Fig. 5

Overall rating of the performance of Image recognition by ChatGPT 4.0. (A) Comparison of the grading of the modified AIPI and image description/recognition by two independent reviewers for (a) Scenario 1 with only the image as a prompt; (b) Scenario 2 with the image and the clinical history of each patient; (c) Scenario 3 with only the clinical history, (B) Overall comparison of the performance. Each bar is the average of the two independent reviewers grading. * equals p > 0.05, ** equals p > 0.01, *** equals p > 0.001.