To tackle the challenge of transforming free text into an OMOP-compatible format, we developed dedicated SNOMED-aware clinical language models using open-source Large Language Models (LLMs). Data privacy is safeguarded through on-premise training and deployment. Additionally, a SNOMED Query Builder (SnoQB) was built to help researchers curate and manage SNOMED CT concept sets for querying patient data. These queries are matched against a vector database of patient data built using the clinical language models. Extraction results are stored in the OMOP model's note_nlp table, thereby enabling flexible down-stream analytics. Harmonising these OMOP models across the participating hospitals facilitates data exchange, and positions them to participate in real-world evidence (RWE) studies. The entire pipeline was developed and implemented during a proof-of-concept study across a consortium of Belgian hospitals (AZ Klina, AZorg, AZ Oostende and AZ Delta), led by AZ Klina. In a follow-up validation project (PROZA), the tools developed in this project were validated with a real-world use case focused on the automated screening of osteoporosis indicators in patients‚ medical history, showcasing the successful integration of structured and unstructured data from diverse healthcare sources. This project was funded by the Belgian federal authorities‚ Data Capabilities initiative. Back View Map ibis.ai NLP>OMOP: Transforming Clinical Narratives into Actionable Data Read More Country / Region EMEA Tags Artificial intelligence, Collaboration, Data quality To tackle the challenge of transforming free text into an OMOP-compatible format, we developed dedicated SNOMED-aware clinical language models using open-source Large Language Models (LLMs). Data privacy is safeguarded through on-premise training and deployment. Additionally, a SNOMED Query Builder (SnoQB) was built to help researchers curate and manage SNOMED CT concept sets for querying patient data. These queries are matched against a vector database of patient data built using the clinical language models. Extraction results are stored in the OMOP model's note_nlp table, thereby enabling flexible down-stream analytics. Harmonising these OMOP models across the participating hospitals facilitates data exchange, and positions them to participate in real-world evidence (RWE) studies. The entire pipeline was developed and implemented during a proof-of-concept study across a consortium of Belgian hospitals (AZ Klina, AZorg, AZ Oostende and AZ Delta), led by AZ Klina. In a follow-up validation project (PROZA), the tools developed in this project were validated with a real-world use case focused on the automated screening of osteoporosis indicators in patients‚ medical history, showcasing the successful integration of structured and unstructured data from diverse healthcare sources. This project was funded by the Belgian federal authorities‚ Data Capabilities initiative. Description The scope of this project centers on integrating Natural Language Processing (NLP) with the OMOP Common Data Model (CDM) to convert unstructured clinical narratives into structured, actionable data through the use of SNOMED CT. Scope SNOMED CT was chosen for the NLP>OMOP project due to its comprehensive nature and its status as a global standard for clinical terminology. It effectively handles the wide array of concepts found in unstructured clinical narratives, enabling precise mapping and consistent representation of data. This supports interoperability between healthcare systems, facilitating data sharing across different institutions. SNOMED CT also allows for complex queries, aiding in detailed research and analysis through tools like the SNOMED Query Builder (SnoQB). How SNOMED CT will be used In the NLP>OMOP project, SNOMED CT plays a central role in standardizing and structuring clinical data extracted from unstructured text, such as patient reports. The project develops clinical language models, specifically tailored to recognize and map clinical narratives to SNOMED CT concepts. This ensures that the transformation of free-text data into structured, consistent representations aligns with a globally recognized terminology system, facilitating interoperability and data exchange. Furthermore, the project includes the development of the SNOMED Query Builder (SnoQB), which allows researchers to define and manage SNOMED CT concept sets relevant to their specific research interests. These SNOMED CT concept sets enable precise querying of patient data, effectively translating complex clinical language into a standardized format that can be systematically analyzed and stored in OMOP. Why SNOMED CT will be used Contact More information Learn more Get SNOMED CT Information about our license and fee structure Learn more Learn more Explore the wide range of resources available to our community of practice Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe

There are a number of ways that Members, clinicians, vendors, and terminologists can contribute to SNOMED International's community of practice and influence the development of SNOMED CT. Get involved There are a number of ways that Members, clinicians, vendors, and terminologists can contribute to SNOMED International's community of practice. Our events Clinical engagement Advisory groups Project groups Vendor marketplace SNOMED in action Our events SNOMED International values engagement throughout the course of the year with the thriving Community of Practice. We produce business meetings and the SNOMED CT Expo each year as well as participating in a number of industry conferences. More information on our events Clinical engagement Engaging with clinicians is fundamental to ensuring that SNOMED CT is, and continues to be, fit to support clinical practice. The vision of clinical engagement is two-fold. We want to "ensure that all activities of SNOMED International are influenced by global clinical communities” while maintaining a “culture that has a progressive and sustainable approach to engaging clinicians”.Guided by a clinical engagement strategy and dedicated regional clinical leads, SNOMED International invites clinical contribution through its Clinical Reference Groups and Clinical Project Groups. More information on clinical engagement Clinical groups Clinical input to support the development of SNOMED CT is delivered through Clinical Reference Groups and Clinical Project Groups - a full list can be found following the link below. View Clinical Group Directory View now Advisory groups SNOMED International has an active ecosystem of advisory groups that conduct specific activities contributing to the fulfilment of the organization’s responsibilities, operational work items as well as the organization’s mandate. Advisory groups are chaired by SNOMED International staff and are agile in nature, given the changing needs of our organization. Playing a critical role in the management and direction of organization priorities, each advisory group initiates the year by developing a group work plan outline, determining the process by which work plans are actioned, outlining applicable resource requirements, and laying out a set of criteria against