Seeing is believing - FAIR metadata for medical imaging data in the SPHN Semantic Interoperability Framework

Seeing is believing - FAIR metadata for medical imaging data in the SPHN Semantic Interoperability Framework | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Method Article Seeing is believing - FAIR metadata for medical imaging data in the SPHN Semantic Interoperability Framework Edwin ter Voert, Harald Witte, Vasundra Touré, Bjoern Menze, Sabine Österle This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8901680/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Medical imaging is vital to modern healthcare, supporting diagnostics, treatment, and research. To integrate imaging data within the Swiss Personalized Health Network (SPHN), we developed an SPHN RDF Schema extension for standardized and structured imaging metadata. Built on the FAIR (Findable Accessible, Interoperable, Reusable) principles and established standards like DICOM and SNOMED CT, this extension models essential imaging information and links it to related clinical data, such as diagnoses, patient visits, and biosamples. This enhances semantic coherence and addresses interoperability gaps, thereby enabling applications in clinical research and precision medicine using the rich resources medical imaging data represents. Personalized Medicine Medical Informatics Information Retrieval and Management FAIR DICOM Medical imaging Metadata Semantics Semantic interoperability Health data interoperability Figures Figure 1 1. Introduction The Swiss Personalized Health Network (SPHN) aims to improve health data interoperability across Switzerland [ 1 ]. To ensure consistent, reusable data for both humans and machines, SPHN developed the Semantic Interoperability Framework – a system of semantic artifacts, including formal concept definitions (building blocks representing specific data elements), Resource Description Framework (RDF) schema specifications, and validation rules, all referring to international standards like Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) where possible, and supported by a dedicated tool stack [ 2 – 4 ]. Starting with a limited set of concepts in 2021, the SPHN Schema has expanded step by step to cover a wide range of clinical domains and diverse data sources such as clinical records, trials, registries, patient-reported outcomes, and molecular analyses. Its latest release includes structured representations for imaging data, procedures, and devices, reflecting the critical role of medical imaging. The included metadata descriptors were carefully accessed based on the needs of researchers and availability in the “Digital Imaging and Communications in Medicine” (DICOM) standard [ 5 , 6 ], the de facto international standard for medical imaging datasets and corresponding metadata. A simplified DICOM model with the real-world entities Patient, Study, Series, and Image is shown in Fig. 1 (left part). 2. Methods As a starting point, a questionnaire (31 questions plus free-text remarks) was sent to eleven senior imaging experts and decision makers working in a clinical or medical imaging research field, stratified across nine institutions in Switzerland. The response rate was 91% (10/11). Subsequently, an on-site workshop with imaging experts from Swiss hospitals and the Federal Institute of Technology was carried out to align with the needs of researchers, institutions and their priorities for data items to develop. During follow-ups with stakeholders the DICOM metadata of interest and its availability in hospitals could be determined Corresponding DICOM attributes were selected, introduced in formal concept definitions in line with the SPHN Schema and structured in tabular form. This concept specification served as input for the SPHN Schema Forge tool [ 3 ] to build the RDF artifacts. 3. Results 3.1. Implementation scope In alignment with stakeholders’ requirements (see Table 1 ), four imaging modalities and associated content were prioritized to be included in the SPHN Schema: Computed Tomography (CT), Magnetic Resonance (MR), Positron Emission Tomography (PET), and X-Ray. Details and examples are available in the imaging concepts guidelines of the SPHN Semantic Interoperability Framework documentation 1 . Table 1 Outcome of the stakeholder survey to identify community needs with respect to medical imaging data. Number of mentions in brackets. Research field Research topics Imaging modalities of interest Metadata areas of interest Radiology (5) Algorithm development (5) MR-related (18) scan parameters (6) Oncology (1) image segmentation (5) CT-related (16) medical studies (5) Cardiology (1) image reconstruction (1) PET-related (15) diagnoses (5) Radiation Therapy (1) AI-based decision support (1) X-ray-related (12) patient information (3) Musculoskeletal functional modelling (1) imaging platforms (1) + 7 others categories (18) + 4 other categories (6) 3.2. Imaging concept integration into the SPHN Schema In total, 30 new medical imaging concepts have been formalized for the SPHN Schema 2025.2 release [ 7 , 8 ], mirroring the DICOM entity-relationship (ER) model (see