Early Autism Diagnosis: Machine Learning Models and Their Effectiveness
Abstract
Diagnosis is of utmost importance for timely intervention and support. However, traditional diagnosis methods, which are based on subjective assessment, are delayed. This project explores the role that machine learning techniques might play in enhancing the accuracy and effectiveness of autism spectrum disorder (ASD) detection. Several state-of-the-art classification algorithms were benchmarked using a dataset from Kaggle. Logistic regression, XG Boost, random forest, decision tree, and gradient boosting were taken into consideration. Other performance measures, in terms of accuracy, F1 -score, and precision, were considered. The results showed that XG Boost was the best model, because this one had the most precision and reliability of ASD prediction. The research signifies the potential of artificial intelligence AI and machine learning ML technologies for the betterment of the diagnostic process and provides a robust and timely tool for early detection of ASD. Conclusions and recommendations of the study strongly emphasize the necessity of approaches that integrate multidisciplinary and ethical considerations for responsible translation into clinical practice.