which to measure the progress of the applicable group work plan. Contact us to join an advisory group Advisory groups Content managers (CMAG) E-learning (ELAG) Modeling (MAG) Editorial (EAG) Terminology release (TRAG) Learn more Learn more about advisory groups Project groups Project Groups are focused on completing a specific task within a particular period of time and typically have a fixed membership that includes members of the community of practice, and may include SNOMED International representatives. Contact us to join a project group Project groups Devices Diabetes French Translation Collaboration German Translation Group Medical Procedures Observable and Investigation Model SNOMED CT Computable Languages SNOMED on FHIR Translation User Group Vendor marketplace SNOMED International values the input of vendors into the product development and planning process. The SNOMED CT marketplace offers a place where vendors of SNOMED CT can exchange business information with potential purchasers, an important part of encouraging and prompting uptake of SNOMED CT. More information Share your story: SNOMED in Action We showcase SNOMED CT success stories around the world. If you would like to share your SNOMED CT implementation story with a worldwide audience, please register with us. Register Learn more Events Annual Business Meetings, Expo, and SNOMED CT Web Series Learn more Learn more Explore the wide range of resources available to our community of practice Learn more News Read our latest news, newsletters and events Learn more Subscribe Subscribe to SNOMED International news Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe

The Korean Ministry of Health and Welfare (MOHW) issued the Standard Terminology and Data Exchange Standards for Healthcare Data in 2023 to ensure data interoperability. The Korea Core Data for Interoperability (KR CDI) defines the minimum dataset for healthcare data exchange. To standardize KR CDI value sets using standard terminologies such as SNOMED CT and LOINC, the Korea Health Information Service (KHIS) commissioned clinical societies to develop standardized terminology sets. However, challenges in standardization limited their use and dissemination. To address these challenges and prepare for the first release of the SNOMED CT Korean Extension, the Korean National Release Center (NRC) designated by MOHW and operated by KHIS has begun active engagement in Korean Extension content management. The Korean NRC conducted a pilot project in partnership with the Korean Academy of Family Medicine (KAFM) aiming to validate effective collaboration with clinical societies for developing standardized terminology sets. KAFM developed terminology sets for past medical history, family history, smoking, and alcohol use which were mapped to SNOMED CT. The Korean NRC reviewed the map and authored new concepts based on priorities identified during the review. Four reference sets were created using the SNOMED CT Reference Set Tool. This collaboration resulted in adding 83 Korean descriptions and 18 new concepts to the SNOMED CT Korean Extension. In addition to these outcomes, this pilot project produced a generalizable process of collaboration with the clinical societies, supporting continued expansion of the Korean Extension and contributing to national health data interoperability. Back View Map K-HIS Collaborative Strategy for Developing Content for the SNOMED CT Korean Extension with Clinical Societies under KAMS (Korean Academy of Medical Sciences) Read More Country / Region APAC Tags Collaboration, Data quality, Mapping, Pre/postcoordination The Korean Ministry of Health and Welfare (MOHW) issued the Standard Terminology and Data Exchange Standards for Healthcare Data in 2023 to ensure data interoperability. The Korea Core Data for Interoperability (KR CDI) defines the minimum dataset for healthcare data exchange. To standardize KR CDI value sets using standard terminologies such as SNOMED CT and LOINC, the Korea Health Information Service (KHIS) commissioned clinical societies to develop standardized terminology sets. However, challenges in standardization limited their use and dissemination. To address these challenges and prepare for the first release of the SNOMED CT Korean Extension, the Korean National Release Center (NRC) designated by MOHW and operated by KHIS has begun active engagement in Korean Extension content management. The Korean NRC conducted a pilot project in partnership with the Korean Academy of Family Medicine (KAFM) aiming to validate effective collaboration with clinical societies for developing standardized terminology sets. KAFM developed terminology sets for past medical history, family history, smoking, and alcohol use which were mapped to SNOMED CT. The Korean NRC reviewed the map and authored new concepts based on priorities identified during the review. Four reference sets were created using the SNOMED CT Reference Set Tool. This collaboration resulted in adding 83 Korean descriptions and 18 new concepts to the SNOMED CT Korean Extension. In addition to these outcomes, this pilot project produced a generalizable process of collaboration with the clinical societies, supporting continued expansion of the Korean Extension and contributing to national health data interoperability. Description The primary scope of this pilot project involved developing standardized terminology sets through a strategic collaboration between the Korean NRC and a selected clinical society, KAFM. This collaboration aimed to establish and validate a generalizable process for future partnerships with other clinical societies in developing other standardized terminology sets. Previously, standardized terminology sets aligned with the KR CDI were developed independently by clinical societies under the KAMS, with research projects commissioned by KHIS to each clinical society. However, this approach faced limitations in standardization and dissemination, highlighting the need for expertise in standard healthcare terminologies such as SNOMED CT. To address these challenges, KHIS, which operates the Korean NRC, expanded the NRC's role to engage directly in terminology standardization. This project covered defining roles and workflows, standardizing terms by mapping to SNOMED CT, and developing reference sets. KAFM proposed terminology sets in four domains: past medical history, family history, smoking and alcohol use. The Korean NRC mapped source terms to SNOMED CT concepts using the SNOMED CT Browser International Edition. Terms related to past medical history and family history were mapped to SNOMED CT concepts with situation with explicit context semantic tag, while those related to smoking and alcohol use were mapped to ones with finding or observable entity tags. New concepts were authored and added to the SNOMED CT Korean Extension via SNOEMD International Authoring Platform. Ultimately, four reference sets were developed using the SNOMED CT Reference Set Tool 2.0 and added to the Korean Extension. The pilot project between the Korean NRC and the KAFM led to formalization of a scalable and generalizable collaboration model between the Korean NRC and other clinical societies. This