A pilot feasibility study comparing large language models in extracting key information from ICU patient text records from an Irish population
Differences exist in large language model performance in readability, organisation, succinctness, and sequencing of clinical events compared to others. All encountered issues with narrative coherence and omitted key clinical data and only moderately captured all clinically meaningful data in the correct order. However, these technologies suggest future potential for creating succinct discharge summaries.
Authors
- Michael G. Madden (ORCID: https://orcid.org/0000-0002-4443-7285)
- Rachel Jooste (ORCID: https://orcid.org/0000-0002-6375-6337)
- Bairbre McNicholas (ORCID: https://orcid.org/0000-0001-9524-4021)
- Conor Judge (ORCID: https://orcid.org/0000-0001-9473-2920)
- Ciara Hanley (ORCID: https://orcid.org/0000-0001-6033-6786)
- Peter Moran
- John G. Laffey (ORCID: https://orcid.org/0000-0002-1246-9573)
- John Ryan (ORCID: https://orcid.org/0000-0002-2805-8808)
- Sean D Hartigan (ORCID: https://orcid.org/0009-0006-7805-9821)
- John Bates
- Ciprian Niță
- E Urquhart
Institutions
- Ollscoil na Gaillimhe – University of Galway (IE)
- University Hospital Galway (IE)
Publication Details
- Journal
- Intensive Care Medicine Experimental
- Published
- 2024-08-16
- DOI
- https://doi.org/10.1186/s40635-024-00656-1
- Citations
- 15
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 5.21