Abou-Abbas Lina, van Noordt Stefon, Desjardins James A, Cichonski Mike, Elsabbagh Mayada
Montreal Neurological Institute, McGill University, Montreal, QC H3A 2B4, Canada.
Cognitive and Affective Neuroscience Lab, Brock University, St. Catharines, ON L2S 3A1, Canada.
Brain Sci. 2021 Mar 24;11(4):409. doi: 10.3390/brainsci11040409.
Event-related potentials (ERPs) activated by faces and gaze processing are found in individuals with autism spectrum disorder (ASD) in the early stages of their development and may serve as a putative biomarker to supplement behavioral diagnosis. We present a novel approach to the classification of visual ERPs collected from 6-month-old infants using intrinsic mode functions (IMFs) derived from empirical mode decomposition (EMD). Selected features were used as inputs to two machine learning methods (support vector machines and -nearest neighbors (-NN)) using nested cross validation. Different runs were executed for the modelling and classification of the participants in the control and high-risk (HR) groups and the classification of diagnosis outcome within the high-risk group: HR-ASD and HR-noASD. The highest accuracy in the classification of familial risk was 88.44%, achieved using a support vector machine (SVM). A maximum accuracy of 74.00% for classifying infants at risk who go on to develop ASD vs. those who do not was achieved through -NN. IMF-based extracted features were highly effective in classifying infants by risk status, but less effective by diagnostic outcome. Advanced signal analysis of ERPs integrated with machine learning may be considered a first step toward the development of an early biomarker for ASD.
在自闭症谱系障碍（ASD）个体发育的早期阶段，就发现了由面孔和注视处理激活的事件相关电位（ERP），其可能作为一种假定的生物标志物来辅助行为诊断。我们提出了一种新方法，用于对从6个月大婴儿收集的视觉ERP进行分类，该方法使用了从经验模态分解（EMD）中导出的本征模态函数（IMF）。选定的特征被用作两种机器学习方法（支持向量机和k近邻（k-NN））的输入，并采用嵌套交叉验证。针对对照组和高危（HR）组参与者的建模和分类以及高危组内诊断结果（HR-ASD和HR-noASD）的分类执行了不同的运行。使用支持向量机（SVM）在家族风险分类中达到了最高准确率88.44%。通过k-NN对有发展为ASD风险的婴儿与无此风险的婴儿进行分类，最高准确率为74.00%。基于IMF提取的特征在按风险状态对婴儿进行分类方面非常有效，但在按诊断结果分类方面效果较差。将ERP的高级信号分析与机器学习相结合，可被视为朝着开发ASD早期生物标志物迈出的第一步。
