Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder mainly showed atypical social interaction, communication, and restricted, repetitive patterns of behavior, interests and activities. Now clinic diagnosis of ASD is mostly based on psychological evaluation, clinical observation and medical history. All these behavioral indexes could not avoid defects such as subjectivity and reporter-dependency. Therefore researchers devoted themselves to seek relatively stable biomarkers of ASD as supplementary diagnostic evidence. The goal of present study is to generate relatively stable predictive model based on anatomical brain features by using machine learning technique. Forty-six ASD children and thirty-nine development delay children aged from 18 to 37 months were evolved in. As a result, the predictive model generated by regional average cortical thickness of regions with top 20 highest importance of random forest classifier showed best diagnostic performance. And random forest was proved to be the optimal approach for neuroimaging data mining in small size set and thickness-based classification outperformed volume-based classification and surface area-based classification in ASD. The brain regions selected by the models might attract attention and the idea of considering biomarkers as a supplementary evidence of ASD diagnosis worth exploring. Autism Res 2017, 0: 000-000. © 2016 International Society for Autism Research, Wiley Periodicals, Inc. Autism Res 2017, 10: 620-630. © 2016 International Society for Autism Research, Wiley Periodicals, Inc.
Keywords: autism spectrum disorder; cortical thickness; magnetic resonance imaging; predictive model; toddler.
© 2016 International Society for Autism Research, Wiley Periodicals, Inc.