Table 2 and Fig. 1 ). They cover imaging modalities, concepts related to contrast agents and radiopharmaceuticals, administration procedures, synchronization parameters, image properties and acquisition as well as algorithms used in image processing. Table 2 Levels of the DICOM ER model and corresponding concepts in the SPHN Schema 2025.2 DICOM SPHN Comment Study Clinical Trial Study Medical imaging data may be collected as part of a clinical trial study protocol. This likely involves multiple imaging sessions of multiple patients. Imaging Procedure An imaging procedure used for examination of a body site or function, may entail multiple imaging series. Series Imaging Series A set of medical image slices or frames obtained by a single imaging modality using a single protocol step with predetermined acquisition parameters. Image Imaging Frame A medical image slice or frame in an imaging series, i.e., an image. Whenever possible, existing SPHN concepts were referenced by the extensions to facilitate linkage across schema components, including imaging procedures, body sites or positions, software, or drugs and their administration. This reuse not only increases interoperability across the schema but it also demonstrates the robustness and adaptability of the SPHN Schema to accommodate domain-specific use cases. 3.3. SPHN Semantic Interoperability Framework components Using the SPHN Schema Forge tool [ 3 ], RDF artifacts for the representation, validation, and statistical analysis were generated from a tabular, structured concept model. Furthermore, the SPHN Schema extension was made available for interactive exploration in the SPHN Schema Scope 2 tool. Together, these components establish a strong foundation for integrating and validating medical imaging metadata within the SPHN Semantic Interoperability Framework. 4. Discussion and Conclusions Introducing imaging concepts in the SPHN Schema addresses a gap in the existing interoperability framework. This development enables imaging data to be represented in a FAIR-compliant manner, facilitating semantic interoperability and promoting exchange and reuse. In turn, this creates new opportunities for more comprehensive patient-centric research leveraging the resources medical imaging offers. 4.1. Specific design choices Some design choices deliberately deviate to some extent from the DICOM model to keep changes to the SPHN Schema manageable and the semantics consistent. For example, the introduction of additional DICOM attributes, e.g., to specify a body site of interest in greater detail, would be beneficial but has been postponed due to the larger impact of such changes across the existing schema. “Private attributes” permitted in the DICOM standard were excluded as the meaning of those proprietary data items is often vendor-specific and not interoperable. Furthermore, several DICOM value sets were streamlined to ensure semantically appropriate code usage, e.g., codes from the SNOMED CT specimen-hierarchy unsuitable to specify an imaging view or projection characteristics. Similarly, highly specific coded contrast agent administration routes were omitted due to missing SNOMED CT equivalents. Requesting corresponding SNOMED CT codes is the way forward to achieve full coverage of the original DICOM value sets. 4.2. Outlook Despite the growing amount of medical imaging data and the widespread use of the DICOM standard, the FAIR utilization of these invaluable data resources remains challenging [ 9 ]. The SPHN Schema is released under a permissive license (CC-BY 4.0) and aligns with widely adopted international standards such as SNOMED CT, LOINC, and DICOM - making it available and suitable for national and international use cases. The introduction of medical imaging concepts in the SPHN Schema represents an important step towards FAIR imaging data in Swiss research and beyond. While the work presented here is conceptual, Swiss hospitals are currently establishing extract-transform-load (ETL)-pipelines, so projects using real-world data can soon test the new framework and provide feedback for an iterative evolution of the imaging extension. Complementary efforts to integrate DICOM-metadata into other standards like HL7-FHIR or OMOP [ 10 , 11 ] offer additional opportunities to pick the most suitable model for the intended purpose, including data exchange and analysis-driven research. Taken together, these exciting developments offer the chance for alignment across initiatives, to the benefit of both patients and research. Declarations Participant consent All participants consented to participate in the survey. No identifiable participant-level information was shared. Acknowledgements We thank the SPHN community, our partners at all hospitals involved, the participants of initial survey and workshop, the SPHN Semantic Working Group, the LOOP Zurich, the PHRT initiative, the Helmut Horten Foundation, Patrick Hirschi, Yves Jäggi, Katie Kalt, and Ender Konukoglu for their support and excellent collaboration. References Gaudet-Blavignac C, Raisaro JL, Touré V, Österle S, Crameri K, Lovis CA, National (2021) Semantic-Driven, Three-Pillar Strategy to Enable Health Data Secondary Usage Interoperability for Research Within the Swiss Personalized Health Network: Methodological Study. JMIR Med Inf 9:e27591. 