Skip to main content
. 2020 Sep;12(9):5078–5085. doi: 10.21037/jtd.2019.08.34

Table 3. Comparison of TBNet and radiologist performance on radiographs obtained from Johns Hopkins Hospital.

Reader Sensitivity Specificity Positive predictive value (PPV) Negative predictive value (NPV)
TBNet 85% 76% 0.64 0.9
Radiologist 1 83% 81% 0.7 0.9
Radiologist 2 77% 75% 0.63 0.86
Majority vote 94% 85% 0.76 0.96