Applying Machine Learning for Autism Risk Evaluation Using a Decision Tree Classification Technique

The present work investigates the use of machine learning methods for evaluating the risk of autism spectrum disorder (ASD) by using a Decision Tree Classifier. Autism, a multifaceted neurodevelopmental disorder, poses distinctive obstacles in the realms of early identification and intervention. Conventional diagnostic approaches often depend on examinations that are both time-consuming and subjective, resulting in the postponement of diagnosis. This study uses a Decision Tree Classifier to examine a large dataset consisting of behavioural and demographic characteristics linked to Autism Spectrum Disorder (ASD). The algorithm undergoes training using a considerable dataset including people both diagnosed with Autism Spectrum Disorder (ASD) and those without ASD access. This training process enables the algorithm to acquire knowledge of patterns and correlations inherent in the dataset’s employment. The objective of this research is to assess the effectiveness of the classifier in properly predicting the likelihood of autism by using input characteristics. The dependability of the model is ensured by the use of stringent cross-validation procedures and statistical measurements to verify the results. The machine learning technique that has been suggested has the capacity to improve early detection procedures, so enabling prompt intervention and assistance for those who are at risk of Autism Spectrum Disorder (ASD).