10.2196/27591 Krauss P, Touré V, Gnodtke K, Crameri K, Österle S (2021) DCC Terminology Service—An Automated CI/CD Pipeline for Converting Clinical and Biomedical Terminologies in Graph Format for the Swiss Personalized Health Network. Appl Sci 11:11311. 10.3390/app112311311 Touré V, Unni D, Krauss P, Abdelwahed A, Buchhorn J, Hinderling L, Geiger TR, Österle S (2025) The SPHN Schema Forge – transform healthcare semantics from human-readable to machine-readable by leveraging semantic web technologies. J Biomed Semant 16:9. 10.1186/s13326-025-00330-9 Touré V, Krauss P, Gnodtke K, Buchhorn J, Unni D, Horki P, Raisaro JL, Kalt K, Teixeira D, Crameri K et al (2023) FAIRification of health-related data using semantic web technologies in the Swiss Personalized Health Network. Sci Data 10:127. 10.1038/s41597-023-02028-y National Electrical Manufacturers Association (NEMA). NEMA PS3 / ISO 12052, Digital Imaging and Communications in Medicine (DICOM) Standard [Internet]. Rosslyn, VA, USA: National Electrical Manufacturers Association (2025) Available from: http://www.dicomstandard.org/ Pianykh OS. Digital Imaging and Communications in Medicine (DICOM) [Internet]., Berlin (2012) Heidelberg: Springer Berlin Heidelberg; [cited 2026 Jan 29]. Available from: https://doi.org/10.1007/978-3-642-10850-1 SPHN Interoperability Framework version 2025-2 release · sphn-semantic-framework / SPHN Semantic Interoperability Framework · GitLab [Internet]. GitLab. [cited 2025 Oct 17]. Available from: https://git.dcc.sib.swiss/sphn-semantic-framework/sphn-schema/-/releases/2025-2 The SPHN RDF Schema - pyLODE documentation [Internet]. Swiss Personalized Health Network; [cited 2025 Oct 17]. Available from: https://www.biomedit.ch/rdf/sphn-schema/sphn/2025/2 Mackenzie A, Lewis E, Loveland J (2023) Successes and challenges in extracting information from DICOM image databases for audit and research. Br J Radiol. ;96:20230104. 10.1259/bjr.20230104 . Cited: in:: PMID: 37698251 Park WY, Jeon K, Schmidt TS, Kondylakis H, Alkasab T, Dewey BE, You SC, Nagy P (2024) J Imaging Inf Med 37:899–908. 10.1007/s10278-024-00982-6 . Development of Medical Imaging Data Standardization for Imaging-Based Observational Research: OMOP Common Data Model Extension Iancu A, Bauer J, May MS, Prokosch H-U, Dörfler A, Uder M, Kapsner LA (2024) Large-Scale Integration of DICOM Metadata into HL7-FHIR for Medical Research. Methods Inf Med 63:077–084. 10.1055/a-2521-4250 Footnotes https://sphn-semantic-framework.readthedocs.io/en/latest/concepts_guidelines/imaging_guidelines.html https://schemascope.dcc.sib.swiss/?project=SPHN&version=2025.2 Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8901680","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Method Article","associatedPublications":[],"authors":[{"id":592779809,"identity":"28cef2d5-e6b7-4889-a7eb-bef319d1aa15","order_by":0,"name":"Edwin ter Voert","email":"","orcid":"https://orcid.org/0000-0001-8877-338X","institution":"University of Zurich","correspondingAuthor":false,"prefix":"","firstName":"Edwin","middleName":"ter","lastName":"Voert","suffix":""},{"id":592779810,"identity":"10fe6a7b-edb4-4315-9541-8faf13f9072e","order_by":1,"name":"Harald Witte","email":"","orcid":"https://orcid.org/0000-0002-4421-3580","institution":"Swiss Institute of Bioinformatics","correspondingAuthor":false,"prefix":"","firstName":"Harald","middleName":"","lastName":"Witte","suffix":""},{"id":592779811,"identity":"671f68cf-ea86-4adc-ab45-4500306c6631","order_by":2,"name":"Vasundra Touré","email":"","orcid":"https://orcid.org/0000-0003-4639-4431","institution":"Swiss Institute of Bioinformatics","correspondingAuthor":false,"prefix":"","firstName":"Vasundra","middleName":"","lastName":"Touré","suffix":""},{"id":592779812,"identity":"891903ac-bf12-4d18-8d87-682e23a49df0","order_by":3,"name":"Bjoern Menze","email":"","orcid":"https://orcid.org/0000-0003-4136-5690","institution":"University of Zurich","correspondingAuthor":false,"prefix":"","firstName":"Bjoern","middleName":"","lastName":"Menze","suffix":""},{"id":592779813,"identity":"1bdc5198-f139-4c6e-bb01-477c6e4e9334","order_by":4,"name":"Sabine Österle","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFElEQVRIie2RMUvEMBiGvxC4W1JvjcvlL3xHF4dD/0pCwVus3NhBjoBQF6HrOfkXOnU1JeDUo2vXw1UEcbGLmlonIerokGfJ+0HevO9HAAKBf4jQDIw75+O4doKyQXGvBc1oiQHoMDrxqwU+L4DSXxYn2M/FcLqr7ToDVcza+iHD5er2KjKkz49OhPbscn0u7bYBdbNN6KLB07S0B5JGOVel8cSYM7RRDqrs6ORQo01LypCSikv0NWsfneUN1F1rp73G95W4ZEj6inuLQTekaJcCyYRoNBIsQ4gqTrSnGHZP0rJ7HvMuiV2xZDHs4nL9u4gitS/sYjmfFfX+WWfHQhS7ev/abPzFRr59nOf9QCAQCPyVDx3GWsJNYXeYAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-3248-7899","institution":"Swiss Institute of Bioinformatics","correspondingAuthor":true,"prefix":"","firstName":"Sabine","middleName":"","lastName":"Österle","suffix":""}],"badges":[],"createdAt":"2026-02-17 13:47:39","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8901680/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8901680/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104340067,"identity":"90b4ae08-d827-4aa4-b095-9a19b95eca65","added_by":"auto","created_at":"2026-03-10 16:31:51","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":477221,"visible":true,"origin":"","legend":"\u003cp\u003eSimplified side-by-side comparison of the DICOM ER model (left part) and its alignment with the SPHN Schema (right part).