MUMBAI, India, Aug. 12 -- Intellectual Property India has published a patent application (202641092010 A) filed by Sr University on July 29, 2026, for Ontology-Linked Graph Retrieval-Augmented Generation Framework Using Umls For Medical Visual Question Answering.
Inventors include Dr. B. Omkar Lakshmi Jagan; Dr. Durgesh Nandan; and Dr S Satyanarayana Ph. D. , Pdfai.
The application for the patent was published on August 07, 2026, under issue no. 32/2026.
Abstract: ABSTRACT [0011] The invention aims to provide an ontology-aware retrieval mechanism capable of enriching retrieved medical evidence by utilizing structured medical knowledge graphs based on the Unified Medical Language System (UMLS), thereby improving clinical reasoning and factual consistency. The invention extracts medical entities from clinical questions and maps them to UMLS Concept Unique Identifiers (CUIs). A graph traversal mechanism explores neighbouring medical concepts including diseases, organs, modalities, symptoms, and anatomical relationships. The retrieved ontological knowledge is transformed into structured clinical facts and integrated with retrieved documents before answer generation. This ontology-guided retrieval significantly enhances diagnostic reasoning, contextual completeness and factual grounding.
Disclaimer: Curated by HT Syndication.
