AUTHOR=Aldhyani Theyazn H. H. , Al-Nefaie Abdullah H. TITLE=DASD- diagnosing autism spectrum disorder based on stereotypical hand-flapping movements using multi-stream neural networks and attention mechanisms JOURNAL=Frontiers in Physiology VOLUME=Volume 16 - 2025 YEAR=2025 URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2025.1593965 DOI=10.3389/fphys.2025.1593965 ISSN=1664-042X ABSTRACT=IntroductionThe early detection and diagnosis of autism spectrum disorder (ASD) remain critical challenges in developmental healthcare, with traditional diagnostic methods relying heavily on subjective clinical observations.MethodsIn this paper, we introduce an innovative multi-stream framework that seamlessly integrates three state-of-the-art convolutional neural networks, namely, EfficientNetV2B0, ResNet50V2, DenseNet121, and Multi-Stream models to analyze stereotypical movements, particularly hand-flapping behaviors automatically. Our architecture incorporates sophisticated spatial and temporal attention mechanisms enhanced by hierarchical feature fusion and adaptive temporal sampling techniques designed to extract characteristics of ASD related movements across multiple scales. The system includes a custom designed temporal attention module that effectively captures the rhythmic nature of hand-flapping behaviors. The spatial attention mechanisms method was used to enhance the proposed models by focusing on the movement characteristics of the patients in the video. The experimental validation was conducted using the Self-Stimulatory Behavior Dataset (SSBD), which includes 66 videos.ResultsThe Multi-Stream framework demonstrated exceptional performance, with 96.55% overall accuracy, 100% specificity, and 94.12% sensitivity in terms of hand-flapping detection and an impressive F1 score of 97%.DiscussionThis research can provide healthcare professionals with a reliable, automated tool for early ASD screening that offers objective, quantifiable metrics that complement traditional diagnostic methods.