论文标题
使用机器学习在皮质和皮质下措施上的机器学习对重度抑郁症的多站点基准分类
Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures
论文作者
论文摘要
机器学习（ML）技术因其对神经精神疾病的潜力而在神经影像领域中广受欢迎。但是，现有算法的诊断预测能力受到小样本量，缺乏代表性，数据泄漏和/或过度拟合的限制。在这里，我们以迄今为止最大的多站点样本量（n = 5,356）克服了这些局限性，以提供可推广的ML分类基准（MDD）。使用FreeSurfer中标准化的谜分析管道中的大脑测量方法，我们能够以大约62％的平衡精度对MDD与健康对照组（HC）进行分类，但是当使用战斗平衡准确度和协调数据时，降至约52％。根据发病年龄，抗抑郁药的使用，发作数量和性别，分层组也观察到了相似的结果。未来的研究结合了较高的大脑成像/表型特征和/或使用更先进的机器和深度学习方法可能会实现更多令人鼓舞的前景。
Machine learning (ML) techniques have gained popularity in the neuroimaging field due to their potential for classifying neuropsychiatric disorders. However, the diagnostic predictive power of the existing algorithms has been limited by small sample sizes, lack of representativeness, data leakage, and/or overfitting. Here, we overcome these limitations with the largest multi-site sample size to date (n=5,356) to provide a generalizable ML classification benchmark of major depressive disorder (MDD). Using brain measures from standardized ENIGMA analysis pipelines in FreeSurfer, we were able to classify MDD vs healthy controls (HC) with around 62% balanced accuracy, but when harmonizing the data using ComBat balanced accuracy dropped to approximately 52%. Similar results were observed in stratified groups according to age of onset, antidepressant use, number of episodes and sex. Future studies incorporating higher dimensional brain imaging/phenotype features, and/or using more advanced machine and deep learning methods may achieve more encouraging prospects.
