighted MRI using FreeSurfer, with feature engineering generating volumetric-cortical thickness interaction terms. A voting ensemble was evaluated under a primary leakage-controlled NeuroComBat harmonization and a secondary exploratory full-dataset harmonization. Performance was assessed using ROC-AUC, F1 score, precision, and recall. RESULTS: In the leakage-controlled analysis, the voting ensemble achieved a held-out ROC-AUC of 0.57 and macro F1 of 0.56; training cross-validation yielded ROC-AUC of 0.715. The full-dataset harmonization analysis yielded ROC-AUC of 0.60 and macro F1 of 0.62, interpreted cautiously due to leakage. Temporal-occipital cortical thickness and choroid plexus volume interaction terms contributed most to model performance. CONCLUSION: Structural MRI features may support cross-sectional discrimination of TRS from TxR. The divergence between harmonization strategies highlights the importance of leakage-aware preprocessing in neuroimaging. Validation in independent cohorts is required to establish whether these features contribute to earlier identification of treatment resistance.

来源:Biol Psychiatry,查看原文。版权归原作者所有。

引用

  1. Torres-Carmona E, Graff-Guerrero M, Nakajima S, et al. Machine Learning-Based Discrimination of Treatment-Resistant Schizophrenia Using Structural Brain Imaging: A Multi-Site Proof-of-Concept Study. Biol Psychiatry. 2026. PMID: 42632582. doi:10.1016/j.biopsych.2026.08.009

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。