The study focused on the diagnosis of autism spectrum disorder (ASD) in children using artificial intelligence (AI) using explainable methods (XAI) such as SHAP and permutation function (PFI). The research used Decision Tree (DT) and K-Nearest Neighbors (KNN) models on data collected in Saudi Arabia and Egypt. After data cleaning and processing, the KNN model with XAI achieved an accuracy of 97% on the Saudi Arabian dataset and 92% on the Egyptian dataset. This method enables earlier and more accurate diagnosis of ASD, which can lead to better treatment and improvement of the quality of life of children with this disorder. The results confirm the effectiveness of the integration of advanced AI techniques into clinical practice in the field of health care for children with ASD. This study highlights the importance of using artificial intelligence to promote inclusiveness and neurodiversity in society.