Predicting Autism Spectrum Disorder Based On Gender Using Machine Learning Techniques

Abstract

Autism is a set of complicated developmental disorders marked by social skills impairments, communication difficulties (verbal and nonverbal), and recurring behavior. Autistic children are frequently alienated as a result of these impairments. Rapid recognition of autism can help to establish a treatment strategy and lessen the burden on sufferers. As a result, effective methods to early diagnosis and treatment for ASD are necessary. The toddler, child, adolescent, and adult screening datasets are collected in this study and separated according to gender (male and female). By using random oversampling (ROS), these datasets are balanced. Next, different classifiers are applied to both the primary and balanced datasets. The MLP classifier produced the best results, and the hyperparameter for it was tuned to improve autism identification rate. However, the experimental outcome for the female dataset is better than the male dataset. The shapely adaptive explanation (SHAP) method is also employed to assess the significant features of male and female.