MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611107715 A) filed by Maharishi Markandeshwar Deemed To Be University on September 05, 2026, for Machine Learning-Enabled Ai-Guided Biomarkers For Cardiac Risk Stratification.
Inventors include Ritu Aggarwal; and Eshaan Aggarwal.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: An Explainable AI (XAI)-guided machine learning framework is disclosed for precise cardiac risk stratification and automated biomarker discovery. Trained and validated on patient clinical records comprising 13 key attributes (including chest pain type, ST depression, maximum heart rate, blood pressure, cholesterol, and blood sugar), the system classifies patient cardiac risk into low, medium, and high-risk categories. The framework integrates SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) algorithms to rank biomarker feature importance and quantify individual contributions toward patient-specific predictions. Evaluated on clinical samples, the SHAP-integrated model achieves a classification accuracy of 97.45%, an AUC-ROC of 94.25%, a precision of 96.42%, and a sensitivity recall of 95.43%, while LIME achieves an accuracy of 98.55%. A Python-based live graphical user interface (GUI) application processes real-time clinical biomarker inputs—such as troponin, BNP, CRP, and systolic BP—to output risk levels, confidence scores, and critical biomarker alerts, supporting clinicians with interpretable diagnostic decisions
Disclaimer: Curated by HT Syndication.
