Table 4. Binary classification of each of four disease classes versus a combined class of the remaining three.
| Classes | AUC | Sensitivity@ 90% speca |
Specificity@ 90% sensb |
Accuracy@ speca=sensb |
Model size (k) |
|---|---|---|---|---|---|
|
T. cruzi vs. Other |
0.97 (0.96-0.98) |
92% (90%-94%) |
94% (90%-96%) |
92% (90%-92%) |
50 |
| HBV vs. Other |
0.94 (0.93-0.95) |
85% (78%-90%) |
85% (78%-90%) |
87% (85%-90%) |
16000 |
| HCV vs. Other |
0.96 (0.94-0.97) |
90% (86%-94%) |
91% (82%-96%) |
90% (88%-93%) |
100 |
| WNV vs. Other |
0.96 (0.95-0.97) |
87% (78%-94%) |
88% (84%-92%) |
89% (86%-91%) |
1000 |
aspec, specificity
bsens, sensitivity