A Machine Learning Model for Timely Autism Spectrum Disorder Detection

Autism Spectrum Disorder (ASD) presents educational and social challenges, impacting judgment and interpersonal interactions. This research introduces a novel approach to ASD diagnosis using Python-based machine learning. Analyzing a dataset of 705 records and 21 features, we employed the Haphazard Forest Classifier and Resolution Shrub Classifier to identify attributes indicative of ASD, such as auditory and visual perception, cognitive abilities, demographics, and medical history. Both classifiers achieved high accuracy, with the Haphazard Forest Classifier scoring 100% in training and 99% in testing, and the Resolution Shrub Classifier achieving 100% in training and 96% in testing. Our model demonstrates the efficacy of machine intelligence in healthcare, providing comprehensive analysis. The findings contribute to early ASD identification and support for affected individuals. Notably, the dataset encompasses a wide range of attributes, ensuring robust analysis. The research highlights the potential of machine learning in enhancing ASD diagnosis, advancing understanding of complex neurodevelopment disorders in healthcare. The fair evaluations made in this study help identify ASD early, allowing for timely help and support for those affected. This highlights how machine intelligence in healthcare can effectively address neurodevelopment disorders.