结构MRI多站点机器学习识别双相障碍
该研究基于ENIGMA联盟13个站点853例双相障碍患者和2167名对照的结构MRI数据,使用支持向量机进行个体分类。汇总受试者水平分析准确率最高达65.23%(95%CI 63.47-67.00),ROC-AUC为71.49%,低于80%临床相关阈值但结果具有前景。
要点
- 汇总多站点数据分类准确率65.23%,未达80%临床阈值。
- 各站点单独准确率45.23%~81.07%,留一站交叉验证58.67%。
- 抗惊厥药治疗和年龄与正确分类几率增加相关。
核心结论
- 基于区域神经结构测量,在多站点生态效度样本中双相障碍分类准确率最高为65.23%。
- 该准确率虽低于80%临床相关阈值,但结果具有前景并提供公平现实的估计。
- 不同样本中的显著分类基于合理且相似的神经解剖特征。
研究设计与样本
- 研究纳入ENIGMA联盟13个队列的853例双相障碍患者和2167名对照。
- 对MRI区域皮层厚度、表面积和皮层下体积数据应用支持向量机进行机器学习分类。
主要发现
- 各站点单独准确率范围为45.23%至81.07%。
- 汇总受试者水平分析准确率最高为65.23%(95%CI 63.47-67.00),ROC-AUC为71.49%(95%CI 69.39-73.59)。
- 留一站交叉验证准确率为58.67%(95%CI 56.70-60.63)。
- 各站点准确率的荟萃分析未提供高于随机水平的结果。
- 表现最佳站点与汇总数据集中贡献于双相障碍识别的脑区高度一致(Cohen's Kappa=0.83,95%CI 0.829-0.831)。
关键数值与推荐
- 汇总受试者水平分析准确率65.23%(95%CI 63.47-67.00),ROC-AUC 71.49%(95%CI 69.39-73.59)。
- 留一站交叉验证准确率58.67%(95%CI 56.70-60.63)。
- 各站点单独准确率范围45.23%~81.07%。
- 表现最佳站点与汇总数据集贡献脑区一致性Cohen's Kappa=0.83(95%CI 0.829-0.831)。
临床怎么用
- 目前基于结构MRI的机器学习分类准确率未达临床诊断阈值,暂不能替代临床评估。
- 抗惊厥药治疗和年龄影响分类正确几率,临床解读结果时需考虑这些因素。
局限性
- 分类准确率未达到80%的临床相关阈值。
- 各站点准确率的荟萃分析未提供高于随机水平的结果。
- 未来多站点研究应转向共享原始或体素水平神经影像数据。
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
Bipolar disorders (BDs) are among the leading causes of morbidity and disability. Objective biological markers, such as those based on brain imaging, could aid in clinical management of BD. Machine learning (ML) brings neuroimaging analyses to individual subject level and may potentially allow for their diagnostic use. However, fair and optimal application of ML requires large, multi-site datasets. We applied ML (support vector machines) to MRI data (regional cortical thickness, surface area, subcortical volumes) from 853 BD and 2167 control participants from 13 cohorts in the ENIGMA consortium. We attempted to differentiate BD from control participants, investigated different data handling strategies and studied the neuroimaging/clinical features most important for classification. Individual site accuracies ranged from 45.23% to 81.07%. Aggregate subject-level analyses yielded the highest accuracy (65.23%, 95% CI = 63.47-67.00, ROC-AUC = 71.49%, 95% CI = 69.39-73.59), followed by leave-one-site-out cross-validation (accuracy = 58.67%, 95% CI = 56.70-60.63). Meta-analysis of individual site accuracies did not provide above chance results. There was substantial agreement between the regions that contributed to identification of BD participants in the best performing site and in the aggregate dataset (Cohen's Kappa = 0.83, 95% CI = 0.829-0.831). Treatment with anticonvulsants and age were associated with greater odds of correct classification. Although short of the 80% clinically relevant accuracy threshold, the results are promising and provide a fair and realistic estimate of classification performance, which can be achieved in a large, ecologically valid, multi-site sample of BD participants based on regional neurostructural measures. Furthermore, the significant classification in different samples was based on plausible and similar neuroanatomical features. Future multi-site studies should move towards sharing of raw/voxelwise neuroimaging data.
引用
- Nunes A, Schnack HG, Ching CRK, et al. Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group. Mol Psychiatry. 2018. PMID: 30171211. doi:10.1038/s41380-018-0228-9
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。