Maya-Vaidya P3: Simulating Dravet Syndrome In Silico — Vairagya-BCM Inhibitory Collapse in a Paediatric SNN with Cross-Patient Seizure Detection

Maya-Vaidya P3 presents DravetSNN, a spiking neural network simulation of Dravet Syndrome built to model the progressive silencing of inhibitory interneurons that underlies this severe infant-onset epilepsy, trained and evaluated on real paediatric EEG recordings from the CHB-MIT Scalp EEG dataset across three paediatric subjects and sixty total experimental runs. The model encodes SCN1A haploinsufficiency as a conductance deficit applied to its inhibitory (Vairagya) neuron population, and confirms exact inhibitory collapse — Vairagya firing reaching 0.000 at full deficit across all patients and random seeds — while achieving a cross-patient seizure detection AUC of 0.743 ± 0.073 on chb13 and an unsupervised ictal chrono_signal of 0.555 above the 0.5 detection threshold, with flat AUC on chb06 confirming that the model captures phenotype specificity rather than noise. This work is the third entry in the Maya-Vaidya Series and confirms the PAIN_DECAY_RATE empirical constant at 0.002315 across three canonical positions, extending the BCM-derived inhibitory collapse architecture first introduced in Maya-Vaidya P2 into a paediatric disease-simulation context. As part of India's first neuromorphic clinical AI research series, Maya-Vaidya P3 represents a proof-of-concept mechanistic study only and is not a licensed medical device; CHB-MIT subjects carry no confirmed SCN1A genetic status, and all findings are preliminary pending replication on genetically validated cohorts. Series: Part of the Maya-Vaidya Series — neuromorphic AI for clinical pain analysis. India-first. Research prototype only — NOT a licensed medical device. For medical emergencies in India: 112. Links: GitHub Repository (private — to request access: email research@nexuslearninglabs.in with subject Code Access Request — Maya-Vaidya-P3 and your research context) | Interactive Dashboard | FAQ | Full Series Index — venky2099.github.io Nexus Learning Labs, Bengaluru · UDYAM-KR-02-0122422 · BHASKAR IN-0526-9452JSORCID: 0000-0002-3315-7907 · VAIRAGYA_DECAY_RATE = 0.002315 (embedded in all canonical hyperparameters)Canary: MayaNexusVS2026NLL_Bengaluru_Narasimha