Ah, if I misread then from the results section of the linked paper:
For the malignancy prediction objective, the algorithm obtained an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI: 0.89, 0.93), with specificity of 77.3% (95% CI: 69.2%, 85.4%) at a sensitivity of 87%.
I haven't read the papers methods, but the data set size is small-ish for this sort of analysis.
For the malignancy prediction objective, the algorithm obtained an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI: 0.89, 0.93), with specificity of 77.3% (95% CI: 69.2%, 85.4%) at a sensitivity of 87%.
I haven't read the papers methods, but the data set size is small-ish for this sort of analysis.