Maya-Vaidya P1: A Neuromorphic Dual-Head Spiking Neural Network for Multimodal Pain Classification and Severity Estimation with BCM Chronification Tracking

Maya-Vaidya P1 introduces a dual-head spiking neural network (SNN) designed to simultaneously classify pain type and estimate pain severity from physiological signals, addressing the need for neurobiologically grounded computational models of clinical pain that can generalise across individuals. The architecture combines leaky integrate-and-fire (LIF) neurons with a BCM ChronificationTracker — a novel module that models the acute-to-chronic pain transition through a sliding modification threshold — trained and evaluated using rigorous Leave-One-Subject-Out cross-validation across 86 participants drawn from the PhysioPain dataset. Across all 86 independent LOSO folds, the model achieved a cross-subject GEV…