Enhancing Autism Spectrum Disorder Diagnosis Using Machine Learning Techniques

Accurate diagnosis of autism spectrum disorder (ASD) is challenging due to its complex nature and reliance on subjective, time-consuming assessments. This study explores the use of machine learning (ML) algorithms to improve ASD diagnosis accuracy and efficiency. We evaluate multiple ML mod-els, including Random Forest, Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Decision Tree, and Logistic Regression, using datasets that include genetic, behavioral, and demographic data. The aim is to identify patterns associated with ASD and assess the strengths and limitations of each model. The findings suggest that ML algorithms have the potential to revolutionize early ASD detection, offering clinicians more objective tools for timely diagnosis and intervention. Ultimately, this research contributes to advancing our understanding of ASD and supports the development of personalized treatment strategies.