Stroke Etiology Prediction Utilizing GPT-4 (P9-14.002)
Based on our previous study to localize stroke lesions, we tested GPT-4 to predict stroke etiology using several key elements: brain imaging, brain vessel imaging, neck vessel imaging, transthoracic echocardiogram (TTE), and history of atrial flutter/fibrillation (AFL/AF).
Authors
- Jung-Hyun Lee (ORCID: https://orcid.org/0000-0001-7751-792X)
- Robert A. McDougal (ORCID: https://orcid.org/0000-0001-6394-3127)
- Sailaja Vasireddy
- Steven R. Levine (ORCID: https://orcid.org/0000-0002-7451-7534)
- William W. Lytton (ORCID: https://orcid.org/0000-0002-3727-2849)
- Sérgio Castro
Institutions
- SUNY Downstate Health Sciences University (US)
- Yale University (US)
- Kings County Hospital Center (US)
Publication Details
- Journal
- Neurology
- Published
- 2025-04-07
- DOI
- https://doi.org/10.1212/wnl.0000000000211572
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00