Comparing Diagnostic Accuracy of Radiologists versus GPT-4V and Gemini Pro Vision Using Image Inputs from Diagnosis Please Cases
Pae Sun Suh, Woo Hyun Shim, Chong Hyun Suh, Hwon Heo, Chae Ri Park, Hye Joung Eom, Kye Jin Park, Jooae Choe, Pyeong Hwa Kim, Hyo Jung Park, Yura Ahn, Ho Young Park, Yoonseok Choi, Chang-Yun Woo, Hyung Park
Abstract
= .02). Radiologists (range, 45%-88%) outperformed the LLMs at T1 (range, 24%-75%) in most subspecialties. Conclusion Using direct radiologic image inputs, GPT-4V and Gemini Pro Vision showed improved diagnostic accuracy with increasing temperature settings. Although GPT-4V slightly underperformed compared with radiologists, it nonetheless demonstrated promising potential as a supportive tool in diagnostic decision-making. © RSNA, 2024 See also the editorial by Nishino and Ballard in this issue.
Topics & Concepts
MedicineMedical physicsRadiologyComputer visionDiagnostic accuracyArtificial intelligenceComputer scienceArtificial Intelligence in Healthcare and EducationAdvanced X-ray and CT ImagingDental Radiography and Imaging