Reiter Maya A, Jahedi Afrooz, Jac Fredo A R, Fishman Inna, Bailey Barbara, Müller Ralph-Axel
Brain Development Imaging Lab (BDIL), Psychology, San Diego State University (SDSU), 6363 Alvarado Ct. Suite 200, San Diego, CA 92120, USA.
Joint Doctoral Program in Clinical Psychology, San Diego State University/UC San Diego, San Diego, CA, USA.
Neural Comput Appl. 2021 Apr;33(8):3299-3310. doi: 10.1007/s00521-020-05193-y. Epub 2020 Jul 24.
Autism spectrum disorders (ASDs) are heterogeneous neurodevelopmental conditions. In fMRI studies, including most machine learning studies seeking to distinguish ASD from typical developing (TD) samples, cohorts differing in gender and symptom severity composition are often treated statistically as one "ASD group". Using resting-state functional connectivity (FC) data, we implemented random forest to build diagnostic classifiers in 4 ASD samples including a total of 656 participants (N = 306, N = 350, ages 6-18). Groups were manipulated to titrate heterogeneity of gender and symptom severity and partially overlapped. Each sample differed on inclusionary criteria: (1) all genders, unrestricted severity range; (2) only male participants, unrestricted severity; (3) all genders, higher severity only; (4) only male participants, higher severity. Each set consisted of 200 participants per group (ASD, TD; matched on age and head motion), 160 for training and 40 for validation. FMRI time series from 237 regions of interest (ROIs) were Pearson correlated in a 237×237 FC matrix and classifiers were built using random forest in training samples. Classification accuracies in validation samples were 62.5%, 65%, 70% and 73.75%, respectively for samples 1-4. Connectivity within cingulo-opercular task control (COTC) network, and between COTC ROIs and default mode and dorsal attention network contributed overall most informative features, but features differed across sets. Findings suggest that diagnostic classifiers vary depending on ASD sample composition. Specifically, greater homogeneity of samples regarding gender and symptom severity enhances classifier performance. However, given the true heterogeneity of ASDs, performance metrics alone may not adequately reflect classifier utility.
自闭症谱系障碍（ASD）是一种异质性神经发育疾病。在功能磁共振成像（fMRI）研究中，包括大多数旨在区分ASD与典型发育（TD）样本的机器学习研究，通常将性别和症状严重程度构成不同的队列在统计学上视为一个“ASD组”。利用静息态功能连接（FC）数据，我们在4个ASD样本中实施随机森林算法来构建诊断分类器，这些样本共有656名参与者（N = 306，N = 350，年龄6 - 18岁）。对各样本进行了处理，以调节性别和症状严重程度的异质性，且样本之间部分重叠。每个样本在纳入标准上有所不同：（1）所有性别，严重程度范围不受限制；（2）仅男性参与者，严重程度不受限制；（3）所有性别，仅严重程度较高者；（4）仅男性参与者，严重程度较高者。每组包含每组200名参与者（ASD、TD；年龄和头部运动相匹配），160名用于训练，40名用于验证。来自237个感兴趣区域（ROI）的fMRI时间序列在一个237×237的FC矩阵中进行皮尔逊相关分析，并在训练样本中使用随机森林算法构建分类器。对于样本1 - 4，验证样本中的分类准确率分别为62.5%、65%、70%和73.75%。扣带回 - 脑岛任务控制（COTC）网络内以及COTC ROI与默认模式和背侧注意网络之间的连接总体上贡献了最具信息性的特征，但不同样本集的特征有所不同。研究结果表明，诊断分类器因ASD样本构成的不同而有所差异。具体而言，样本在性别和症状严重程度方面更高的同质性会提高分类器的性能。然而，鉴于ASD的真正异质性，仅性能指标可能无法充分反映分类器的效用。
