MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202641089475 A) filed by Mrs. Sreedevi Kadiyala; Mr. Chandra Srinivas Potluri; Mothukuri Sai Prasad Rao; Ravindra Changala; K. Bhargava Triveni Nandana; K. Nagamani; Dr. Annapurna Gummadi; and Dr. Mahesh Kotha on July 22, 2026, for Quantum-Enhanced Machine Learning Framework For Early Diabetes Prediction And Personalized Healthcare Analytics.
Inventors include Mrs. Sreedevi Kadiyala; Mr. Chandra Srinivas Potluri; Mothukuri Sai Prasad Rao; Ravindra Changala; K. Bhargava Triveni Nandana; K. Nagamani; Dr. Annapurna Gummadi; and Dr. Mahesh Kotha.
The application for the patent was published on July 31, 2026, under issue no. 31/2026.
Abstract: ABSTRACT OF THE INVENTION: Quantum-Enhanced Machine Learning Framework for Early Diabetes Prediction and Personalized Healthcare Analytics The present invention provides a novel hybrid Quantum-Classical computational framework for the early detection and personalized management of diabetes. The system addresses the critical challenges of high-dimensional data processing and the lack of individualized therapeutic insights inherent in classical machine learning models. The framework operates by first acquiring and pre-processing multi-modal patient data, including genomic information, glucometric readings, and lifestyle factors. This data is subsequently encoded into a quantum Hilbert space using a specifically designed feature map, which captures intricate, non-linear relationships between disparate variables. A Variational Quantum Circuit (VQC) processes the encoded data, and the resulting expectation values are utilized to generate a high-accuracy risk score with enhanced computational efficiency. A distinctive feature of the invention is its closed-loop Personalization Engine, which leverages a Quantum Approximate Optimization Algorithm to compare a patient's quantum state with optimal intervention states, thereby generating specific, actionable healthcare directives. The invention significantly improves prediction accuracy by over 10% compared to conventional methods and reduces training latency, facilitating real-time clinical decision-making. Furthermore, it provides a continuum of care by updating the patient's unique quantum profile with new data, ensuring long-term, adaptable predictive maintenance. The present invention is scalable for deployment in telemedicine platforms and wearable health devices, representing a significant advancement in the field of computational personalized medicine.
Disclaimer: Curated by HT Syndication.
