Analysis and Detection of Autism Spectrum Disorder Using ML Techniques

Abstract—Diagnosing Autism Spectrum Disorder (ASD) is challenging due to its complexity and the diverse symptoms it presents. In this study, we focus on applying machine learning techniques, specifically the Random Forest algorithm, for identifying ASD. Utilizing a comprehensive dataset that encompasses both behavioral and demographic information, we perform thorough preprocessing, feature selection, and model evaluation. The study examines the Random Forest classifier's effectiveness in differentiating between individuals with and without ASD. The results are encouraging and highlight the algorithm's predictive capabilities. By concentrating solely on this method, we gain insights into its strengths and limitations, which are critical for enhancing ASD diagnostic processes. This research underscores the potential of Random Forest in advancing early ASD detection and improving intervention strategies in clinical practice.