Apparatus and Methods for Supporting Medical Decisions
Summary
The USPTO granted patent US12603178B2 to Kyung Hee University's Industry Cooperation Group for an AI-powered medical decision support apparatus and methods. The patent covers a visual-linguistic neural learning system with cause mining, logical reasoning, and proof inference capabilities for analyzing medical images and generating reports. The patent claims include 14 items across multiple CPC classifications including G16H medical informatics categories.
What changed
The USPTO issued patent grant US12603178B2 to Kyung Hee University's Industry Cooperation Group for an AI-based medical decision support apparatus. The invention includes a visual-linguistic neural learner for extracting features from medical images, a cause miner using hash maps with index-concept pairs, a logical reasoner generating medical reports from visual embeddings and knowledge graphs, and a proof inference unit for answering user queries with supporting evidence. The patent covers 14 claims spanning multiple CPC classifications in medical informatics (G16H) and computer vision/neural network technologies (G06N, G06V).
For research institutions and universities developing AI medical technologies, this patent establishes IP rights in the medical decision support space. Healthcare AI developers and medical technology companies should consider freedom-to-operate implications when designing similar systems. Academic medical centers engaged in AI research partnerships should review IP assignment provisions in collaboration agreements to ensure appropriate ownership of any developed technology.
Archived snapshot
Apr 17, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
Apparatus and methods for supporting medical decisions
Grant US12603178B2 Kind: B2 Apr 14, 2026
Assignee
University-Industry Cooperation Group of Kyung Hee University
Inventors
Sung Young Lee, Hao Hua-Cam, Ubaid Ur Rehman
Abstract
A medical decision supporting apparatus according to an embodiment may include a visual and linguistic neural learner, which receives a medical image and extracts visual embedding, a cause miner, which extracts a predetermined index based on the visual embedding and pretrained embedding, and outputs a predetermined cause for the medical image based on a hash map including at least one index-concept pair and the extracted predetermined index, a logical reasoner, which generates a medical report based on the visual embedding, a background knowledge graph, and the predetermined cause, and a proof inference unit, which generates an answer including a proof for a user's question about the medical image based on the predetermined cause and the medical report.
CPC Classifications
G16H 50/20 G16H 15/00 G16H 30/40 G16H 50/70 G16H 10/20 G16H 30/20 G16H 50/50 G16H 70/60 G06V 10/82 G06V 30/18 G06V 2201/03 G06F 40/205 G06F 40/30 G06N 3/0455 G06N 3/0464
Filing Date
2023-03-20
Application No.
18123449
Claims
14
Related changes
Get daily alerts for USPTO Patent Grants - Health Informatics (G16H)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Grants - Health Informatics (G16H) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.