PCEtoFHIR: Decomposition of Postcoordinated SNOMED CT Expressions for Storage as HL7 FHIR Resources
Notice bibliographique
Résumé
BACKGROUND: To ensure interoperability, both structural and semantic standards must be followed. For exchanging medical data between information systems, the structural standard FHIR (Fast Healthcare Interoperability Resources) has recently gained popularity. Regarding semantic interoperability, the reference terminology SNOMED Clinical Terms (SNOMED CT), as a semantic standard, allows for postcoordination, offering advantages over many other vocabularies. These postcoordinated expressions (PCEs) make SNOMED CT an expressive and flexible interlingua, allowing for precise coding of medical facts. However, this comes at the cost of increased complexity, as well as challenges in storage and processing. Additionally, the boundary between semantic (terminology) and structural (information model) standards becomes blurred, leading to what is known as the TermInfo problem. Although often viewed critically, the TermInfo overlap can also be explored for its potential benefits, such as enabling flexible transformation of parts of PCEs. OBJECTIVE: In this paper, an alternative solution for storing PCEs is presented, which involves combining them with the FHIR data model. Ultimately, all components of a PCE should be expressible solely through precoordinated concepts that are linked to the appropriate elements of the information model. METHODS: The approach involves storing PCEs decomposed into their components in alignment with FHIR resources. By utilizing the Web Ontology Language (OWL) to generate an OWL ClassExpression, and combining it with an external reasoner and semantic similarity measures, a precoordinated SNOMED CT concept that most accurately describes the PCE is identified as a Superconcept. In addition, the nonmatching attribute relationships between the Superconcept and the PCE are identified as the "Delta." Once SNOMED CT attributes are manually mapped to FHIR elements, FHIRPath expressions can be defined for both the Superconcept and the Delta, allowing the identified precoordinated codes to be stored within FHIR resources. RESULTS: A web application called PCEtoFHIR was developed to implement this approach. In a validation process with 600 randomly selected precoordinated concepts, the formal correctness of the generated OWL ClassExpressions was verified. Additionally, 33 PCEs were used for two separate validation tests. Based on these validations, it was demonstrated that a previously proposed semantic similarity calculation is suitable for determining the Superconcept. Additionally, the 33 PCEs were used to confirm the correct functioning of the entire approach. Furthermore, the FHIR StructureMaps were reviewed and deemed meaningful by FHIR experts. CONCLUSIONS: PCEtoFHIR offers services to decompose PCEs for storage within FHIR resources. When creating structure mappings for specific subdomains of SNOMED CT concepts (eg, allergies) to desired FHIR profiles, the use of SNOMED CT Expression Templates has proven highly effective. Domain experts can create templates with appropriate mappings, which can then be easily reused in a constrained manner by end users.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,004 | 0,009 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,001 |
| Méta-épidémiologie (sens large) | 0,001 | 0,002 |
| Bibliométrie | 0,003 | 0,002 |
| Études des sciences et des technologies | 0,001 | 0,001 |
| Communication savante | 0,005 | 0,006 |
| Science ouverte | 0,002 | 0,004 |
| Intégrité de la recherche | 0,001 | 0,002 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,019 | 0,008 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».