GPT-4 as a Clinical Decision Support Tool in Ischemic Stroke Management: Evaluation Study
This study demonstrates the potential of GPT-4 as a viable clinical decision-support tool in the management of acute stroke. Its ability to provide explainable recommendations without requiring structured data input aligns well with the routine workflows of treating physicians. However, the tendency toward more aggressive treatment recommendations highlights the importance of human oversight in clinical decision-making. Future studies should focus on prospective validations and exploring the safe integration of such artificial intelligence tools into clinical practice.
Authors
- Mark Katson (ORCID: https://orcid.org/0000-0002-5568-998X)
- Shiran Bookstein Peretz (ORCID: https://orcid.org/0000-0002-9045-9987)
- Shahar Shelly (ORCID: https://orcid.org/0000-0002-3585-1687)
- Dvir Aran (ORCID: https://orcid.org/0000-0001-6334-5039)
- Michal Cohen-Shelly (ORCID: https://orcid.org/0009-0007-6532-9252)
- Amit-Haim Shmilovitch (ORCID: https://orcid.org/0009-0008-7587-7073)
Institutions
- Tel Aviv University (IL)
- Technion – Israel Institute of Technology (IL)
- Sheba Medical Center (IL)
- Rambam Health Care Campus (IL)
- Assaf Harofeh Medical Center (IL)
Publication Details
- Journal
- JMIR AI
- Published
- 2025-03-07
- DOI
- https://doi.org/10.2196/60391
- Citations
- 4
- Primary Topic
- Acute Ischemic Stroke Management
- Type
- article
- Field-Weighted Citation Impact
- 5.42