Table 2.

Performance metrics of the genomic and clinical predictors

T/FAC (n = 91)FACx6 (n = 87)
Genomic predictor
    ROC, AUC0.711 (95% CI, 0.570-0.852)0.584 (95% CI, 0.353-0.815)
    PPV38% (95% CI, 21-56)9% (95% CI, 1-29)
    NPV88% (95% CI, 77-95)92% (95% CI, 83-97)
    Sensitivity63% (95% CI, 38-84)29% (95% CI, 4-71)
    Specificity72% (95% CI, 60-82)75% (95% CI, 64-84)
Clinical predictor
    Discrimination (ROC), AUC0.89 (95% CI, 0.85-0.93)0.82 (95% CI, 0.75-0.89)
    Calibration
        P0.210.03
        Emax10.5%15.5%
        Eaverage4.8%9.2%

NOTE: The corresponding ROC and calibration curves are represented graphically in Fig. 2.

Abbreviations: E, difference in predicted probabilities and observed frequencies; Emax, maximal error; Eaverage, average error.