MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202641125827 A) filed by Srm Institute Of Science And Technology, Ramapuram Campus; and Easwari Engineering College on October 22, 2026, for Neurofusion Adaptive Temporal Framework For Eeg-Based Prognosis Prediction In Moderate Traumatic Brain Injury.
Inventors include Dr. S. Sridevi; Mrs. J. Arthy; and Dr. N. Suganthi.
The application for the patent was published on October 30, 2026, under issue no. 44/2026.
Abstract: ABSTRACT: Traumatic Brain Injury (TBI), particularly moderate TBI (moTBI), presents significant challenges in early prognosis due to heterogeneous recovery patterns and subtle functional brain abnormalities that may not be adequately captured by conventional clinical scores and neuroimaging. Existing EEG-based machine learning and deep learning approaches often depend on handcrafted features or standalone architectures such as CNN and LSTM, with limitations including class imbalance, limited generalization, binary outcome prediction, noise sensitivity, and inadequate validation across independent datasets. To address these limitations, the proposed invention introduces a NeuroFusion Adaptive Temporal Framework, a hybrid EEG-based deep ensemble system for automated prognosis prediction in moderate TBI. The framework integrates Self-Attention Temporal Encoding, Dual-Channel Residual Bidirectional LSTM layers, Gradient-Weighted Adaptive Boosting, and an Adaptive Gradient-Boosted Meta-Classifier to learn salient temporal EEG patterns and improve classification robustness. A Stratified Bootstrap with Synthetic Minority Oversampling Technique (SMOTE) is employed to address class imbalance while reducing sampling bias. Ensemble parameters are optimized using Adaptive Moment Estimation with cosine annealing scheduling to achieve stable convergence and improved generalization. The system provides rapid, objective, and automated EEG-based prognosis estimation, with potential real-time application in neurocritical care units for early therapeutic decision-making, intensive-care resource prioritization and rehabilitation planning.
Disclaimer: Curated by HT Syndication.
