Table 2.
Diagnostic performance summary for biomarker-based diagnostic algorithm. Performance summary of three diagnostic tests. Vis = qualitative visual imaging; Classification efficiencies, sensitivities (Sn), negative predictive values (NPV), specificities (Sp), and positive predictive values (PPV) for tumor tissue diagnosis are tabulated.
| Classification efficiency(%) | Sn (%) | NPV (%) | Sp (%) | PPV (%) | |
|---|---|---|---|---|---|
|
SVM | |||||
| AG | 94 | 94 | 87 | 94 | 97 |
| LGG | 96 | 94 | 88 | 100 | 100 |
| HGG | 92 | 92 | 87 | 91 | 95 |
| RCG | 98 | 98 | 86 | 100 | 100 |
|
cPpIX | |||||
| AG | 83 | 84 | 68 | 78 | 90 |
| LGG | 63 | 50 | 44 | 93 | 95 |
| HGG | 81 | 75 | 68 | 91 | 94 |
| RCG | 97 | 96 | 75 | 100 | 100 |
|
VIS | |||||
| AG | 64 | 50 | 45 | 96 | 97 |
| LGG | 35 | 8 | 31 | 100 | 100 |
| HGG | 67 | 50 | 53 | 95 | 94 |
| RCG | 80 | 78 | 33 | 100 | 100 |