\u003c/p\u003e","description":"","filename":"Fig01DICOMSPHNMedicalImagingv06.png","url":"https://assets-eu.researchsquare.com/files/rs-8901680/v1/c196ec2906faf145c5430b9f.png"},{"id":104340068,"identity":"a52bafd7-0d27-43ac-949a-a7a109d093e5","added_by":"auto","created_at":"2026-03-10 16:31:56","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":623985,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8901680/v1/df5829b6-c58d-4ad5-8d85-49541543c961.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eSeeing is believing - FAIR metadata for medical imaging data in the SPHN Semantic Interoperability Framework\u003c/p\u003e","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eThe Swiss Personalized Health Network (SPHN) aims to improve health data interoperability across Switzerland [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. To ensure consistent, reusable data for both humans and machines, SPHN developed the Semantic Interoperability Framework \u0026ndash; a system of semantic artifacts, including formal concept definitions (building blocks representing specific data elements), Resource Description Framework (RDF) schema specifications, and validation rules, all referring to international standards like Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT) where possible, and supported by a dedicated tool stack [\u003cspan additionalcitationids=\"CR3\" citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eStarting with a limited set of concepts in 2021, the SPHN Schema has expanded step by step to cover a wide range of clinical domains and diverse data sources such as clinical records, trials, registries, patient-reported outcomes, and molecular analyses. Its latest release includes structured representations for imaging data, procedures, and devices, reflecting the critical role of medical imaging. The included metadata descriptors were carefully accessed based on the needs of researchers and availability in the \u0026ldquo;Digital Imaging and Communications in Medicine\u0026rdquo; (DICOM) standard [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e], the \u003cem\u003ede facto\u003c/em\u003e international standard for medical imaging datasets and corresponding metadata. A simplified DICOM model with the real-world entities Patient, Study, Series, and Image is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e (left part).\u003c/p\u003e"},{"header":"2. Methods","content":"\u003cp\u003eAs a starting point, a questionnaire (31 questions plus free-text remarks) was sent to eleven senior imaging experts and decision makers working in a clinical or medical imaging research field, stratified across nine institutions in Switzerland. The response rate was 91% (10/11). Subsequently, an on-site workshop with imaging experts from Swiss hospitals and the Federal Institute of Technology was carried out to align with the needs of researchers, institutions and their priorities for data items to develop. During follow-ups with stakeholders the DICOM metadata of interest and its availability in hospitals could be determined Corresponding DICOM attributes were selected, introduced in formal concept definitions in line with the SPHN Schema and structured in tabular form. This concept specification served as input for the SPHN Schema Forge tool [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e] to build the RDF artifacts.\u003c/p\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e3.1. Implementation scope\u003c/h2\u003e \u003cp\u003eIn alignment with stakeholders\u0026rsquo; requirements (see Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e), four imaging modalities and associated content were prioritized to be included in the SPHN Schema: Computed Tomography (CT), Magnetic Resonance (MR), Positron Emission Tomography (PET), and X-Ray. Details and examples are available in the imaging concepts guidelines of the SPHN Semantic Interoperability Framework documentation\u003csup\u003e1\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eOutcome of the stakeholder survey to identify community needs with respect to medical imaging data. Number of mentions in brackets.