Multimodal physiological monitoring in augmented reality teaching environments for children with neurodevelopmental disorders

Abstract

This study investigates the integration of augmented reality (AR) teaching environments with multimodal physiological monitoring for children with neurodevelopmental disorders. We collected EEG, ECG, and eye-tracking data from 115 children (ASD n = 45, ADHD n = 38, SLD n = 32) during AR-enhanced learning tasks. The multimodal fusion approach achieved 89.3% classification accuracy in identifying disorder-specific patterns. Key biomarkers included frontal theta power variations (p < 0.001), heart rate variability indices (LF/HF ratio), and fixation duration patterns. AR environments reduced cognitive load by 27% compared to traditional settings while maintaining engagement levels. Personalized intervention based on real-time physiological feedback improved attention performance by 31.2% and social interaction scores by 24.8% over 12 months. These findings demonstrate the efficacy of combining AR technology with physiological monitoring for adaptive special education.