Detection and Analysis of Autism Spectrum Disorder Using Machine Learning

This project investigates the application of machine learning methods to behavioral and clinical data-driven early identification of autism spectrum disorder (ASD). The suggested model uses support vector machines (SVM), k-NN, and random forest algorithms among others for classification. Principal Component Analysis (PCA) and Recursive Feature Elimination (RFE) are two feature extraction techniques used to choose the most pertinent characteristics. With the help of datasets with diagnostic data, the model is trained and verified, and it successfully detects ASD with a high sensitivity and specificity. This method helps with prompt intervention and better outcomes for people with ASD by providing a non-invasive, affordable option for early diagnosis.