Autism Spectrum Disorder Detection and Classification Using Machine Learning and Deep Learning Techniques

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that can affect communication, social interaction, behavior, and cognitive development. Early detection of ASD is important because timely intervention can significantly improve an individual's developmental and social outcomes. However, conventional diagnosis mainly depends on clinical observations, behavioral assessments, and expert evaluation, which can be timeconsuming and subjective. This study proposes an intelligent approach for the detection and classification of Autism Spectrum Disorder using Machine Learning (ML) and Deep Learning (DL) techniques. The proposed system processes relevant clinical, behavioral, and demographic features to identify patterns associated with ASD. Various machine learning algorithms, such as Support Vector Machine, Random Forest, Decision Tree, Logistic Regression, and K-Nearest Neighbors, can be employed for comparative analysis, while deep learning models are used to automatically learn complex feature representations and improve classification performance. The models are evaluated using performance measures such as accuracy, precision, recall, F1-score, and confusion matrix. The proposed approach aims to provide an efficient, reliable, and automated method for ASD screening and classification, reducing dependence on manual assessment and supporting healthcare professionals in early decision-making. The integration of ML and DL techniques can enhance prediction accuracy and provide a scalable framework for computer-assisted ASD detection.