Graph-Based Analysis of Electroretinograms for Reducing Computational Complexity and Classifying Neurodevelopmental Disorders

Electroretinogram (ERG) signals show distinctive patterns in neurodevelopmental disorders including autism spectrum disorder (ASD) and attention deficit/hyperactivity disorder (ADHD). Traditional ERG analysis relies primarily on time-domain features, limiting the capture of complex nonlinear relationships. We propose ERG-Graph, a novel graph signal processing approach that transforms ERG signals into graph networks to extract topological features for improved classification. Using 5,838 ERG recordings from 278 subjects across four groups (Control, ADHD, ASD, ASD+ADHD), we applied quantization and k-nearest neighbor graph construction to create ERG-graphs and extracted 25 graph-level features including centrality measures, spectral properties, and connectivity metrics. Seven machine learning algorithms were evaluated with leave-one-subject-out cross-validation, achieving balanced accuracies of 0.77 for ADHD vs. Control and 0.76 for ASD vs. Control using Random Forest, outperforming traditional ERG features. ERG-Graph demonstrates superior performance in multi-class scenarios and captures subtle topological patterns associated with neurodevelopmental conditions, offering a promising advancement in automated ERG-based diagnosis.