Automated redaction of names in adverse event reports using transformer-based neural networks
Automated redaction of names in free-text narratives of adverse event reports can achieve sufficient recall including shorter tokens like patient initials. In-depth review shows that the rare leaks that occur tend not to compromise patient confidentiality. Precision and false positive rates are acceptable with almost all clinically relevant information retained.
Authors
- Eva-Lisa Meldau (ORCID: https://orcid.org/0000-0003-0268-7769)
- G. Niklas Norén (ORCID: https://orcid.org/0000-0002-4595-230X)
- Shachi Bista (ORCID: https://orcid.org/0000-0001-8319-4936)
- Carlos Melgarejo-González (ORCID: https://orcid.org/0009-0006-2742-1667)
Institutions
- Uppsala Monitoring Centre (SE)
Publication Details
- Journal
- BMC Medical Informatics and Decision Making
- Published
- 2024-12-23
- DOI
- https://doi.org/10.1186/s12911-024-02785-9
- Citations
- 2
- Primary Topic
- Pharmacovigilance and Adverse Drug Reactions
- Type
- article
- Field-Weighted Citation Impact
- 0.70
Funders
- Eli Lilly and Company