Utilising large language models to improve comprehension of breast imaging reports
Hemal Grover, New York / United States
- To evaluate the performance of large language models (like ChatGPT and Gemini in improving the readability of actionable breast imaging reports (ie BIRADS 3, 4 and 5).
- To evaluate the accuracy of LLM-generated layperson reports.
- To compare the performance of ChatGPT and Gemini.