Institution-Specific LLM Prompting Recovers PHI That De-identification Systems and Their Gold Standards Both Miss
Large language models outperform traditional de-identification tools by mastering local clinical context.
Secondary use of electronic health records requires de-identification, yet existing systems miss \emph{institutionally situated} protected health information (PHI) such as hospital abbreviations, building names, and internal codes whose status is locally determined. We ask whethe...
ArXiv CS.CL
Source
Generated insight by OnAirToday AI
This research demonstrates that LLMs can identify context-dependent protected health information that traditional automated systems consistently overlook. By leveraging institution-specific prompting, healthcare providers can achieve significantly higher recall rates, closing critical security gaps in medical record de-identification.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.