Annotation of epilepsy clinic letters for natural language processing
The synthetic letters, annotations, and annotation guidelines have been made freely available. To our knowledge, this is the first publicly available set of annotated epilepsy clinic letters and guidelines that can be used for NLP researchers with minimum epilepsy knowledge. The IAA results show that clinical text annotation tasks are difficult and require a gold standard to be arranged by researcher consensus. The results for ExECTv2, our automated epilepsy NLP pipeline, extracted detailed epilepsy information from unstructured epilepsy letters with more accuracy than human annotators, further confirming the utility of NLP for clinical and research applications.
Authors
- Beata Fonferko‐Shadrach (ORCID: https://orcid.org/0000-0003-3282-9502)
- Jonathan Hawken (ORCID: https://orcid.org/0000-0003-1184-552X)
- Huw Strafford (ORCID: https://orcid.org/0000-0003-2147-3969)
- William Owen Pickrell (ORCID: https://orcid.org/0000-0003-4396-5657)
- Luke Shrimpton
- Arron Lacey (ORCID: https://orcid.org/0000-0001-7983-8073)
- Robert Powell (ORCID: https://orcid.org/0000-0002-9768-1142)
- Jenny Edwards (ORCID: https://orcid.org/0000-0002-7105-997X)
- Catharine P. White
- Carys Jones
- I. M. S. Sawhney (ORCID: https://orcid.org/0000-0001-6554-5472)
- Sharon Brown
- Russell Khan
Institutions
- Swansea Bay University Health Board (GB)
- Swansea University (GB)
Publication Details
- Journal
- Journal of Biomedical Semantics
- Published
- 2024-09-14
- DOI
- https://doi.org/10.1186/s13326-024-00316-z
- Citations
- 2
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.47
Funders
- Epilepsy Research UK