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eResearch field\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eResearch topics\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eImaging modalities of interest\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eMetadata areas of interest\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRadiology (5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAlgorithm development (5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMR-related (18)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003escan parameters (6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOncology (1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eimage segmentation (5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCT-related (16)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003emedical studies (5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCardiology (1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eimage reconstruction (1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePET-related (15)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ediagnoses (5)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRadiation Therapy (1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAI-based decision support (1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eX-ray-related (12)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epatient information (3)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMusculoskeletal functional modelling (1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eimaging platforms (1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e+\u0026thinsp;7 others categories (18)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e+\u0026thinsp;4 other categories (6)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e3.2. Imaging concept integration into the SPHN Schema\u003c/h2\u003e \u003cp\u003eIn total, 30 new medical imaging concepts have been formalized for the SPHN Schema 2025.2 release [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e], mirroring the DICOM entity-relationship (ER) model (see Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). They cover imaging modalities, concepts related to contrast agents and radiopharmaceuticals, administration procedures, synchronization parameters, image properties and acquisition as well as algorithms used in image processing.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eLevels of the DICOM ER model and corresponding concepts in the SPHN Schema 2025.2\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDICOM\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSPHN\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eComment\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eStudy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eClinical Trial Study\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMedical imaging data may be collected as part of a clinical trial study protocol. This likely involves multiple imaging sessions of multiple patients.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eImaging Procedure\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAn imaging procedure used for examination of a body site or function, may entail multiple imaging series.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSeries\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eImaging Series\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eA set of medical image slices or frames obtained by a single imaging modality using a single protocol step with predetermined acquisition parameters.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eImaging Frame\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eA medical image slice or frame in an imaging series, i.e., an image.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eWhenever possible, existing SPHN concepts were referenced by the extensions to facilitate linkage across schema components, including imaging procedures, body sites or positions, software, or drugs and their administration. This reuse not only increases interoperability across the schema but it also demonstrates the robustness and adaptability of the SPHN Schema to accommodate domain-specific use cases.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e3.3. SPHN Semantic Interoperability Framework components\u003c/h2\u003e \u003cp\u003eUsing the SPHN Schema Forge tool [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e], RDF artifacts for the representation, validation, and statistical analysis were generated from a tabular, structured concept model. Furthermore, the SPHN Schema extension was made available for interactive exploration in the SPHN Schema Scope\u003csup\u003e2\u003c/sup\u003e tool. Together, these components establish a strong foundation for integrating and validating medical imaging metadata within the SPHN Semantic Interoperability Framework.\u003c/p\u003e \u003c/div\u003e"},{"header":"4. Discussion and Conclusions","content":"\u003cp\u003eIntroducing imaging concepts in the SPHN Schema addresses a gap in the existing interoperability framework. This development enables imaging data to be represented in a FAIR-compliant manner, facilitating semantic interoperability and promoting exchange and reuse. In turn, this creates new opportunities for more comprehensive patient-centric research leveraging the resources medical imaging offers.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e4.1. Specific design choices\u003c/h2\u003e \u003cp\u003eSome design choices deliberately deviate to some extent from the DICOM model to keep changes to the SPHN Schema manageable and the semantics consistent.