Large Language Models for Health Knowledge Modelling in Data Interoperability: A Scoping Review of Methods, Standards, and Applications
Clinical Snapshot
PICO Framework
| P — Population | Healthcare systems and data requiring semantic interoperability |
| I — Intervention | Large Language Models (LLMs) for health knowledge modelling |
| C — Comparator | Manual ontology mapping and traditional automated methods |
| O — Outcomes | Automation efficiency, mapping precision, scalability across health data standards |
Bottom Line
This scoping review identifies promising applications of large language models for automating health data interoperability tasks, particularly in ontology mapping and terminology alignment across standards like FHIR and OMOP. However, the evidence base remains limited with only 20 relevant studies identified. The review's methodology has significant limitations including a narrow search strategy and lack of quality assessment. While LLMs show potential for improving efficiency and precision in semantic mapping tasks, the authors appropriately conclude that standardised evaluation benchmarks and explainable frameworks are essential before trustworthy clinical adoption. Australian healthcare organisations considering LLM implementation for data interoperability should await more robust evidence and established evaluation standards before large-scale deployment.
Key Findings
P Value: Not applicable for scoping review
Effect Size: Not quantified - qualitative synthesis only
Primary Outcome: LLM applications show potential for automating semantic interoperability in health informatics
Nnt Or Sensitivity: 20 studies identified from 166 records (12% inclusion rate)
Confidence Interval: Not provided
Clinical Application
Moderate - requires technical expertise and standardised evaluation frameworks before widespread implementation Relevant to Australian Digital Health Agency initiatives, My Health Record interoperability, and FHIR implementation across Australian healthcare systems Healthcare organisations implementing electronic health records and seeking data interoperability solutions
Abstract
Achieving interoperability in healthcare requires semantic alignment of data with standards such as SNOMED CT, LOINC, and FHIR. Manual ontology mapping is slow and inconsistent. Evolving Large Language Models (LLMs) can automate knowledge modelling and data harmonisation. This review explores how LLMs are applied to enhance or automate health knowledge modelling for data interoperability. Following PRISMA-ScR guidance, PubMed and Compendex were searched. Studies applying LLMs to ontology alignment, terminology mapping, schema integration, or knowledge-graph construction were included. From 166 records, 20 studies met the inclusion criteria. Most used GPT-4 or BERT-derived models with retrieval-augmented or embedding-based methods. Reported gains included automation, improved mapping precision, and scalability across standards such as FHIR, OMOP, and UMLS. LLMs show strong potential for automating semantic interoperability in health informatics. Standardised evaluation benchmarks and explainable frameworks are essential for trustworthy adoption.
References
- 1.Pournik, O., Abbasi, S. F., Ding, X., Mahmoodi, N., Allington, R., Peltonen, L. M., Gallos, P., Ghalichi, L., & Arvanitis, T. N. (2026). Large Language Models for Health Knowledge Modelling in Data Interoperability: A Scoping Review of Methods, Standards, and Applications. Studies in Health Technology and Informatics. https://doi.org/10.3233/SHTI260406
Related Research
Journal of medical Internet research
Advancing Human-Centered AI in Clinical Decision Support: Sociocognitive Human-in-the-Loop Study in HIV Care
2 Aug 2026
Neurological research
Federated deep learning model for epilepsy seizure detection using electroencephalogram (EEG) signal
2 Aug 2026
Neural networks : the official journal of the International Neural Network Society
MFBD: Model-free backdoor defense based on vision-language pre-trained models
2 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service