Detection of Autism Spectrum Disorder in Children Using Efficient Pre-Processing and Machine Learning Techniques

Early diagnosis of the brain condition known as autism spectrum disorder (ASD) could significantly reduce the high healthcare costs typically involved with treating ASD. Autism's fiscal toll emphasizes the importance of developing easy and effective detection instruments. Therefore, a quick ASD evaluation is essential to helping healthcare professionals and letting people know if they should seek a formal clinical diagnosis. Currently, there are very few autism datasets related to screening accessible, most of which are based on genetics. To expose critical information about autism screening, this work suggests applying a novel machine learning framework that contains vital characteristics and performing predictive analysis utilising a Support vector machine, logistic regression, K-nearest neighbour, and random forest. The main objective of this study is to develop a system for the early detection of children at risk for autism spectrum disorders (ASD).