Power your workflows with smarter, faster medical terminology matching, the fastest way to turn medical text into standardized codes - no matter the source.
Input free medical text to get corresponding medical codes. Automatic detection of spelling errors or abbreviations in user queries with option to accept or ignore the suggestion/correction.
Intelligently prioritize and rank results that are most relevant to the user’s specific intent. Reduce irrelevant results, improve precision for specialized domains, and streamline workflows by surfacing the most applicable codes faster.
Locate a specific medical code within the Terminology Server’s curated set of medical coding systems. View the equivalent medical code in a different vocabulary – such as SNOMED CT to ICD-10 crosswalks or LOINC to SNOMED mappings.
Filter by Domain (e.g. Condition/Device, Condition/Meas, Drug, Gender), OMOP Standards Concepts Only, Concept Validity, and Confidence Score for enhanced search precision.
Refine your results using boolean operators: use AND/OR logic for exact text matching to get precisely the codes you need.
Use Document Accurate Search, define or modify entity labels at runtime and use the built in pretrained clinical zero-shot entity recognition model.
Entities are mapped to different code systems based on user mappings.
CSV Upload Create your Value Sets a CSV file and upload directly into the Terminology Service
Version Control Support for Value Set versioning to track changes and maintain consistency
Filter Integration Filter search results by your custom Value Sets for targeted code discovery
Full access to all functionality available through the user interface. Implement custom workflows to fully leverage the platform's capabilities within your own systems.
Regular updates of Terminology Server standard vocabularies. Always up to date with latest vocabularies to ensure accuracy and compliance.
Encryption in transit and at rest, role-based access control for administrative functions, and comprehensive audit logging.
Expose any Terminology Server search module (Default, Map Codes, Document Search) as a named agent tool; no custom API wrappers needed.
Agents resolve ambiguous clinical language to canonical codes at inference time, not post-hoc.
SNOMED CT → ICD-10, LOINC → SNOMED, RxNorm → NDC, and any configured concept map, on demand.
Start in minutes with a fully documented Jupyter notebook demonstrating end-to-end agentic terminology workflows.
Be in control of your data and process via on premise installation for maximum security and compliance.
Seamless integration with your Azure environment for enterprise healthcare solutions
Need additional customization and integration within your existing workflow?
When the Terminology Server is deployed on-prem or in a private cloud, all queries to it (e.g., a phrase to code search) stay within the organization’s secure network. Unlike some cloud-based terminology or NLP services, there is no need to send potentially sensitive text or codes over the public internet for processing.
From a compliance standpoint, the Terminology Server supports the full healthcare security stack: encryption in transit and at rest, role-based access control for administrative functions, audit logging of terminology updates and user access, and compatibility with single sign-on (SAML/OAuth) if integrated via the UI. The platform has been used in environments that require HIPAA compliance and has the necessary safeguards to qualify as a HIPAA-compliant component (e.g., no persistent PHI storage—only codes and metadata are stored; any transient query data can be purged or anonymized as needed). No patient identifiers or clinical notes are stored in the server – only the standard terminologies and user-defined mappings – which further simplifies compliance, as the server deals purely with reference data and mapping logic.
Yes, there is zero data sharing with John Snow Labs or third parties; there is no persistent PHI storage—only codes and metadata are stored.
John Snow Labs provides commercial support for the Terminology Server, including regular updates of content (e.g., new code releases) and software patches. Dedicated support ensures that as new versions of terminologies (ICD, SNOMED, etc.) are released, the server’s content library can be updated seamlessly without downtime.
John Snow Labs’ Terminology Server is engineered for high performance and scalability, capable of serving low-latency responses even under heavy workloads and with extremely large vocabulary. The server has been tested with millions of concept entries (the combined size of loaded terminologies) and is optimized for sub-second query times in typical deployments. Its architecture allows horizontal scaling to handle high concurrency.
For example, in an enterprise environment, the Terminology Server can handle real-time code lookups or validations for dozens of simultaneous EHR transactions without noticeable delay. Batch operations (like normalizing an entire dataset) are performed efficiently by leveraging distributed processing when available. Additionally, the embedding-based search is accelerated with vector indexing techniques, ensuring that semantic searches remain fast even as new terms and embeddings are added.
The platform provides documentation with step-by-step installation instructions as well as comprehensive API code samples.
The license provides full access to all the features of the product, with no limitation to the number of users or the number of searches.
No, installation through the marketplaces will generate a cost, and using an on-premise deployment will require a license key. Contact us at support@johnsnowlabs.com for on-premise deployments.
We currently offer Terminology Server on AWS Marketplace and Azure Marketplace
Yes. See online documentation for detailed information.
See hardware requirements online documentation.
Charges are reflected on your AWs or Azure bill and billed through your cloud provider. For on-premise installation you need a valid license; to obtain a license please email us.
Yes. Please email us to discuss your situation and needs.
No. The software is designed to be installed and operated entirely on your own infrastructure. It is built with privacy and data sovereignty in mind, ensuring that it does not transmit any data or results outside of your controlled environment. This architecture guarantees that your data remains within your jurisdiction, providing you with full control over its security and privacy.
Email support@johnsnowlabs.com, call us at +1-302-786-5227, or start a chat on spark-nlp.slack.com. Paying customers get a private Slack channel, so that you can ask your questions privately.
Same business day 8x5 support is included with all subscriptions.
Demos