established the foundation for sustainable SNOMED CT Korean Extension content development. Scope SNOMED CT was selected for several key reasons. First, SNOMED CT concepts are easily searchable using SNOMED CT Browser. When identifying semantically equivalent concepts for the source terms, various search strategies such as using the first three characters of a term or exploring various synonyms could be employed to find the most appropriate match. This enabled the project team to effectively standardize source terms, specifically the values generated to create standardized terminology sets by the Korean Society of Family Medicine. Second, new SNOMED CT concepts can be modeled and added to the SNOMED CT Korean Extension using SNOMED International Authoring Platform. Until now, Korean Extension was not officially released to the public, limiting the practical use of newly added concepts. However, Korea is planning to release its first official version of the Korean Extension in July 2025. This is expected to significantly expand the use and implementation of the Korean Extension concepts. Third, SNOMED CT reference sets tailored to specific use cases can be developed using the SNOMED CT Reference Set Tool 2.0 (RT2). While RT2 facilitated development of multiple reference sets, there was previously no mechanism for public distribution. With the upcoming release of the Korean Extension, reference sets for various standardized terminology sets can be made publicly available to support diverse user needs. How SNOMED CT will be used SNOMED CT was utilized to map values derived by researchers from the Korean Academy of Family Medicine in the process of creating standardized terminology sets for past history, family history, smoking and alcohol use. SNOMED CT Browser International Edition was searched to identify semantically equivalent concepts. When appropriate SNOMED CT concepts were not available, the Korean NRC used SNOMED International Authoring Platform to model and add new concepts to the SNOMED CT Korean Extension. Once all the source terms are mapped to SNOMED CT concepts, SNOMED CT Reference Set Tool 2.0 was used to create reference sets for past history, family history, smoking and alcohol use. Why SNOMED CT will be used Contact More information Learn more Get SNOMED CT Information about our license and fee structure Learn more Learn more Explore the wide range of resources available to our community of practice Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe

Standardizing digital vaccination records in Canada Back 13 Jul 2018 Back OTTAWA, July 11, 2018 — As provinces and territories across Canada work to digitize vaccination records, a team of Canadian physicians, researchers and policy-makers has released the first version of the Canadian Vaccine Catalogue (CVC). This comprehensive, standards-based source-of-truth is a crucial resource for vaccine terminology and vaccine product information in Canada. It was developed by The Ottawa Hospital mHealth Lab (the team behind CANImmunize) and is funded by the Public Health Agency of Canada. For more information go to: https://cvc.canimmunize.ca . Provinces and territories across Canada are working towards the development of a national network of immunization registries whereby each jurisdiction would maintain its own system for tracking immunization coverage. To facilitate the standardization of these registries and other digital health records that collect immunization data, like electronic medical records, the CVC provides monthly updates of vaccine terminology and product information that is aggregated from various governmental and industry sources. “The Canadian Vaccine Catalogue will make it easier for provinces, territories and industry to build digital vaccination systems that adhere to national standards, without the burden of having to aggregate this information themselves.” – Cameron Bell, lead developer for the CVC. The CVC aggregates the following data which is then made available for consumption by electronic health systems through an HL7® FHIR® interface: Global trade item numbers and associated product information from vaccine manufacturers via GS1 Canada and the Public Health Agency of Canada Vaccine lot release information from the Health Canada Biologics and Genetic Therapies Directorate Vaccine product information from the Health Canada Drug Product Database The vaccination related subsets from the Canadian SNOMED CT edition developed and maintained by Canada Health Infoway The CVC makes it possible for a physician’s electronic medical record to always have an up-to-date list of vaccines that are available for use in Canada and will enable the software to produce vaccination records that are consistent with nationally agreed upon data standards. The CVC also facilitates vaccine barcode scanning for both inventory management and immunization administration. “Our national immunization strategy depends on our ability to collect high-quality data on immunizations, in all provinces and territories, and from a myriad of digital systems and providers. The Canadian Vaccine Catalogue can help facilitate this.” Dr. Kumanan Wilson, senior scientist at The Ottawa Hospital, professor at the University of Ottawa and founder of The Ottawa Hospital mHealth Lab, based at Algonquin College. The CVC powers the pan-Canadian immunization app CANImmunize ( www.canimmunize.ca ) which allows people to manage their immunization records across mobile devices, and soon on the web. CANImmunize uses the CVC to ensure that when users track vaccinations in their app, that the resulting digital records are compatible with provincial immunization registries that adhere to the same standards. The CVC is important for the following users: Electronic medical record vendors Drug database providers Public health immunization system implementers Consumer health application developers The catalogue is open and free to use and can be downloaded from https://cvc.canimmunize.ca . Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe

SNOMED CT is the main clinical terminology in Helseplattformen EHR representing diagnoses, patient nursing plans and medication. This enables closed loop medication, advanced clinical decision support, and efficient reporting to health registries by FHIR profiles. SNOMED CT is a primary factor for interoperability across different operating systems and to bridge primary and secondary health care services. Back View Map Helseplattformen SNOMED CT: An engine for data driven healthcare services in Central Norway Read More Country / Region EMEA Tags Clinical Practice, Data quality, EHDS (European Health Data Space), Implementation, Innovation SNOMED CT is the main clinical terminology in Helseplattformen EHR representing diagnoses, patient nursing plans and medication. This enables closed loop medication, advanced clinical decision support, and efficient reporting to health registries by FHIR profiles. SNOMED CT is a primary factor for interoperability across different operating systems and to bridge primary and secondary health care services. Description Since 2019, the implementation of the Helseplattformen Electronic Health Record (EHR) has been