Skip to main content
. 2022 Mar 18;9:854677. doi: 10.3389/fmed.2022.854677

Table 3.

Comparison of time consumption for diagnosing the same test dataset (unit: s).

Trainee endoscopist (highest) Competent endoscopist (highest) Deep model P-value (Trainee endoscopist vs. Model) P-value (Competent endoscopist vs. Model)
All lesion images 12,862 11,326 6.00 P < 0.001 P < 0.001
All patients 2,421 2,429 6.20 P < 0.001 P < 0.001