Deep-Fusion of Scalogram and Spatio-Temporal EEG Features with Attention Mechanism for Autism Spectrum Disorder Identification.

Researchers developed a computer system that can detect autism by analyzing brain wave patterns recorded through EEG (a non-invasive brain monitoring technique). The system achieved 84% accuracy in identifying autism compared to typical development. This approach could potentially offer an objective way to help with early autism detection, which is important because early intervention improves outcomes. The method analyzes brain activity patterns rather than relying only on behavioural observations.

This study presents a novel deep-learning approach for autism spectrum disorder (ASD) detection using resting-state EEG. The methodology combines spatiotemporal EEG features with scalogram-derived image features, processed through an EfficientNet model enhanced with attention mechanisms. The model achieved 84% accuracy, 82% F1-score, 82% recall and precision, and 0.89 AUC-ROC in distinguishing autistic individuals from healthy controls. The research demonstrates EEG's potential as a non-invasive, objective biomarker for early ASD detection, offering advantages over subjective behavioural assessments.

The attention mechanism captures both spatial and temporal neural patterns, providing direct insights into ASD-related neuronal activity abnormalities.

EEG-based detection could complement traditional diagnostic approaches by providing objective neurophysiological markers. Potential for early screening, especially in young children where behavioural assessment may be challenging. However, clinical validation and integration into diagnostic workflows requires further research before practical implementation.

Sample size not reported in abstract. Study type unclear. Performance metrics need validation in larger, diverse populations. No comparison with existing diagnostic methods provided. Long-term clinical utility and implementation feasibility not addressed.

Autism Spectrum Disorder is a neurodevelopmental condition characterised by social and communication challenges, repetitive behaviours, and sensory sensitivities. Early diagnosis allows for timely intervention, improving quality of life. This study introduces a novel approach to Autism Spectrum Disorder detection using resting-state electroencephalography (EEG), which captures neuronal activity to identify Autism Spectrum Disorder-related abnormalities. Our methodology integrates spatiotemporal EEG features with image-based features extracted from scalograms.

To improve classification performance, we proposed a novel deep-learning pipeline that combined scalogram and EEG signal features to emphasise feature fusion. This fusion was processed through an EfficientNet-based model, enhanced with a Convolutional Block Attention Mechanism to capture comprehensive spatial and temporal representations. The attention module leveraged both channel and spatial attention to refine feature extraction. Our model achieved an accuracy of 84%, with an F1-score of 82%, recall of 82%, precision of 82%, and an AUC-ROC of 0.89, demonstrating the potential of EEG in distinguishing ASD from healthy controls.Clinical relevance-EEG offers a non-invasive, cost-effective, and objective approach to early Autism Spectrum Disorder detection.

Unlike subjective behavioural assessments, it provides direct neural insights, enabling scalable screening, especially in young children. This study enhances the diagnostic accuracy of Autism Spectrum Disorder by integrating single channel scalogram and spatiotemporal-based deep feature fusion with attention mechanism, establishing EEG signatures as a promising biomarker and a valuable clinical tool.