About Semedy
Founded in 2012, Semedy offers a complete Knowledge Management platform known as “Clinical Knowledge Management System” (CKMS). The CKMS platform is designed to create and manage multiple types of clinical content artifacts, alongside with detailed metadata and versioning. Semedy’s interdisciplinary team of software engineers and clinical informaticists provides deep domain expertise to help organizations implement CKMS to solve complex authoring, governance, and content dissemination challenges.
Overview of CKMS
CKMS is a high-performance Knowledge Graph (KG) implemented using extensible ontological models. The KG functions as a flexible repository for content artifacts — or knowledge assets — in heterogeneous formats. Knowledge assets are represented as detailed entities ranging from atomic terminology concepts to complex clinical decision support protocols. Connections and dependencies between assets are represented as semantic links that capture meaningful, computable relationships. The platform is designed for scale, with demonstrated capacity to manage millions of knowledge assets.
A semantic reasoner is integrated within CKMS, enabling queries across knowledge assets and their semantic relationships and underlying models. The reasoner enables inferences based on meaning that transcend conventional searching methods. The reasoner also supports pattern detection and the derivation of actionable insights. For instance, it can identify which concepts have been modified in a new terminology release and automatically assess the impact of these changes on related knowledge assets.
CKMS leverages a suite of artificial intelligence (AI) methods — including transformer models and large language models — to automate and streamline labor-intensive content curation tasks. For example, extracting and encoding clinical concepts or detailed logic statements from unstructured text.
Representative Use Cases
- Integration and versioning of reference terminologies, value sets, and data models, enabling the representation of multiple types of knowledge assets
- Representation of executable clinical guidelines, with detailed logic statements defined using extensible data models and integrated value sets and terminologies
- Automated encoding of free text statements using reference terminology concepts, enabling data normalization and semantic interoperability
Learn More
Visit the Semedy website to obtain detailed product documentation and an expanded catalog of application scenarios, or schedule a demonstration.
Blogs
Why Grounding Artificial intelligence in Curated Knowledge is Necessary in Healthcare
Healthcare AI that produces confident but incorrect answers is not just an inconvenience—it erodes trust, introduces risk, and undermines the clinical workflows it was meant to support. The solution is not to distrust AI. It is to give AI access to the right knowledge at the right time. Semedy's CKMS as an MCP (Model Context Protocol) server addresses major dimensions of the AI knowledge problem.
Managing the Knowledge Graph Lifecycle: How Semedy is Already Solving Recognized Challenges
Semedy’s CKMS provides a practical implementation that addresses the challenges identified in the lifecycle management of knowledge graphs. By integrating heterogeneous data sources, supporting evolving knowledge structures, ensuring data quality, and providing role-specific interactions, CKMS offers a comprehensive framework for managing knowledge graphs, small or large, simple or complex.
AI Language Models for Semantic Concept Mapping
The future of healthcare data standardization and interoperability lies in AI- driven solutions that bridge the gap between unstructured data sources and standardized models and terminologies. With our novel AI-based semantic algorithm, we are moving closer to a reality where clinical data is broadly interoperable and actionable.
Recent Presentations
- A Visual Working-Set Approach for Auditing Clinical Classification Logic in Knowledge-Graph-Based Explainable AI
(poster, AMIA Annual Symposium 2026) - Extensional Value Set Curation with Knowledge Graph Augmented LLMs
(poster, AMIA Amplify Informatics Conference 2026) - Core Terminology Management Features for Non-Terminologists
(poster, AMIA Amplify Informatics Conference 2026) - Evaluation of a mapping tool using the WHO-FIC Mapping Principles
(poster, AMIA Amplify Informatics Conference 2026) - Hybrid Retrieval and Reasoning to Predict Procedure Codes from Key Terms Using Knowledge Graphs and Large Language Models: A Formative Study
(oral presentation, AMIA Annual Symposium 2025) - An AI Semantic Mapping Tool in a Knowledge Management System
(poster, AMIA Annual Symposium 2025) - Knowledge Graph for Propositional Reasoning: A Multi-Case Study of Clinical Classifications Software Refined (CCSR) for ICD-10-PCS
(poster, AMIA Annual Symposium 2025) - Knowledge Management Program Implementation
(workshop, AMIA Clinical Informatics Conference 2025) - A Knowledge Graph Driven Approach to Extend BioNLP Annotations to Facilitate the Generation of Clinical Code Sets
(poster, AMIA Annual Symposium 2024) - Knowledge Management at Scale
(workshop, AMIA Clinical Informatics Conference 2024)