\u003c/p\u003e \u003cp\u003eFor example, the introduction of additional DICOM attributes, e.g., to specify a body site of interest in greater detail, would be beneficial but has been postponed due to the larger impact of such changes across the existing schema. \u0026ldquo;Private attributes\u0026rdquo; permitted in the DICOM standard were excluded as the meaning of those proprietary data items is often vendor-specific and not interoperable. Furthermore, several DICOM value sets were streamlined to ensure semantically appropriate code usage, e.g., codes from the SNOMED CT specimen-hierarchy unsuitable to specify an imaging view or projection characteristics. Similarly, highly specific coded contrast agent administration routes were omitted due to missing SNOMED CT equivalents. Requesting corresponding SNOMED CT codes is the way forward to achieve full coverage of the original DICOM value sets.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e4.2. Outlook\u003c/h2\u003e \u003cp\u003eDespite the growing amount of medical imaging data and the widespread use of the DICOM standard, the FAIR utilization of these invaluable data resources remains challenging [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. The SPHN Schema is released under a permissive license (CC-BY 4.0) and aligns with widely adopted international standards such as SNOMED CT, LOINC, and DICOM - making it available and suitable for national and international use cases. The introduction of medical imaging concepts in the SPHN Schema represents an important step towards FAIR imaging data in Swiss research and beyond. While the work presented here is conceptual, Swiss hospitals are currently establishing extract-transform-load (ETL)-pipelines, so projects using real-world data can soon test the new framework and provide feedback for an iterative evolution of the imaging extension. Complementary efforts to integrate DICOM-metadata into other standards like HL7-FHIR or OMOP [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e] offer additional opportunities to pick the most suitable model for the intended purpose, including data exchange and analysis-driven research.\u003c/p\u003e \u003cp\u003eTaken together, these exciting developments offer the chance for alignment across initiatives, to the benefit of both patients and research.\u003c/p\u003e \u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003eParticipant consent All participants consented to participate in the survey. No identifiable participant-level information was shared.\u003c/p\u003e\u003ch2\u003eAcknowledgements\u003c/h2\u003e \u003cp\u003eWe thank the SPHN community, our partners at all hospitals involved, the participants of initial survey and workshop, the SPHN Semantic Working Group, the LOOP Zurich, the PHRT initiative, the Helmut Horten Foundation, Patrick Hirschi, Yves J\u0026auml;ggi, Katie Kalt, and Ender Konukoglu for their support and excellent collaboration.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eGaudet-Blavignac C, Raisaro JL, Tour\u0026eacute; V, \u0026Ouml;sterle S, Crameri K, Lovis CA, National (2021) Semantic-Driven, Three-Pillar Strategy to Enable Health Data Secondary Usage Interoperability for Research Within the Swiss Personalized Health Network: Methodological Study. JMIR Med Inf 9:e27591. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.2196/27591\u003c/span\u003e\u003cspan address=\"10.2196/27591\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKrauss P, Tour\u0026eacute; V, Gnodtke K, Crameri K, \u0026Ouml;sterle S (2021) DCC Terminology Service\u0026mdash;An Automated CI/CD Pipeline for Converting Clinical and Biomedical Terminologies in Graph Format for the Swiss Personalized Health Network. Appl Sci 11:11311. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/app112311311\u003c/span\u003e\u003cspan address=\"10.3390/app112311311\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTour\u0026eacute; V, Unni D, Krauss P, Abdelwahed A, Buchhorn J, Hinderling L, Geiger TR, \u0026Ouml;sterle S (2025) The SPHN Schema Forge \u0026ndash; transform healthcare semantics from human-readable to machine-readable by leveraging semantic web technologies. J Biomed Semant 16:9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s13326-025-00330-9\u003c/span\u003e\u003cspan address=\"10.1186/s13326-025-00330-9\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTour\u0026eacute; V, Krauss P, Gnodtke K, Buchhorn J, Unni D, Horki P, Raisaro JL, Kalt K, Teixeira D, Crameri K et al (2023) FAIRification of health-related data using semantic web technologies in the Swiss Personalized Health Network. Sci Data 10:127. