Leveraging AI-Driven Neuroimaging Biomarkers for Early Detection and Social Function Prediction in Autism Spectrum Disorders. A Systematic Review

This systematic review examines artificial intelligence (AI) applications in neuroimaging for autism spectrum disorder (ASD), addressing the critical need for objective biomarkers that could enable earlier detection and more accurate prediction of developmental outcomes. Methods: Following PRISMA guidelines, we conducted a comprehensive literature search across eight databases, yielding 146 studies from an initial 1,872 records. These studies were systematically analyzed to address key questions regarding AI-neuroimaging approaches in ASD detection and prognosis. Results: Neuroimaging combined with AI algorithms demonstrated significant potential for early ASD detection, with electroencephalography (EEG) showing promise. Machine learning classifiers achieved high diagnostic accuracy (85-99%) using features derived from neural oscillatory patterns, connectivity measures, and signal complexity metrics. Studies of infant populations identified the 9–12-month developmental window as critical for biomarker detection and preceding behavioral symptoms. Multimodal approaches integrating various imaging techniques substantially enhanced predictive capabilities, while longitudinal analyses showed potential for tracking developmental trajectories and treatment response. Conclusions: AI-driven neuroimaging biomarkers represent a promising frontier in ASD research, potentially enabling detection before behavioral symptoms manifest and providing objective measures of intervention efficacy. While technical and methodological challenges remain, advancements in standardization, diverse sampling, and clinical validation could facilitate translation into practice, ultimately supporting earlier intervention during critical developmental periods and improving outcomes for individuals with ASD.