Intelligent Autism Disease Prediction System Using Machine Learning

Communication difficulties and repetitive sensory-motor behaviors have a strong hereditary component, although contextual circumstances may also play a role. Certain genetic and neurological risk factors have been established via research, but there is still more to learn about this disease. This study uses Weka, Naive Bayes, and decision tree algorithms to diagnose and forecast autism spectrum disorder. This research study makes use of a dataset from the UCI repository. This study additionally investigates the genetic traits, external factors, and anomalies in brain connections for detecting autism. Autism does not have an acknowledged cure, but early identification and intervention can improve outcomes. The survey of the research examines several models for predicting autism spectrum disorders, including one that combines behavioral indicators and machine learning techniques like decision tree and support vector machine.