underway, heralding a significant leap in healthcare technology within the Central Norway region. This system is built on the foundation of Epic Electronic Patient Journal (EPJ). In May 2022, Trondheim municipality was the first to use the new EHR system. Today Helseplattformen is operative for 39200 health workers, 9 hospitals, 34 municipalities, 71% of the population in Central Norway, 2 GP offices, 2 emergency care centers, all hospital labs and pharmacies. Helseplattformen EHR utilizes SNOMED CTs hierarchal structure (disorder, finding, procedure (to some extent), substance, body structure) to facilitate a wide range of functionality. From diagnose making, registering patient nursing plans, a closed-loop medication management system, clinical decision support and allergy warnings to efficient reporting to health registries by FHIR profiles. SNOMED CT provides Helseplattformen EHR with a solution to interoperate across different operating systems and bridge primary and secondary health care services. Scope SNOMED CT is the only terminology/ standard with the potential to enable us to interoperate across different operating systems and bridge primary and secondary health care services. How SNOMED CT will be used Helseplattformen EHR utilizes SNOMED CTs hierarchal structure. Disorder, finding, procedure (to some extent), substance, body structure hierarchies are used to facilitate a wide range of functionality in the system. From diagnose making by doctors, registering patient nursing plans, a closed-loop medication management system, clinical decision support and allergy warnings to efficient reporting to health registries by FHIR profiles. Why SNOMED CT will be used Contact More information Learn more Get SNOMED CT Information about our license and fee structure Learn more Learn more Explore the wide range of resources available to our community of practice Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe

In Region Stockholm and Region Gotland we have a decision that we are going to use SNOMED CT as our common terminology. To meet the decision we were needed to have a strategy and a roadmap adjusted to our regions needs and to meet the organizational complexety and size. There has been active work on the implementation and integration of SNOMED CT (Systematized Nomenclature of Medicine – Clinical Terms) to standardize healthcare terminology. The region uses SNOMED CT as part of its efforts to enhance interoperability, data quality, and patient safety within electronic health records (EHRs). This initiative is part of a broader digital health strategy to improve the quality and efficiency of care through structured and semantically rich data. We would like represent the strategy and the roadmap and the work around it, the successes and failes. Back View Map Karolinska Universitetssjukhuset (2 of 2) SNOMED CT implementation and strategy in Region Stockholm, Sweden Read More Country / Region EMEA Tags Collaboration, Data quality, Implementation In Region Stockholm and Region Gotland we have a decision that we are going to use SNOMED CT as our common terminology. To meet the decision we were needed to have a strategy and a roadmap adjusted to our regions needs and to meet the organizational complexety and size. There has been active work on the implementation and integration of SNOMED CT (Systematized Nomenclature of Medicine – Clinical Terms) to standardize healthcare terminology. The region uses SNOMED CT as part of its efforts to enhance interoperability, data quality, and patient safety within electronic health records (EHRs). This initiative is part of a broader digital health strategy to improve the quality and efficiency of care through structured and semantically rich data. We would like represent the strategy and the roadmap and the work around it, the successes and failes. Description In Region Stockholm we have a decision that we are going to use SNOMED CT as our common terminology in our technical systems and project. To meet the decison we were needed to have a strategy and a roadmap. The region is responsible for healthcare services for approximately 2.3 million residents and operates seven emergency hospitals, including Karolinska University Hospital, as well as around 200 primary care centers and specialist clinics. The implementation in the region is therefore a longterm process where needs from multiple directions must be considered. Scope Several stakeholders explained a need for a national controlled terminology and for that we only have SNOMED CT. And for preperation for the EHDS requirements. How SNOMED CT will be used The region uses SNOMED CT as part of its efforts to enhance interoperability, data quality, and patient safety within electronic health records (EHRs). This initiative is part of a broader digital health strategy to improve the quality and efficiency of care through structured and semantically rich data. Why SNOMED CT will be used Contact More information Learn more Get SNOMED CT Information about our license and fee structure Learn more Learn more Explore the wide range of resources available to our community of practice Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe

New Global Licensing Agreement for SNOMED CT Code Inclusion in the DICOM Standard Back 2 Mar 2016 Back IHTSDO and the DICOM Standards Committee today announced a new global licensing agreement for SNOMED CT codes and descriptions to be used in the Digital Imaging and Communications in Medicine (DICOM) standard. The renewable five-year licensing agreement between IHTSDO and DICOM continues the long-standing DICOM policy of using SNOMED terminology, previously established with the SNOMED DICOM Microglossary of 1997 and an agreement with the College of American Pathologists. The SNOMED CT licensing agreement covers the use of a subset of 7,314 SNOMED CT codes and descriptions, including all current SNOMED CT concepts used in the DICOM standard. Other key points from the agreement include the following: The agreed SNOMED CT subset will be updated after each biannual SNOMED CT international release, taking into account changes to SNOMED CT and requests from the DICOM Standards Committee to use additional concepts. The agreed SNOMED CT subset is free for use, both for publication in DICOM as well as by implementers and users of DICOM-compliant products and software globally, without restriction to IHTSDO member countries. If implementers use additional SNOMED CT codes (beyond the scope of the agreed subset), they are subject to SNOMED CT licensing arrangements that may incur a fee in IHTSDO non-member countries. The DICOM standard will be updated to retire and replace concepts that have been inactivated in SNOMED CT. For more details on the agreement please visit the IHTSDO and DICOM websites. Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe

