MUMBAI, India, Feb. 6 -- Intellectual Property India has published a patent application (202511131885 A) filed by Chandigarh University, Mohali, Punjab, on Dec. 26, 2025, for 'wearable ai system for real-time epileptic seizure detection using multi-modal sensor fusion.'
Inventor(s) include Chinmaya Nanda Panda; Pawan Kumar Pandey; Deeksha Sonal; Aditya Tiwari; Aarav Vaish; and Armaan Preet Singh.
The application for the patent was published on Feb. 6, under issue no. 06/2026.
According to the abstract released by the Intellectual Property India: "The present invention provides a wearable, real-time seizure detection and prediction system that integrates multi-modal physiological sensing with edge-based artificial intelligence. The device combines electrodermal activity, accelerometry, heart rate variability, electromyography, and optional EEG sensors to accurately identify tonic-clonic, focal, and absence seizures while minimizing false positives using adaptive thresholds and motion-artifact rejection. A lightweight CNN-LSTM model enables sub-second, on-device analysis without cloud dependency, and federated learning allows personalized pattern recognition while preserving patient privacy. The system further incorporates pre-seizure prediction through autonomic biomarkers and delivers closed-loop intervention via haptic feedback or transcutaneous vagus nerve stimulation to potentially disrupt early seizure activity. GPS-enabled emergency alerts and a HIPAA-compliant cloud dashboard support caregiver notification and long-term clinical monitoring. This invention advances epilepsy management by combining detection, prediction, and intervention in a single, power-efficient wearable platform."
Disclaimer: Curated by HT Syndication.
