Published Paper Details:

Autism Spectrum Disorder (ASD) diagnosis has experienced a remarkable evolution with the integration of Artificial Intelligence (AI) and data-driven healthcare analytics. This paper presents an AI-based diagnostic framework that leverages behavioral data, demographic attributes, and machine learning algorithms to predict the likelihood of ASD in children, adolescents, and adults. The research highlights the methodology, experimental design, and comparative analysis of multiple models including Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), and Convolutional Neural Network (CNN). The proposed system provides accurate and early detection of ASD symptoms using non-clinical datasets from the UCI repository, ensuring reliable predictions for healthcare practitioners. The framework integrates intelligent data preprocessing and deep learning layers to enhance classification accuracy and minimize diagnostic errors. A cloud-based implementation and interactive dashboard improve accessibility, scalability, and usability for researchers, caregivers, and medical professionals across diverse regions.