DETECTING AUTISM USING ARTIFICIAL INTELLIGENCE ALGORITHMS

Abstract

Autism Spectrum Disorder is a complex neurodevelopmental condition characterized by variability in social communication, interaction, and behavioral patterns. Accurate and timely identification of autism remains a persistent challenge due to the heterogeneous nature of its symptoms and the reliance on subjective observational assessments. In recent years, artificial intelligence has gained increasing attention as a potential tool for supporting diagnostic processes in developmental disorders. This study explores the application of artificial intelligence algorithms in the detection of autism through the analysis of behavioral and interaction-based data. By employing machine learning and deep learning approaches, the research examines how computational models can identify latent developmental patterns that are not easily observable through traditional assessment methods. The findings indicate that artificial intelligence systems demonstrate strong potential in recognizing consistent behavioral structures associated with autism spectrum disorder. The results further suggest that multimodal data integration enhances diagnostic coherence and contributes to more stable screening outcomes. While artificial intelligence does not replace clinical evaluation, its use as a supportive analytical instrument may improve early screening efficiency and assist professionals in decision-making processes. The study underscores the importance of ethically guided implementation and interdisciplinary collaboration in advancing technology-assisted autism detection.