Accurate documentation of anaphylaxis-related information in electronic health records (EHRs) is critical for patient safety, particularly in reducing the risk of adverse drug events. However, such information is often stored in unstructured formats, hindering interoperability and effective decision-making. To address this challenge, we propose a multi-stage processing pipeline that utilizes large language models (LLMs) to extract clinical entities from free-text clinical notes and structure them into standardized FHIR AllergyIntolerance resources. The pipeline includes entity linking of key fields, such as substance, manifestation, and exposure route, to SNOMED CT concepts, using external terminology services to ensure precision and semantic alignment. To support the creation of high-quality annotated datasets for evaluation, we developed a web-based annotation tool. This application presents the automatically generated FHIR resources in a user-friendly form interface, enabling clinical and terminological experts to collaboratively review, validate, and refine the extracted data. The tool supports real-time saving, author attribution, and status tracking, facilitating a streamlined annotation workflow. SNOMED CT was selected as the target terminology due to its comprehensive coverage, formal structure, and suitability for representing allergy-related content. Our goal is to allow for the automation of anaphylaxis data structuring at scale, while also addressing the need for accurate ground truth datasets to evaluate information extraction systems. Back View Map University of Sao Paolo Large language model-based pipeline for anaphylaxis data structuring and SNOMED CT concept mapping Read More Country / Region Americas Tags Artificial intelligence, Data analytics, Mapping, Patient safety, Research Accurate documentation of anaphylaxis-related information in electronic health records (EHRs) is critical for patient safety, particularly in reducing the risk of adverse drug events. However, such information is often stored in unstructured formats, hindering interoperability and effective decision-making. To address this challenge, we propose a multi-stage processing pipeline that utilizes large language models (LLMs) to extract clinical entities from free-text clinical notes and structure them into standardized FHIR AllergyIntolerance resources. The pipeline includes entity linking of key fields, such as substance, manifestation, and exposure route, to SNOMED CT concepts, using external terminology services to ensure precision and semantic alignment. To support the creation of high-quality annotated datasets for evaluation, we developed a web-based annotation tool. This application presents the automatically generated FHIR resources in a user-friendly form interface, enabling clinical and terminological experts to collaboratively review, validate, and refine the extracted data. The tool supports real-time saving, author attribution, and status tracking, facilitating a streamlined annotation workflow. SNOMED CT was selected as the target terminology due to its comprehensive coverage, formal structure, and suitability for representing allergy-related content. Our goal is to allow for the automation of anaphylaxis data structuring at scale, while also addressing the need for accurate ground truth datasets to evaluate information extraction systems. Description Over 35% of patients have at least one allergy recorded in their electronic health records (EHRs), with approximately 4% having three or more documented allergies. Despite this, allergy documentation is often incomplete or inaccurate, impeding effective clinical decision-making and compromising patient safety during prescription [1]. Allergic reactions account for roughly 10% of fatal adverse drug events, underscoring the critical importance of accurate allergy information [2]. Anaphylaxis represents the most severe manifestation of acute systemic allergic reactions, typically occurring within minutes to a few hours following exposure to an allergen or other triggering agent [3]. The accurate documentation and exchange of allergy-related data are essential for ensuring patient safety, effective care delivery, and health education. Research indicates that 8-13% of medication errors could be prevented if allergy information were reliably documented at the time of medication ordering [4]. However, healthcare data are frequently unstructured, inconsistently formatted, or fragmented across different systems, making standardization a complex and resource-intensive process [5, 6]. Recent advancements in deep learning and natural language processing (NLP, particularly through the development of large language models (LLMs), have shown potential for automating the structuring of clinical data at scale. These techniques allow for the extraction of medical entities from unstructured text, the mapping to standardized terminologies such as SNOMED CT, and the generation of structured data in compliance with international healthcare standards, such as FHIR (Fast Healthcare Interoperability Resources) [6, 7]. In this context, we propose a processing pipeline that utilizes LLMs to extract and structure anaphylaxis-related information from free-text clinical notes [11] into the FHIR AllergyIntolerance [10] resource. This pipeline includes mapping of extracted entities, such as substances, clinical manifestations, and exposure routes, to standardized SNOMED CT concepts. To ensure the accuracy and usability of these structured resources, we developed a Web-based application that allows annotators to review and refine the automatically generated data, enhancing the reliability of allergy documentation and reducing the impact of adverse events caused by re-exposure to the identified agents in clinical practice. The proposed multi-stage processing pipeline begins by extracting clinical entities from unstructured text and structuring them into FHIR-compliant AllergyIntolerance resources in JSON format. To enhance the reliability of this generation process and minimize the occurrence of hallucinations (i.e., the generation of incorrect or extraneous information), structured output generation techniques are employed. These techniques are guided by detailed documentation on the expected output format derived from the official FHIR specification, ensuring that the generated resources conform closely to the standard. Subsequent to entity extraction, a concept mapping step (also known as entity linking) is performed for those entities requiring binding to standardized medical vocabularies. In particular, entities categorized under substance, manifestation, and exposure route are mapped to corresponding concepts in SNOMED CT. To improve accuracy and contextual relevance, the system utilizes non-parametric external resources, including terminology service APIs. This external access is essential, given that generating correspondences de novo(without additional context) is challenging for large language models [8]. The pipeline operates under a tool-calling agent architecture [9], where each processing stage is modular and can invoke specialized tools as needed. This architecture allows the system to iteratively refine outputs, correcting errors at intermediate steps before they can affect downstream processing. Furthermore, the modular design supports the integration of different models and external tools, enabling comparative evaluation of both open-source and proprietary LLMs. To assess the pipeline’s performance, system-generated