Effective Prediction of Autism Disease using Data Mining Techniques

The medical costs associated with autism spectrum disorder (ASD), a neurodevelopmental condition, can be significantly reduced with early identification. However, lengthy wait times and high costs come along with an ASD diagnosis. The cost of autism and the increase in ASD cases globally highlight the urgent need for the development of straightforward screening methods. A short and useful ASD test will soon be available to help healthcare professionals and allow people determine whether a formal clinical diagnosis is required or not. ASD cases are rising globally, necessitating the need for datasets pertaining to behavioral features. Due to the dearth of such datasets, it is difficult to perform in-depth research to improve the efficiency, sensitivity, specificity, and predictive accuracy of the AS D screening technique. There are currently only few diagnostic or screening trials, and the greater part of databases on autism are genetic in origin. A brand-new dataset with twenty characteristics is proposed for adult autism screening. Upcoming study may benefit from this information, particularly when identifying the fundamental components of autism and improving the classification of individuals with ASD. The ten behavioural variables (AQ-10-Adult) and ten personality traits included in this dataset can be used to identify ASD cases from controls, according to behavioural study.