Department of Computing Science, University of Alberta, Edmonton, Alberta, Canada; Alberta Machine Intelligence Institute, Edmonton, Alberta, Canada.
Department of Psychiatry, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada; Hotchkiss Brain Institute, Mathison Centre for Mental Health Research and Education, University of Calgary, Calgary, Alberta, Canada.
Neuroimage Clin. 2022;35:103120. doi: 10.1016/j.nicl.2022.103120. Epub 2022 Jul 16.
Many previous intervention studies have used functional magnetic resonance imaging (fMRI) data to predict the antidepressant response of patients with major depressive disorder (MDD); however, practical constraints have limited many of those attempts to small, single centre studies which may not adequately reflect how these models will generalize when used in clinical practice. Not only does the act of collecting data at multiple sites generally increase sample sizes (a critical point in machine learning development) it also generates a more heterogeneous dataset due to systematic differences in scanners at different sites, and geographical differences in patient populations. As part of the Canadian Biomarker Integration Network in Depression (CAN-BIND-1) study, 144 MDD patients from six sites underwent resting state fMRI prior to starting escitalopram treatment, and again two weeks after the start. Here, we consider ways to use machine learning techniques to produce models that can predict response (measured at eight weeks after initiation), based on various parcellations, functional connectivity (FC) metrics, dimensionality reduction algorithms, and base learners, and also whether to use scans from one or both time points. Models that use only baseline (pre-treatment) or only week 2 (early-response) whole-brain FC features consistently failed to perform significantly better than default models. Utilizing the change in FC between these two time points, however, yielded significant results, with the best performing analytical pipeline achieving 69.6% (SD 10.8) accuracy. These results appear contrary to findings from many smaller single-site studies, which report substantially higher predictive accuracies from models trained on only baseline resting state FC features, suggesting these models may not generalize well beyond data used for development. Further, these results indicate the potential value of collecting data both before and shortly after treatment initiation.
许多先前的干预研究使用功能磁共振成像（fMRI）数据来预测重度抑郁症（MDD）患者的抗抑郁反应；然而，实际限制使得许多尝试仅限于小的单一中心研究，这些研究可能无法充分反映这些模型在临床实践中使用时的概括程度。在多个地点收集数据不仅通常会增加样本量（这是机器学习发展的关键点），而且由于不同地点扫描仪的系统差异以及患者群体的地理差异，还会生成更异构的数据集。作为加拿大抑郁症生物标志物综合网络（CAN-BIND-1）研究的一部分，来自六个地点的 144 名 MDD 患者在开始依他普仑治疗之前和开始后两周进行了静息状态 fMRI。在这里，我们考虑使用机器学习技术来产生模型的方法，这些模型可以根据各种分割、功能连接（FC）指标、降维算法和基础学习者，以及是否使用一个或两个时间点的扫描，来预测反应（在开始后八周测量）。仅使用基线（治疗前）或仅第 2 周（早期反应）全脑 FC 特征的模型始终未能显著优于默认模型。然而，利用这两个时间点之间的 FC 变化，产生了显著的结果，表现最佳的分析管道达到了 69.6%（SD 10.8）的准确率。这些结果与许多较小的单一地点研究的结果相反，这些研究报告仅从基线静息状态 FC 特征训练的模型具有更高的预测准确性，这表明这些模型可能无法很好地推广到用于开发的数据之外。此外，这些结果表明在治疗开始前后收集数据的潜在价值。
