Leveraging GPT-4o for Automated Extraction and Categorization of CAD-RADS Features From Free-Text Coronary CT Angiography Reports: Diagnostic Study
The GPT-4o model efficiently and accurately converts CCTA free-text reports into structured data, excelling in CAD-RADS classification, plaque burden assessment, and detection of myocardial bridges and calcified plaques.
Authors
- Jie Sun
- Yiqing Yang (ORCID: https://orcid.org/0009-0003-2888-7846)
- Zhanao Meng (ORCID: https://orcid.org/0009-0001-1872-0976)
- Mengshi Dong
- Youmei Chen
- Jie Qin (ORCID: https://orcid.org/0000-0002-4088-3296)
- Abudushalamu Muhetaier
- Chao Li
Institutions
- Sun Yat-sen University (CN)
- Third Affiliated Hospital of Sun Yat-sen University (CN)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-06-17
- DOI
- https://doi.org/10.2196/70967
- Citations
- 1
- Primary Topic
- Advanced X-ray and CT Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.67