AllergyIntolerance resources are evaluated against expert-annotated datasets. This evaluation considers the accuracy of extracted entities, conformity to the FHIR schema, and correctness of SNOMED CT mappings. For this purpose, a Web-based annotation application was developed, capable of rendering JSON-formatted resources in an intuitive form-based interface. This application enhances usability for clinical and terminological specialists, supports real-time saving, and facilitates collaborative annotation across domains. It also includes author attribution and annotation status tracking features. By streamlining the annotation workflow, this application contributes to the creation of high-quality ground truth datasets, thereby enabling a rigorous evaluation of the pipeline’s effectiveness in automating the conversion of unstructured clinical text into standardized, interoperable formats. [1] Wang, Liqin et al. A dynamic reaction picklist for improving allergy reaction documentation in the electronic health record. Journal of the American Medical Informatics Association, v. 27, n. 6, p. 917-923, 2020. [2] Nakayama, Masaharu; Inoue, Ryusuke. Implementation and effect of a novel electronic medical record format for patient allergy information. In: Building Continents of Knowledge in Oceans of Data: The Future of Co-Created eHealth. IOS Press, 2018. p. 51-55. [3] Cardona V, Ansotegui IJ, Ebisawa M, El-Gamal Y, Fernandez Rivas M, Fineman S, et al. World allergy organization anaphylaxis guidance 2020. World Allergy Organ J. 2020;13(10):100472. [4] Goss, F. R., Zhou, L., Plasek, J. M., Broverman, C., Robinson, G., Middleton, B., & Rocha, R. A. (2013). Evaluating standard terminologies for encoding allergy information. Journal of the American Medical Informatics Association, 20(5), 969–979. [5] Mello, Blanda H et al. Semantic interoperability in health records standards: a systematic literature review. In: Health and technology 12.2 (2022), pp. 255–272. [6] Yang, Xi et al. A large language model for electronic health records. In: NPJ digital medicine 5.1 (2022), p. 194. [7] Agrawal, Monica et al. Large Language Models are Few-Shot Clinical Information Extractors. 2022. arXiv: 2205.12689 [cs.CL]. [8] Matentzoglu, Nicolas et al. MapperGPT: Large Language Models for Linking and Mapping Entities. 2023. arXiv: 2310.03666 [cs.CL]. [9] Yao, Shunyu et al. “React: Synergizing reasoning and acting in language models”. In: arXiv preprint arXiv:2210.03629 (2022). [10] HL7. Fast Healthcare Interoperability Resources. URL: https://hl7.org/fhir/ [11] Ensina, L.F.; Machado, M.M.; Marques, J.B.M.; dos Santos, M.P.H.; Lario, F.C.; Araújo, C.A.; Oliveira, F.A.N.; Moreira, D. Artificial intelligence for detecting anaphylaxis in electronic medical records. Asia Pacific Allergy, v. 1, p. 1-6, 2025. Scope SNOMED CT was selected for concept mapping within the AllergyIntolerance FHIR resource due to its alignment with key criteria for standardized clinical terminologies. Among available medical vocabularies, SNOMED CT offers extensive domain-specific content coverage, including detailed representation of drug, food, and environmental allergies. It is particularly well-suited for encoding allergy and anaphylaxis-related information owing to its robust concept orientation, formal definitions, and levels of granularity, which are essential for capturing the clinical nuances of allergic reactions [4]. Moreover, SNOMED CT's vocabulary structure and ongoing maintainability further support its suitability for integration into automated data structuring pipelines. Its ability to fulfill the majority of desirable criteria, including the representation of complex clinical entities and their relationships [4], enhances the reliability of the extracted data. By using SNOMED CT, the proposed system ensures that anaphylaxis-related entities are standardized in a way that supports consistent interpretation and reuse across healthcare applications and systems. How SNOMED CT will be used In the context of the AllergyIntolerance FHIR resource [10], the fields 'code' 'substance' 'manifestation' and 'exposureRoute' are particularly important for accurate semantic representation. To enhance interoperability and ensure alignment with standardized clinical vocabularies, entities extracted for these fields are mapped to SNOMED CT concepts. Specifically, the 'code' field captures the substance associated with the risk of an adverse reaction, while the 'substance' field refers to the actual agent believed to have triggered the reaction. The 'manifestation' field records the clinical signs or symptoms exhibited during the reaction, and 'exposureRoute' describes how the subject was exposed to the substance. We have also introduced an additional field to capture sudden onset information, which is important for identifying anaphylaxis, and have mapped this information to SNOMED CT concepts to increase clinical rigor. During the concept mapping stage of the pipeline, the system interfaces with external terminology services (such as API-accessible SNOMED CT endpoints) to perform entity linking. For each extracted clinical entity, the system queries these resources and selects the concept that most accurately matches the entity's meaning. This external querying step supports more reliable mapping by grounding the system's output in standardized clinical vocabularies, mitigating the limitations of language models in generating mappings without context. Why SNOMED CT will be used Contact More information Learn more Get SNOMED CT Information about our license and fee structure Learn more Learn more Explore the wide range of resources available to our community of practice Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe

First Member from the Caribbean region, Jamaica adopts SNOMED as a needed element of its digital health transformation Back 2 Jun 2023 Back SNOMED International is pleased to announce that Jamaica has joined the global SNOMED CT community, becoming SNOMED International’s inaugural Member from the Caribbean region. Jamaica, the third largest island in the Caribbean Sea, boasts a population of nearly 3 million. Currently, Jamaica is undergoing a major digital transformation of its healthcare system, spearheaded by the national EHR pilot and health data exchange platform. These cutting-edge initiatives will empower patients to access their healthcare data and streamline transitions between public and private healthcare systems. By leveraging technology to improve healthcare access and quality, Jamaica is poised to make significant strides in enhancing the well-being of its citizens, while setting a compelling example for other nations in the region to follow. Founded in 2007 by nine charter nations, SNOMED International is a not-for-profit, member-owned and driven international organization. Jamaica’s adoption of SNOMED CT, the world’s most comprehensive health terminology, is an important part of its digital health transformation: not only does it provide access to SNOMED CT and SNOMED International’s related products and services, but it also opens the door to the broad expertise of a global community of stakeholders, including other Members, collaboration