Game Based Therapy for Autism Spectrum Disorder (ASD) Childrens Using Machine Learning

Game-based therapy is an emerging intervention for children's with Autism Spectrum Disorder (ASD), utilizing engaging nature of games to improve social, communication, and cognitive skills. Findings show significant improvements in engagement, social interactions, and cognitive functions. In this research evaluate the effectiveness of different machine learning algorithms to analyze therapeutic outcomes by using mobile games. The Random Forest Classifier achieved an accuracy of 91%, outperforming Artificial Neural Networks (ANN), which had 88% accuracy, and K-Nearest Neighbors (KNN), which had 85% accuracy. Based on these results, Random Forest (RF) Classifier is selected for further integration into the game-based therapy platform. The results indicate that game-based therapy, supported by the Random Forest Classifier, is a valuable complement to traditional therapies for children with ASD. Such a tool can monitor the course of the therapy, modify it as needed, and report its results. Additionally, these interactive tools provide personalized feedback, adapt to individual needs, and track progress over time.