Large Language Models–Supported Thrombectomy Decision-Making in Acute Ischemic Stroke Based on Radiology Reports: Feasibility Qualitative Study
The LLM achieved promising accuracy in determining the eligibility of patients with AIS for MT based on radiology reports and clinical information. Our results underscore the potential of LLMs for radiological and medical data integration. This investigation should serve as a stimulus for further clinical applications of LLMs, in which this AI should be used as an augmented supporting system for human decision-making.
Authors
- Johannes Bremm (ORCID: https://orcid.org/0000-0002-6081-1070)
- Christoph Kabbasch (ORCID: https://orcid.org/0000-0003-3712-2258)
- Michael Schönfeld (ORCID: https://orcid.org/0000-0003-2096-3448)
- Kai Roman Laukamp (ORCID: https://orcid.org/0000-0002-5600-5914)
- Thorsten Persigehl (ORCID: https://orcid.org/0000-0001-5928-4405)
- Robert Hahnfeldt (ORCID: https://orcid.org/0000-0001-7997-3216)
- Marc Schlamann (ORCID: https://orcid.org/0000-0002-7734-611X)
- Andra-Iza Iuga (ORCID: https://orcid.org/0000-0002-3694-0235)
- Philipp Fervers (ORCID: https://orcid.org/0000-0003-3663-3486)
- David Maintz (ORCID: https://orcid.org/0000-0002-8942-3776)
- Simon Lennartz (ORCID: https://orcid.org/0000-0002-3254-4809)
- Lukas Goertz
- Jonathan Kottlors (ORCID: https://orcid.org/0000-0001-5021-6895)
- David Zopfs (ORCID: https://orcid.org/0000-0001-9978-7453)
- Oezguer A. Onur (ORCID: https://orcid.org/0000-0001-8336-7075)
Institutions
- University of Cologne (DE)
- University Hospital Cologne (DE)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-02-13
- DOI
- https://doi.org/10.2196/48328
- Citations
- 10
- Primary Topic
- Acute Ischemic Stroke Management
- Type
- article
- Field-Weighted Citation Impact
- 13.54