Early Detection of Autism Spectrum Disorder Using Clinical and Image-Based Data

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by challenges in social communication and the presence of repetitive behaviors, with symptoms typically emerging in early childhood. Accurate and timely diagnosis is critical for effective intervention, yet traditional diagnostic methods often struggle with the heterogeneous presentation of ASD. This paper presents a comprehensive web-based system that integrates both structured clinical behavioral data and image analysis to enhance autism prediction. Machine learning algorithms, including Random Forest, Support Vector Machine, and Decision Tree classifiers, are employed to analyze behavioral assessments and clinical history, while a deep learning-based Convolutional Neural Network processes image data for alternative detection pathways. The platform offers an interactive interface, allowing users to input clinical data or upload images for risk evaluation, and provides immediate, interpretable results. Additionally, the system includes educational resources and administrative tools for user management. By combining conventional machine learning with state-of-the-art deep learning models, this approach delivers a robust, multi-dimensional solution for early ASD screening, supporting timely intervention and improved outcomes for affected individuals and their familie