MUMBAI, India, Aug. 17 -- Intellectual Property India has published a patent application (202641095181 A) filed by Bangalore Technological Institute on August 06, 2026, for An Explainable Artificial Intelligence-Based System For Early Prediction And Risk Assessment Of Heart Attack.

Inventors include D. Jerline Sheebha Anni; Kalpana M; Chethan Gowda M. B; Mithun R; and Harsha Cm.

The application for the patent was published on August 14, 2026, under issue no. 33/2026.

Abstract: The present invention discloses a computer-implemented Heart Attack Risk Prediction System for the early prediction and risk assessment of heart attacks using a stacked ensemble machine learning framework integrated with Explainable Artificial Intelligence (XAI). The system receives patient clinical and demographic parameters including age, gender, blood pressure, cholesterol level, blood glucose level, electrocardiogram (ECG) results, heart rate, chest pain type, and other cardiovascular indicators. The acquired data undergoes preprocessing, feature engineering, and normalization before being analyzed using multiple machine learning algorithms including Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), AdaBoost, and XGBoost. The individual prediction results are combined through a stacking-based ensemble model to improve prediction accuracy and reliability. The system further employs XAI techniques such as SHAP and LIME to generate transparent and interpretable prediction results, enabling healthcare professionals to understand the influence of individual clinical parameters on the predicted risk. Based on the prediction outcome, the system classifies patients into predefined risk categories and generates automated clinical recommendations, reports, alerts, and decision-support information. The invention facilitates early diagnosis, improves clinical decision-making, enhances prediction reliability, and supports timely medical intervention across hospitals, diagnostic centers, and remote healthcare environments.

Disclaimer: Curated by HT Syndication.