partners, researchers, policy-makers, implementers, vendors, care providers, and patients and citizens. Learn more about the varied stakeholders contributing to the use and ongoing development of SNOMED CT at www.value.snomed.org . Joining a community of 48 global Members, Jamaica’s Ministry of Health & Wellness will serve as the National Release Centre for SNOMED CT. The Ministry will appoint representatives to the General Assembly and the Member Forum, the governance bodies that shape and guide SNOMED International projects and products, promote consultation and communication between SNOMED International and Members and make binding organizational decisions. “We are thrilled to welcome our first Member of the Caribbean region,” said SNOMED International CEO Don Sweete. “The implementation of SNOMED CT in Jamaica aligns with and supports the country’s commitment to digitally transforming its health system and will contribute to improved patient outcomes for Jamaica’s citizens.” Learn more about Jamaica’s Ministry of Health & Wellness . Visit Jamaica’s Member page on the SNOMED International website to view the country’s representatives to the Member Forum and the General Assembly. To learn more about SNOMED International and SNOMED CT, visit www.snomed.org . About the Jamaican Ministry of Health & Wellness The Ministry of Health (MOH) is the pre-eminent Government organization whose mandate is “to ensure the provision of quality health services and to promote healthy lifestyles and environmental practices.” The Ministry and its Regional Health Authorities, agencies and related organizations make up the public health system and are responsible for health care delivery across the island. Jamaica’s health vision is: “Healthy People, Healthy Environment.” It is one which envisages a health system that is client-centred and guarantees access to quality health care for every person in its population, at reasonable costs, and which takes into account the needs of the vulnerable. It is one which seeks to provide information and to educate the populace, to facilitate individuals taking responsibility for their own health, making informed decisions and adopting healthy lifestyle habits. All this, within a clean, healthy environment where families and communities actively participate and are integrated into the system of health. About SNOMED International SNOMED International is a not-for-profit organization that owns and develops SNOMED CT, the world's most comprehensive healthcare terminology product. We play an essential role in improving the health of humankind by determining standards for a codified language that represents groups of clinical terms. This enables healthcare information to be exchanged globally for the benefit of patients and other stakeholders. We are committed to the rigorous evolution of our products and services, to deliver continuous innovation for the global healthcare community. SNOMED International is the trading name of the International Health Terminology Standards Development Organization (IHTSDO.) Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe

Global Patient Set The GPS supports health information interoperability across care settings, systems, organizations and national borders. Download GPS What is the GPS? The GPS is an open, and freely accessible collection of SNOMED CT terms that represent the breadth of the content in the SNOMED CT International Edition to better support core health data exchange, public health reporting, research, and more. GPS offers global access to all SNOMED CT unique identifiers, fully specified names (FSNs), preferred terms in international English, and active/inactive indicators — made available at no cost to users. The GPS does not include SNOMED CT’s relationships, hierarchies and remaining descriptions. GPS resources GPS Implementation Guide The GPS Implementation Guide provides practical implementation guidance for organizations adopting the GPS. It describes how systems can receive SNOMED CT identifiers (for example through HL7 FHIR data structures), treat them as opaque codes, store them alongside the relevant GPS version, and perform basic validation checks. It also outlines governance and operational considerations, including release management, handling inactive concepts, and maintaining locally defined value sets where limited data entry is required. Access the GPS Implementation Guide here. Tooling Licensing Commonly asked questions GPS in the news Contact us About the GPS The GPS is an initiative from SNOMED International designed to support the global exchange and use of clinical information encoded with SNOMED CT identifiers. The GPS enables healthcare systems in both SNOMED CT Member and non-Member countries to share, store, and display SNOMED CT–coded data without requiring access to the full SNOMED CT terminology or a licensing agreement. Its primary goal is to improve international interoperability and continuity of care, particularly in cross-border healthcare, global health programmes, and environments where SNOMED CT licensing is not available. GPS Implementation Guide First & last name* Position* Email* Organization or Company* Country Which of the following best describes your organization?* If you plan to translate the GPS, please specify into which language* Licensed Use The GPS is produced by SNOMED International under the terms of the Creative Commons Attribution-NoDerivatives 4.0 International License . General Data Protection Regulation (GDPR) Opt-In / Opt-Out We would like to keep you informed about updates or changes to the International Patient Set. If you would like to receive this information via email please indicate your preference below. You can change this preference in the future by using the unsubscribe, manage notifications or opt out options in the footer of our emails. We will only use your email address to send you information you have requested. We will never pass on your information to other companies for marketing or other purposes without your explicit permission. I have reviewed and acknowledge SNOMED International's Privacy Policy Submit Download the GPS Please register your use of SNOMED International's Global Patient Set. Learn more Get SNOMED CT Information about our license and fee structure Learn more Subscribe Subscribe to SNOMED International news Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe What is the GPS? Download the GPS GPS Resources

