Enhancing autism severity prediction: A fusion of convolutional neural networks and random forest model

Abstract

A neurological condition affecting both the brain and behaviour is identified as autism spectrum disorder (ASD). Due to the absence of a reliable medical test for detecting autism, diagnoses rely on historical evidence. Essential in assessing the degree of autism are models like Convolutional Neural Networks (CNNs) and Random Forest (RF). In order to reduce the amount of diagnostic tests required for autism diagnosis, this research work presents a new hybrid model that combines the strengths of RF and CNNs, providing healthcare solutions. It is noteworthy that this model properly predicted the severity of autism with an astounding accuracy rate of 99.15% when applied to historical data gathered from the Kaggle Repository.