Assessing the performance of ChatGPT and Bard/Gemini against radiologists for Prostate Imaging-Reporting and Data System classification based on prostate multiparametric MRI text reports

Abstract

This study highlights the limitations of LLMs in accurately classifying PI-RADS categories from clinical text reports. While the performance of LLMs has improved with newer versions, caution is warranted before integrating such technologies into clinical practice.