Applying Machine Learning and the Gradient Boosting Classification Method for Evaluating the Probability of Autism

This research investigates the use of machine learning, especially the Gradient Boosting Classification (GBC) technique, to evaluate the likelihood of autism. Autism Spectrum Disorder (ASD) is an intricate neurodevelopmental illness that may range in severity, highlighting the need of promptly and accurately diagnosing the disorder to ensure successful management. Conventional diagnostic techniques depend on clinical assessments, which may be subjective and time-consuming. This study used a dataset that includes a wide range of demographic and clinical characteristics to train and fine-tune a Gradient Boosting Classification model. The GBC algorithm is selected because to its capacity to manage intricate connections within data, adjust to non-linear patterns, and provide exceptional forecast accuracy. The research showcases the efficacy of the GBC model in accurately categorising persons with and without autism, yielding encouraging outcomes in terms of sensitivity, specificity, and overall performance metrics. The results indicate and access that machine learning, namely the GBC technique, has the ability to enhance the effectiveness and impartiality of autism diagnosis. This may lead to early intervention methods and better outcomes for persons with autism. Additional investigation and verification are necessary to enhance the model's potential to be applied to a wide range of situations and to incorporate and its effective employment into medical practise. The suggested Gradient Boosting Classifier achieves an accuracy of 93 percent during classification.