The study of the 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.

OBJECTIVE

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.

METHODS

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.

RESULTS

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.

CONCLUSIONS

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.