TABLE 2.
Metric | PR vs CR | PR vs AS | CR vs AS | |||
---|---|---|---|---|---|---|
10 | 10 + 2 | 10 | 10 + 2 | 10 | 10 + 2 | |
AUC | 0.792 | 0.933b | 0.966 | 0.971 | 0.803 | 0.83 |
Sensitivity (%) | 57.9 | 81.6 | 89.5 | 86.8 | 68.8 | 68.8 |
Specificity (%) | 85.4 | 83.3 | 90 | 90 | 76.7 | 80 |
Including antibodies improves the AUC in all three comparisons. The sensitivity is calculated with respect to Progressors in the first two comparisons and Controllers in the last comparison. Please refer to Fig. S3 for the confusion matrices. AS, asymptomatic; CR, controller; PR, progressor.
For each of the classification tasks and their corresponding metrics, the panel with the higher performance is highlighted in bold.