Skip to main content
. 2017 Aug 2;8(13):2554–2560. doi: 10.7150/jca.20031

Table 5.

Predicted and actual data for selected three cut-off points with overall sensitivity, specificity, PPV and NPV for predicting patients with PCa ≥3+4 and patients with PCa Gleason ≥4+3. The number of cases missed by the algorithm were 16, 2, and 3 for Gleason 3+4, 4+3, and ≥4+3, respectively, using low cut-off; 9, 1, and 3 for Gleason 3+4, 4+3, and ≥4+3, respectively, using standard cut-off; and 3, 0, and 1 for Gleason 3+4, 4+3, and ≥4+3, respectively, using high cut-off.

Cut-off Neg 3+3 3+4 4+3 >4+3 Total Missed Sensitivity Specificity NPV PPV
≥3+4 ≥4+3 ≥3+4 ≥4+3 ≥3+4 ≥4+3 ≥3+4 ≥4+3
Actual 239 103 92 29 26
Predicted Low 93 54 76 27 23 21 (4.3%) 86% 96% 57% 59% 90% 98% 46% 46%
Standard 106 63 83 28 23 13 (2.7%) 91% 97% 51% 44% 93% 98% 44% 52%
High 148 70 89 29 25 4 (0.8%) 97% 99% 36% 37% 97% 99% 40% 40%