A hybrid deep learning framework for early autism screening
Abstract Objectives: Early diagnosis of autism spectrum disorder (ASD) remains a significant challenge due to the time-consuming and subjective nature of traditional diagnostic methods. This study proposes a reliability-oriented hybrid deep learning framework that provides a low-cost, scalable, non-invasive, and AI-assisted pre-screening tool for early ASD risk indication and referral support. Methods: The proposed system integrates two independent deep learning architectures: (1) a ResNet18 model optimized with 10-fold cross-validation using static periocular image data, and (2) a multi-CNN facial image classification ensemble combining ResNet50, EfficientNet-B0, and DenseNet121 architectures. The periocular pathway uses the fine-tuned ResNet18 fully connected softmax layer as its decision boundary. The facial pathway uses weighted probabilistic averaging, and the two subsystem outputs are subsequently combined through an OR-based reliability fusion rule. Additionally, explainable artificial intelligence (Grad-CAM) was employed to visualize decision-relevant regions. Results: The static periocular ResNet18 model achieved a sensitivity of 90%, while the multi-CNN facial classification ensemble reached a sensitivity of 87.1% and an AUC of 0.948. Under the conditional-independence assumption, OR-based reliability fusion yielded an analytically estimated system-level sensitivity of 0.9871, corresponding to a joint false-negative probability of approximately 1.29%. Conclusions: The developed hybrid model is positioned as an AI-assisted pre-screening and early-referral support tool, not as a replacement for clinical evaluation. By combining reliability-oriented parallel fusion with explainable AI, the system supports clinical transparency and offers a scalable pathway for early ASD risk indication.