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41597-023-02028-y\u003c/span\u003e\u003cspan address=\"10.1038/s41597-023-02028-y\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNational Electrical Manufacturers Association (NEMA). NEMA PS3 / ISO 12052, Digital Imaging and Communications in Medicine (DICOM) Standard [Internet]. Rosslyn, VA, USA: National Electrical Manufacturers Association (2025) Available from: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://www.dicomstandard.org/\u003c/span\u003e\u003cspan address=\"http://www.dicomstandard.org/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePianykh OS. Digital Imaging and Communications in Medicine (DICOM) [Internet]., Berlin (2012) Heidelberg: Springer Berlin Heidelberg; [cited 2026 Jan 29]. Available from: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1007/978-3-642-10850-1\u003c/span\u003e\u003cspan address=\"10.1007/978-3-642-10850-1\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSPHN Interoperability Framework version 2025-2 release \u0026middot; sphn-semantic-framework / SPHN Semantic Interoperability Framework \u0026middot; GitLab [Internet]. GitLab. [cited 2025 Oct 17]. Available from: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://git.dcc.sib.swiss/sphn-semantic-framework/sphn-schema/-/releases/2025-2\u003c/span\u003e\u003cspan address=\"https://git.dcc.sib.swiss/sphn-semantic-framework/sphn-schema/-/releases/2025-2\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThe SPHN RDF Schema - pyLODE documentation [Internet]. Swiss Personalized Health Network; [cited 2025 Oct 17]. Available from: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.biomedit.ch/rdf/sphn-schema/sphn/2025/2\u003c/span\u003e\u003cspan address=\"https://www.biomedit.ch/rdf/sphn-schema/sphn/2025/2\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMackenzie A, Lewis E, Loveland J (2023) Successes and challenges in extracting information from DICOM image databases for audit and research. Br J Radiol. ;96:20230104. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1259/bjr.20230104\u003c/span\u003e\u003cspan address=\"10.1259/bjr.20230104\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Cited: in:: PMID: 37698251\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePark WY, Jeon K, Schmidt TS, Kondylakis H, Alkasab T, Dewey BE, You SC, Nagy P (2024) J Imaging Inf Med 37:899\u0026ndash;908. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s10278-024-00982-6\u003c/span\u003e\u003cspan address=\"10.1007/s10278-024-00982-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Development of Medical Imaging Data Standardization for Imaging-Based Observational Research: OMOP Common Data Model Extension\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIancu A, Bauer J, May MS, Prokosch H-U, D\u0026ouml;rfler A, Uder M, Kapsner LA (2024) Large-Scale Integration of DICOM Metadata into HL7-FHIR for Medical Research. Methods Inf Med 63:077\u0026ndash;084. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1055/a-2521-4250\u003c/span\u003e\u003cspan address=\"10.1055/a-2521-4250\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"},{"header":"Footnotes","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://sphn-semantic-framework.readthedocs.io/en/latest/concepts_guidelines/imaging_guidelines.html\u003c/span\u003e\u003cspan address=\"https://sphn-semantic-framework.readthedocs.io/en/latest/concepts_guidelines/imaging_guidelines.html\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://schemascope.dcc.sib.swiss/?project=SPHN\u0026amp;version=2025.2\u003c/span\u003e\u003cspan address=\"https://schemascope.dcc.sib.swiss/?project=SPHN\u0026amp;version=2025.2\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Swiss Institute of Bioinformatics","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"FAIR, DICOM, Medical imaging, Metadata, Semantics, Semantic interoperability, Health data interoperability","lastPublishedDoi":"10.21203/rs.3.rs-8901680/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8901680/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMedical imaging is vital to modern healthcare, supporting diagnostics, treatment, and research. To integrate imaging data within the Swiss Personalized Health Network (SPHN), we developed an SPHN RDF Schema extension for standardized and structured imaging metadata. Built on the FAIR (Findable Accessible, Interoperable, Reusable) principles and established standards like DICOM and SNOMED CT, this extension models essential imaging information and links it to related clinical data, such as diagnoses, patient visits, and biosamples. This enhances semantic coherence and addresses interoperability gaps, thereby enabling applications in clinical research and precision medicine using the rich resources medical imaging data represents.\u003c/p\u003e","manuscriptTitle":"Seeing is believing - FAIR metadata for medical imaging data in the SPHN Semantic Interoperability Framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-10 16:31:46","doi":"10.21203/rs.3.rs-8901680/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"4f8bbadd-9236-4dcf-8647-17dae9973331","owner":[],"postedDate":"March 10th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":63075006,"name":"Personalized Medicine"},{"id":63075007,"name":"Medical Informatics"},{"id":63075008,"name":"Information Retrieval and Management"}],"tags":[],"updatedAt":"2026-03-10T16:31:46+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-10 16:31:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8901680","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8901680","identity":"rs-8901680","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}