Intellectual Property India Publishes Patent Application for 'A Hybrid Quantum-classical Machine Learning System With Weighted Attention Fusion And Shap-lime Explainability For Cardiovascular Disease Prediction' Filed by Dr. A. Pramod Reddy; Shirisha Reddy Kontham; P. Venkata Kishan Rao; E. Radhika; and N. Padmavathi

MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641047860 A) filed by Dr. A. Pramod Reddy; Shirisha Reddy Kontham; P. Venkata Kishan Rao; E. Radhika; and N. Padmavathi, Hyderabad, Telangana, on April 15, for 'a hybrid quantum-classical machine learning system with weighted attention fusion and shap-lime explainability for cardiovascular disease prediction.'

Inventor(s) include Dr. A. Pramod Reddy; Shirisha Reddy Kontham; P. Venkata Kishan Rao; E. Radhika; and N. Padmavathi.

The application for the patent was published on May 1, under issue no. 18/2026.

According to the abstract released by the Intellectual Property India: "The present invention relates to a hybrid predictive system integrating classical machine learning techniques and quantum computational models for improved disease risk prediction. The system comprises a data preprocessing module configured to clean, normalize, and transform raw input data into structured formats suitable for predictive analysis. A classical prediction module processes the structured data using machine learning algorithms to generate classical prediction outputs, while a quantum prediction module utilizes variational quantum circuits to extract complex feature relationships and generate quantum prediction outputs. A weighted attention fusion module dynamically combines classical and quantum outputs using adaptive weighting mechanisms to generate a unified hybrid prediction result. The system further includes an explainability module that integrates global and local interpretation techniques to provide meaningful insights into prediction outcomes. The explainability module generates feature importance values and instance-specific explanations to enhance transparency and interpretability. An output generation module presents prediction results and interpretability insights through structured outputs and visual representations. The proposed hybrid architecture improves prediction accuracy, reliability, and interpretability, making it suitable for applications in healthcare diagnostics, particularly cardiovascular disease risk prediction, as well as other predictive analytics domains."

Disclaimer: Curated by HT Syndication.