ARKE: An ontology-driven framework for automated mapping of local radiology procedure terms to the LOINC-RadLex playbook using large language model.
Authors
Affiliations (5)
Affiliations (5)
- Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, The Republic of Korea; Yonsei Institute for Digital Health, Yonsei University, Seoul, The Republic of Korea.
- Department of Radiology, Severance Hospital, Yonsei University College of Medicine, Seoul, The Republic of Korea.
- Department of Medicine, Yonsei University College of Medicine, Seoul, The Republic of Korea.
- Department of Radiology, Seoul National University College of Medicine, Seoul, South Korea; Department of Radiology, National Jewish Health, Denver, CO, USA.
- Department of Biomedical Systems Informatics, Yonsei University College of Medicine, Seoul, The Republic of Korea; Yonsei Institute for Digital Health, Yonsei University, Seoul, The Republic of Korea. Electronic address: [email protected].
Abstract
To develop an ontology-driven framework that standardizes heterogeneous local radiology procedure names by decomposing them into semantic components and aligning them to LOINC/RSNA Radiology Playbook codes using constrained large language model (LLM)-based parsing and selection. Radiology procedure names from two tertiary hospitals in Korea were parsed into semantic components using LLM prompting with retrieval-augmented generation, aligned with the LOINC/RSNA Radiology Playbook (version 2.80). Ontology-based similarity scoring quantify correspondence between parsed components and Playbook candidates' attributes, and retrieve the Top 10 candidates, followed by LLM-based selection within this candidate set. Performance was evaluated against direct Playbook code name-based mapping and conventional similarity metrics using a radiologist-curated gold reference. A total of 3,326 local procedure names were analyzed. Ontology-based mapping approach substantially outperformed direct Playbook code name mapping across all evaluation metrics. At the candidate retrieval stage, ontology-based attribute matching achieved recall@5 of up to 0.78 (internal) and 0.89 (external), compared with 0.51 and 0.47 for direct mapping. After LLM-based selection, the ontology-based approach achieved a final selection recall@1 of up to 0.70 (internal) and 0.81 (external), exceeding direct mapping (0.48 and 0.50) more than 20 percentage points in both settings (p < 0.001). Decomposing procedure names into ontology-grounded semantic components enables robust handling of heterogeneous local terminology, while constraining LLM reasoning to structured selection tasks mitigates hallucination and preserves semantic fidelity. Ontology-driven knowledge encoding provides a scalable and reliable approach to standardizing radiology procedure names, supporting cross-institutional interoperability and secondary data use of imaging research.