Optimized Machine Learning Classification Approaches (Omlc-Asd) For Early Detection of Autism Spectrum Disorder

Abstract

Autism spectrum disorder is a neurological condition that impairs social interaction and communication because it alters how people perceive and relate to one another. ASD screening refers to the process of identifying suspected autistic features in individuals through exams administered by a physician, carer, or parent. This study evaluates the performance of various machine learning algorithms and pre-processing strategies to categorise medical datasets used to identify early signs of autism in children and adults. Many earlier studies in this field use sophisticated pre-processing and machine learning methods to perform accurate categorization. Yet, this experiment shows that a range of classifier algorithms, such as logistic regression, KNN, and Random Forest, can produce results that are comparable to the state-of-the-art.