MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202611099454 A) filed by Manipal University Jaipur on August 18, 2026, for An Adaptive Edge Intelligence Framework For Cardiovascular Disease Prediction.
Inventors include Himanshu Singh; and Sunita Singhal.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: The present invention relates to an adaptive edge intelligence framework for cardiovascular disease prediction that enables real-time and computationally efficient prediction on resource-constrained edge devices. The framework acquires physiological and clinical data from sensing devices and clinical data sources, followed by preprocessing comprising missing-value handling, scaling, normalization, and class balancing. A swarm intelligence-based feature selection module employs Harris Hawks Optimization (HHO), Northern Goshawk Optimization (NGO), and Osprey Optimization Algorithm (OOA) to identify a reduced subset of relevant cardiovascular features. A lightweight student prediction model generated through knowledge distillation from a high-capacity teacher model performs local prediction. A confidence estimation module evaluates prediction reliability and selectively invokes cloud-based inference when the confidence falls below a predefined threshold. A confidence-gated adaptive fusion mechanism combines edge and cloud predictions, while SHAP-based explainability provides feature-level interpretation. The framework thereby reduces computational and communication requirements while supporting reliable, interpretable, and real-time cardiovascular disease prediction.
Disclaimer: Curated by HT Syndication.
