We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Advancing radiology reporting with large language models: Is GPT- 4 the LI- RADS game changer or just a wild card?
- Authors
Díaz González, Álvaro; Forner, Alejandro; Turnes, Juan
- Abstract
The article discusses the challenges faced by the field of radiology in standardizing and extracting structured data from free-text reports. The Liver Imaging Reporting and Data System (LI-RADS) was developed to address these challenges, but its use is not universal and adherence is suboptimal. The article highlights a study that used GPT-4, a large language model, to accurately extract LI-RADS features from multilingual free-text reports, demonstrating the potential of these models to enhance the efficiency and accuracy of radiology reporting. The study's methodology and transparency in sharing resources set a model for future research in the field. However, the study also acknowledges the limitations and potential risks of using large language models in healthcare settings.
- Subjects
LANGUAGE models; RADIOLOGY
- Publication
Liver International, 2024, Vol 44, Issue 7, p1575
- ISSN
1478-3223
- Publication type
Article
- DOI
10.1111/liv.15952