Skip to main content
. 2023 Apr 14;13(5):2989–3000. doi: 10.21037/qims-22-950

Table 3. A comparison of the diagnostic performance of doctors and the deep learning (DL) model before combining clinical data.

Methods Sensitivity Specificity Accuracy F1-score
Doctor 1 0.850 0.300 0.575 0.540
Doctor 2 0.700 0.600 0.650 0.649
Doctor 3 0.750 0.750 0.750 0.750
DL model 0.972 0.944 0.958 0.959