Utilization of Naive Bayes Classifier for Autism Risk Assessment Using Machine Learning

The present work investigates the use of the Naive Bayes classifier for the purpose of autism risk assessment via the implementation of machine learning methodologies. Autism spectrum disorder (ASD) is a multifaceted neurodevelopmental syndrome characterised by a diverse array of symptoms, hence presenting difficulties in promptly identifying and diagnosing the illness. By using a dataset that encompasses a range of variables linked to risk factors for autism, we utilise the Naive Bayes classifier to construct a prediction model. The objective of the model is to categorise people into two distinct groups: those who are deemed to be at risk of Autism Spectrum Disorder (ASD) and those who are not considered to be at risk. The research evaluates the performance of the classifier by using variables such as accuracy, precision, recall, and F1 score. Moreover, the examination of feature significance offers valuable insights into the primary elements that contribute to the decision-making process of the classifier. The findings of this study provide a valuable contribution to the expanding field of using machine learning techniques for the evaluation of autism risk. These results present a promising tool that might be used for early intervention and assistance within clinical environments.