Extracting Pulmonary Embolism Diagnoses From Radiology Impressions Using GPT-4o: Large Language Model Evaluation Study
The GPT-4o model provides an effective solution for the automatic extraction of PE diagnoses from radiology reports, offering a reliable tool that aids timely and accurate clinical decision-making. This approach has the potential to significantly improve patient outcomes by expediting diagnosis and treatment pathways for critical conditions like PE.
Authors
- Ajit Shukla
- Kacie Dougherty (ORCID: https://orcid.org/0000-0001-6295-0026)
- Mohammed A. Mahyoub (ORCID: https://orcid.org/0000-0002-0808-3205)
Institutions
- Binghamton University (US)
- Virtua Health (US)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-04-09
- DOI
- https://doi.org/10.2196/67706
- Citations
- 4
- Primary Topic
- Venous Thromboembolism Diagnosis and Management
- Type
- article
- Field-Weighted Citation Impact
- 7.48