A hybrid framework with large language models for rare disease phenotyping
The hybrid approach combining dictionary-based NLP tools with LLMs shows great promise for improving rare disease identification from unstructured clinical reports. By leveraging the strengths of both techniques, the method demonstrates superior performance and the potential to uncover hidden rare disease cases. Further research is needed to address limitations related to ontology mapping and overlapping case identification, and to integrate the approach into clinical practice for early diagnosis and improved patient outcomes.
Authors
- Chengliang Dai (ORCID: https://orcid.org/0000-0002-9931-5437)
- Phil Scordis (ORCID: https://orcid.org/0000-0003-3477-9959)
- Hang Dong (ORCID: https://orcid.org/0000-0001-6828-6891)
- Honghan Wu (ORCID: https://orcid.org/0000-0002-0213-5668)
- Zexi Li
- R Li
- Waqar Ali (ORCID: https://orcid.org/0000-0002-6308-8682)
- Jinge Wu
- Arijit Patra
- Haowei Wang (ORCID: https://orcid.org/0009-0004-1186-4303)
Institutions
- University of Exeter (GB)
- University of Oxford (GB)
- UCB Pharma (United Kingdom) (GB)
- Health Data Research UK (GB)
- University College London (GB)
- University of Glasgow (GB)
Publication Details
- Journal
- BMC Medical Informatics and Decision Making
- Published
- 2024-10-08
- DOI
- https://doi.org/10.1186/s12911-024-02698-7
- Citations
- 16
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 3.74
Funders
- National Institute for Health and Care Research
- Department of Health and Social Care
- Medical Research Council