Quality and efficiency of integrating customised large language model-generated summaries versus physician-written summaries: a validation study
LLM-generated summaries are comparable to physician-written summaries in completeness and correctness, although slightly less concise. With a clear time-saving benefit, LLMs could help reduce clinicians' administrative burden without compromising summary quality.
Authors
- Job Nicolaas Doornberg (ORCID: https://orcid.org/0000-0002-1270-2742)
- Jessica D. Workum (ORCID: https://orcid.org/0000-0002-4134-0242)
- Rosanne C. Schoonbeek (ORCID: https://orcid.org/0000-0002-3103-943X)
- Anne Hannah Hoekman (ORCID: https://orcid.org/0009-0006-5308-4211)
- Stephanie C. E. Schuit
- Charlotte M. H. H. T. Bootsma-Robroeks
- Tom P. van der Laan
- Tarannom Mehri
Institutions
- University Medical Center Groningen (NL)
- Erasmus MC (NL)
- Elisabeth-TweeSteden Ziekenhuis (NL)
- Erasmus University Rotterdam (NL)
Publication Details
- Journal
- BMJ Open
- Published
- 2025-09-01
- DOI
- https://doi.org/10.1136/bmjopen-2025-099301
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00