Table 3

Discrimination and calibration statistics from recalibrated predicted probability algorithms

36.1–37.5°C⩽36.0°C or >37.5°C
CRIB IICRIB II(−T)CRIB IICRIB II(−T)
Observed deaths, n (%)167 (7.3)150 (15.3)
Predicted deaths, n (%)141.3 (6.2)164.8 (7.2)175.7 (17.9)152.2 (15.6)
Brier score0.0440.0430.0750.075
Spiegelhalter’s z-scorep = 0.02p = 0.4p = 0.9p = 0.7
AUC0.9170.9170.9210.919
Calibration-in-the-small0.00050.00010.00180.0011
Calibration-in-the-large0.0001<0.00010.0007<0.0001
Cox’s regression:
    Intercept α (SE)0.36 (0.15)0.00 (0.14)−0.28 (0.13)0.00 (0.14)
    Slope β (SE)0.05 (0.06)0.98 (0.06)1.07 (0.08)1.04 (0.08)
    Test: α = 0, β = 1p = 0.02p = 0.9p = 0.01p = 0.9
    Test: α = 0 | β = 1p = 0.008p = 0.8p = 0.004p = 0.8
    Test: β = 1 | αp = 0.4p = 0.8p = 0.4p = 0.6
  • AUC, area under the curve; CRIB, Clinical Risk Index for Babies; CRIB II(−T), CRIB II without temperature at admission.