MUMBAI, India, March 13 -- Intellectual Property India has published a patent application (202621011114 A) filed by Symbiosis International, Pune, Maharashtra, on Feb. 2, for 'machine learning based predictive sepsis detection system with explainable ai and automated post-operative health monitoring.'
Inventor(s) include Dr. Pradnya Borkar; Sagarkumar Badhiye; Tanmay Kalinkar; Siddhesh Mawale; and Eavam Margamwar.
The application for the patent was published on March 13, under issue no. 11/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses a machine learning based predictive sepsis detection system (100) with explainable artificial intelligence and automated post-operative health monitoring. The system comprises a patient data input module (110), API request handler (120), data validation unit (130), feature preprocessing engine (140), feature scaling module (150), machine learning inference engine (160) implementing an Enhanced XGBoost classifier, SHAP explanation generation module (170), frontend visualization interface (180), and clinical decision support output module (190). The system is trained on over 200,000 ICU patient records achieving 98.04% accuracy and 0.7447 AUC-ROC with 99.75% specificity for reducing alarm fatigue. The SHAP module provides transparent per-patient explanations identifying key clinical factors including gender, ICU prolonged stay, tachycardia, and temperature patterns. The cloud-deployed architecture achieves prediction latency under 50 milliseconds enabling real-time clinical decision support. The post-operative monitoring module (250) addresses critical care gaps during vulnerable periods following ICU discharge through continuous vital sign tracking and automated alert generation."
Disclaimer: Curated by HT Syndication.
