MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202611101832 A) filed by Manipal University Jaipur on August 24, 2026, for A Method For Optimizing Heart Disease Risk Assessment Using Integrated Unsupervised, Semi-Supervised And Supervised Learning With Clinical Data.
Inventors include Dr Dibakar Sinha; and Dr Ashish Sharma.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: The present invention relates to a hybrid artificial intelligence framework for heart disease risk assessment by integrating unsupervised, semi-supervised, and supervised learning techniques and methods thereof. The method preprocesses clinical data, performs feature engineering, applies K-means clustering to identify hidden patient groups, and generates pseudo-labels for unlabeled samples. A label propagation mechanism refines labels and expands the effective training dataset. The enriched dataset is subsequently processed using ensemble learning models including Random Forest, Gradient Boosting, AdaBoost, Deep Neural Networks, and a stacking meta-learner. The framework improves prediction accuracy, robustness, and interpretability, particularly when labeled medical data are limited. The invention supports efficient clinical decision-making, early diagnosis, and healthcare resource optimization while maintaining adaptability for other medical diagnostic applications
Disclaimer: Curated by HT Syndication.
