Institute of Electrical Engineering, Yanshan University, Qinhuangdao, China.
School of Information Science & Engineering, Yanshan University, Qinhuangdao, China.
J Clin Neurosci. 2020 Nov;81:54-60. doi: 10.1016/j.jocn.2020.09.039. Epub 2020 Sep 28.
Autism spectrum disorder (ASD) is a heterogeneous neurodevelopmental disorder which affects the developmental trajectory in several behavioral domains, including impairments of social communication and stereotyped behavior. Unlike typically developing children who can successfully obtain the detailed facial information to decode the mental status with ease, autistic children cannot infer instant feelings and thoughts of other people due to their abnormal face processing. In the present study, we tested the other-race face, the own-race strange face and the own-race familiar face as stimuli material to explore whether ASD children would display different face fixation patterns for the different types of face compared to TD children. We used a machine learning approach based on eye tracking data to classify autistic children and TD children.
Seventy-seven low-functioning autistic children and eighty typically developing children were recruited. They were required to watch a series face photos in a random order. According to the coordinate frequency distribution, the K-means clustering algorithm divided the image into 64 Area Of Interest (AOI) and selected the features using the minimal redundancy and maximal relevance (mRMR) algorithm. The Support Vector Machine (SVM) was used to classify to determine whether the scan patterns of different faces can be used to identify ASD, and to evaluate classification models from both accuracy and reliability.
The results showed that the maximum classification accuracy was 72.50% (AUC = 0.77) when 32 of the 64 features of unfamiliar other-race faces were selected; the maximum classification accuracy was 70.63% (AUC = 0.76) when 18 features of own-race strange faces were selected; the maximum classification accuracy was 78.33% (AUC = 0.84) when 48 features of own-race familiar faces were selected; The classification accuracy of combining three types of faces reached a maximum of 84.17% and AUC = 0.89 when 120 features were selected.
There are some differences between low-functioning autistic children and typically developing children in the processing of the own-race and other-race faces by the machine learning approach, which might be a useful tool for classifying low-functioning autistic children and TD children.
自闭症谱系障碍（ASD）是一种异质性神经发育障碍，会影响包括社交沟通和刻板行为在内的多个行为领域的发展轨迹。与能够轻松地从详细面部信息中解码出他人心理状态的正常发育儿童不同，自闭症儿童由于面部处理异常，无法推断出他人的即时感受和想法。在本研究中，我们以异种族面孔、本种族陌生面孔和本种族熟悉面孔作为刺激材料，来探索 ASD 儿童与 TD 儿童相比，是否会对面孔的不同类型表现出不同的注视模式。我们使用基于眼动追踪数据的机器学习方法来对自闭症儿童和 TD 儿童进行分类。
共招募了 77 名低功能自闭症儿童和 80 名正常发育儿童。他们被要求随机观看一系列面孔照片。根据坐标频率分布，K-means 聚类算法将图像分为 64 个感兴趣区域（AOI），并使用最小冗余最大相关性（mRMR）算法选择特征。支持向量机（SVM）用于分类，以确定不同面孔的扫描模式是否可用于识别 ASD，并从准确性和可靠性两个方面评估分类模型。
结果显示，当选择 32 个不熟悉的异种族面孔的 64 个特征中的 32 个时，最大分类准确率为 72.50%（AUC=0.77）；当选择 18 个本族陌生面孔的 64 个特征中的 18 个时，最大分类准确率为 70.63%（AUC=0.76）；当选择 48 个本族熟悉面孔的 64 个特征中的 48 个时，最大分类准确率为 78.33%（AUC=0.84）；当选择三种面孔的 120 个特征时，分类准确率达到最高的 84.17%，AUC=0.89。
通过机器学习方法，低功能自闭症儿童与正常发育儿童在处理本族和异族面孔时存在一些差异，这可能是一种有用的工具，可用于对低功能自闭症儿童和 TD 儿童进行分类。
