MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641080568 A) filed by Narsimha Reddy Engineering College Nrcm on June 30, 2026, for Explainable Ai-Driven Clinical Decision Support System For Early Sepsis Prediction In Smart Hospitals.
Inventors include Dr Shoban Mude; Dr. M. Ashok Kumar; Dandu Srinivas; V. Pradeep Kumar; Dhananjaya; and Dyavarasetty Sunitha.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: An explainable edge-based clinical decision support system for early prediction of sepsis in smart hospitals is disclosed. The system comprises a physiological sensor module (110), analog front-end circuit (111), analog-to-digital conversion module (112), edge computing unit (120) including volatile memory (121) and non-volatile memory (122), feature extraction engine (130), prediction engine (140), explainability engine (150), clinician interface module (160), and secure communication interface (170). Multi- parameter physiological signals are acquired, conditioned, digitized, and buffered using a sliding window framework. Structured feature vectors are generated and processed by a gradient-boosted decision ensemble to compute a sepsis probability score. A tree- based Shapley attribution mechanism generates real-time feature contribution values mapped to physiological signal sources. All computations are executed locally within a deterministic processing cycle below 500 milliseconds, enabling interpretable early sepsis alert generation with reduced false alarm rate and minimized network latency.
Disclaimer: Curated by HT Syndication.
