Skip to main content
. Author manuscript; available in PMC: 2012 Aug 1.
Published in final edited form as: AJR Am J Roentgenol. 2011 Aug;197(2):325–333. doi: 10.2214/AJR.10.5909

TABLE 5.

Accuracy Measures for Training Data (n = 120) and Validation Data (n = 71)

Statistic Cutoff Sensitivity Specificity AUC
Probability of normal drainage (Y1 = 1)
 Training data 0.5 0.89 (0.03) 0.93 (0.02) 0.97 (0.01)
 Validation data 0.5 0.85 (0.04) 0.93 (0.02) 0.93 (0.02)
Probability of obstructed kidney(Y2 = 2)
 Training data 0.4 0.86 (0.07) 0.83 (0.07) 0.88 (0.05)
 Validation data 0.4 0.82 (0.08) 0.83 (0.07) 0.84 (0.06)
Probability of combined obstructed/equivocal (Y2 ≥ 1)
 Training data 0.6 0.85 (0.06) 0.95 (0.05) 0.89 (0.05)
 Validation data 0.6 0.78 (0.07) 0.95 (0.05) 0.84 (0.06)

Note—Values in parentheses are standard error. AUC = area under the receiver operating characteristic curve.