Published Paper Details:

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by challenges in communication, behavior, and social interaction. Early detection of ASD is crucial for effective intervention, yet access to diagnostic tools remains limited in many regions. This study explores the application of machine learning techniques to develop a predictive model for ASD screening. Using a publicly available dataset, we preprocess and analyze features such as age, gender, and behavioral scores to train multiple algorithms, including Logistic Regression, Decision Tree, Support Vector Machine (SVM), and Random Forest. The Random Forest algorithm demonstrated the highest accuracy, precision, and recall, achieving an Area Under the Curve (AUC) of approximately 1.0. A user-friendly web interface was developed using Streamlit to facilitate accessibility. Our results highlight the potential of machine learning as a preliminary screening tool for ASD, particularly in resource-constrained settings.