Automating the extraction of otology symptoms from clinic letters: a methodological study using natural language processing
NLP models for symptom extraction and contextualisation were successfully created and shown to perform well on real life data. Refinement is needed to produce models that can run without manual review. Downstream applications for these models include deep semantic searching in electronic health records, cohort identification for clinical trials and facilitating research into hearing loss phenotypes. Further testing of the external validity of the developed models is required.
Authors
- Xi Bai (ORCID: https://orcid.org/0000-0002-2177-8458)
- Talisa Ross (ORCID: https://orcid.org/0000-0003-4211-6418)
- Marina Forbes (ORCID: https://orcid.org/0000-0002-0753-297X)
- Nikhil Joshi (ORCID: https://orcid.org/0000-0001-9258-4960)
- Nishchay Mehta (ORCID: https://orcid.org/0000-0001-9317-3055)
- Liam Barrett (ORCID: https://orcid.org/0000-0002-8201-7281)
- Watjana Lilaonitkul (ORCID: https://orcid.org/0000-0002-1742-7583)
- Richard Dobson (ORCID: https://orcid.org/0000-0003-4224-9245)
- Anne GM Schilder (ORCID: https://orcid.org/0000-0002-5496-4580)
- Kawsar Noor (ORCID: https://orcid.org/0000-0003-0052-2573)
Institutions
- Energy Institute (GB)
- University College London Hospitals NHS Foundation Trust (GB)
- UCL Biomedical Research Centre (GB)
- Eastman Dental Hospital (GB)
- University College London (GB)
Publication Details
- Journal
- BMC Medical Informatics and Decision Making
- Published
- 2025-09-29
- DOI
- https://doi.org/10.1186/s12911-025-03180-8
- Citations
- 1
- Primary Topic
- Nursing Diagnosis and Documentation
- Type
- article
- Field-Weighted Citation Impact
- 5.53
Funders
- National Institute for Health and Care Research
- Department of Health and Social Care
- University College London Hospitals NHS Foundation Trust