Diabetic patients require constant monitoring and foot screening on hospital admission by clinicians to identify injuries that might lead to infection and ulceration and to prevent progression of foot disease. Studies show that the correct management of diabetic foot patients (DFPs) in the UK could lead to a decrease in amputation rates, hospital admission avoidance, and a drastic reduction in the NHS cost of managing patients with diabetic foot problems1. The aim of this work is to develop and deploy a fully automated, API-based dashboard system that supports management of DFPs at Barts Health NHS Trust. Our algorithm extracts a list of patients from the Trust Data Warehouse who have been admitted to the hospital. For each patient, the free-text clinical notes created in the past 6 months are identified and processed with CLiX, a commercial natural language processing tool developed by Clinithink which uses post coordinated SNOMED-CT expressions to extract clinical terms from unstructured clinical notes. Demographic, clinical, and automated risk assessment data are presented in a secure and customizable dashboard. Preliminary results at the Royal London Hospital in east London showed that, in one month, the dashboard correctly identified 42 DFPs. Of these, 33 received an immediate clinical intervention and 9 had no recorded intervention. There were 7 incorrect identifications, mostly involving gestational diabetes, congenital conditions or non-diabetic patients. Our data-driven clinical tool continues to identify inpatients with diabetes and shows strong potential for improving early clinical intervention for DFPs. 1 - Guest JF et al., 2018. Back View Map Bart's Health NHS Trust (3 of 3) A SNOMED driven clinical dashboard system to support the identification and management of diabetic patients with possible foot disease in a large academic health system in east London Read More Country / Region EMEA Tags Artificial intelligence, Clinical Practice, Data analytics, Implementation, Research Diabetic patients require constant monitoring and foot screening on hospital admission by clinicians to identify injuries that might lead to infection and ulceration and to prevent progression of foot disease. Studies show that the correct management of diabetic foot patients (DFPs) in the UK could lead to a decrease in amputation rates, hospital admission avoidance, and a drastic reduction in the NHS cost of managing patients with diabetic foot problems1. The aim of this work is to develop and deploy a fully automated, API-based dashboard system that supports management of DFPs at Barts Health NHS Trust. Our algorithm extracts a list of patients from the Trust Data Warehouse who have been admitted to the hospital. For each patient, the free-text clinical notes created in the past 6 months are identified and processed with CLiX, a commercial natural language processing tool developed by Clinithink which uses post coordinated SNOMED-CT expressions to extract clinical terms from unstructured clinical notes. Demographic, clinical, and automated risk assessment data are presented in a secure and customizable dashboard. Preliminary results at the Royal London Hospital in east London showed that, in one month, the dashboard correctly identified 42 DFPs. Of these, 33 received an immediate clinical intervention and 9 had no recorded intervention. There were 7 incorrect identifications, mostly involving gestational diabetes, congenital conditions or non-diabetic patients. Our data-driven clinical tool continues to identify inpatients with diabetes and shows strong potential for improving early clinical intervention for DFPs. 1 - Guest JF et al., 2018. Description This project aims to develop a simple, user-friendly dashboard system to support clinicians at Barts Health NHS Trust in managing diabetic foot patients. The system helps identify patients who are currently in the Trust and highlights diabetic patients who may be at risk of developing foot infections or ulcers. The system extracts structured and free text information from patient EHRs, which are routinely exported from Oracle Millennium and stored in the Trust's Data Warehouse. The extracted notes are then sent to CLiX, a commercial natural language processing tool developed by Clinithink which uses SNOMED-CT to identify clinically relevant text and match to cohorts of interest. Patient clinical summaries with previously defined risk stratification obtained from CLIX are then displayed in easy-to-understand charts and tables that staff can personalise. By making it easier to spot issues early, the tool helps healthcare providers improve care, reduce the number of amputations, and save NHS resources. Scope SNOMED CT is a standardized terminology system able to identify and categorize clinical concepts and key terms related to diabetic foot disease. This not only improves the quality of data extracted from unstructured medical notes but also facilitates interoperability across different systems in healthcare. We used SNOMED CT because we wanted to extract granular, relevant clinical information consistently and comprehensively from clinical reports. By using SNOMED CT, we are able to align with national and international standards, making our solution scalable and adaptable to various clinical environments and a range of clinical conditions. How SNOMED CT will be used We used SNOMED CT Expression Constraint Language (ECL) to define cohorts of patients with diabetes and diabetic foot disease. These expressions are used by the CLiX NLP tool to identify and categorise relevant patients based on post coordinated SNOMED expressions extracted from unstructured clinical notes. Granular symptom information is automatically extracted by the NLP tool in SNOMED CT format. This level of detail allows us to * stratify patients based on their risk of developing diabetic foot disease, supporting early intervention and more personalised care pathways * generate a large SNOMED CT coded dataset used for analytics projects to better understand patients with diabetic foot disease in east London Finally, confirmed cases identified using the dashboard have the appropriate SNOMED CT code added to the patient's electronic care record by the clinical team. This ensures the information is available for future care and planning decisions, embedding the tool's outputs into routine clinical workflows. Why SNOMED CT will be used Contact More information Learn more Get SNOMED CT Information about our license and fee structure Learn more Learn more Explore the wide range of resources available to our community of practice Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe

Opinions and perspectives on SNOMED CT and its use in digital health from thought leaders across our global community. Blog Series Opinions and perspectives on SNOMED CT and its use in digital health from thought leaders across our global community. Submit your blog idea Learn more 3 Jun 2026 Dr James Case, SNOMED International Chief Terminologist BLOG: Exploring a move from PCOS to PMOS Learn more 11 Dec 2025 Tudor Groza (Bioinformatics Institute, A*STAR & Maternal and Child Health Research Institute, KK Women’s and Children’s Hospital, Singapore) and Ian Green (SNOMED International) Surfacing Rare Diseases Earlier: Smarter Signals from Health System Clinical Data Learn more 16 Sept 2025 Blog: SNOMED International concludes community feedback period on proposed description character limit increase and finalizes next steps Learn more 18 Mar 2025 By: Anne Randorff Højen, Alejandro Lopez Osornio & Kai Kewley Discover the SNOMED CT Implementation Demonstrators Learn more 12 Mar 2025 By: Marte Rime Bø, Norwegian Directorate of Health Learn about SNOMED CT in Norway: internal implementations and global experiences Load more Subscribe to SNOMED International news Stay up to date on SNOMED news, features, developments and newsletters by subscribing to our news service. Subscribe