A recent study published in Current Problems in Diagnostic Radiology compared the performance of OpenAI’s ChatGPT and Google Bard in suggesting appropriate urologic imaging methods based on American College of Radiology (ACR) criteria. Led by researchers from the University of Toledo, the study found that both chatbots demonstrated an appropriate imaging modality rate of over 60% and showed no significant difference in the proportion of correct imaging modality selected.
Despite this, the study highlighted that both chatbots lacked consistent accuracy, emphasizing the need for further development before their implementation in clinical settings.
While ChatGPT and Bard provided usually appropriate imaging modality responses in 62% of urologic clinical scenarios, the study noted no significant differences between the chatbots’ performances. However, ChatGPT produced shorter responses and had a slightly longer response time compared to Bard. Despite their inconsistencies, the study authors suggested that these chatbots hold promise in assisting healthcare providers in determining the best imaging modality, signaling a potential role for AI in improving medical decision-making processes.
Read more: https://lnkd.in/enhxVNZV