On embedding-based automatic mapping of clinical classification system: handling linguistic variations and granular inconsistencies
Our findings demonstrate that integrating the representational power of pretrained encoders with LLM reasoning offers a robust, scalable strategy for automatic ICD mapping.
Authors
- Oliver Obst (ORCID: https://orcid.org/0000-0002-8284-2062)
- Jeewani Anupama Ginige (ORCID: https://orcid.org/0000-0002-6695-6983)
- Santosh Purja Pun (ORCID: https://orcid.org/0000-0002-9820-2553)
- Jim Basilakis
Institutions
- Western Sydney University (AU)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2026-01-12
- DOI
- https://doi.org/10.1093/jamia/ocag004
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00