Skip to main content

Table 3 True values and posterior estimates across 1000 simulated datasets of Area Under the Curve (AUC) and Integrated Discrimination Improvement (IDI) statistics obtained from latent class models assuming conditional dependence (with S1=0.7, C1=0.9)

From: A Bayesian framework for estimating the incremental value of a diagnostic test in the absence of a gold standard

Accuracy of T2 compared to T1 Parameter value AUC for T1 and T2 AUC for T1 AUC difference IDI in events IDI in non events IDI*
1) Higher sensitivity S2 = 80, C2 = 90 True 0.88 0.80 0.09 0.10 0.04 0.15
Estimated 0.90 (0.89, 0.90) 0.80 (0.80, 0.81) 0.09 (0.08, 0.10) 0.13 (0.11, 0.15) 0.06 (0.04, 0.07) 0.19 (0.16, 0.21)
2) Higher specificity S2 = 70, C2 = 95 True 0.87 0.80 0.07 0.10 0.04 0.15
Estimated 0.88 (0.87. 0.89) 0.80 (0.80, 0.81) 0.07 (0.06, 0.09) 0.12 (0.10, 0.14) 0.05 (0.04, 0.06) 0.17 (0.15, 0.19)
3) Lower sensitivity S2 = 60, C2 = 90 True 0.84 0.80 0.04 0.03 0.01 0.04
Estimated 0.85 (0.84, 0.86) 0.80 (0.80, 0.81) 0.05 (0.04, 0.05) 0.05 (0.04, 0.06) 0.02 (0.02, 0.03) 0.08 (0.06, 0.19)
4) Lower specificity S2 = 70, C2 = 80 True 0.83 0.80 0.03 0.02 0.01 0.03
Estimated 0.85 (0.84, 0.86) 0.80 (0.80, 0.81) 0.04 (0.04, 0.05) 0.04 (0.03, 0.04) 0.02 (0.01, 0.02) 0.06 (0.05, 0.06)
5) Both better S2 = 80, C2 = 95 True 0.90 0.80 0.11 0.17 0.07 0.24
Estimated 0.91 (0.90, 0.92) 0.80 (0.79, 0.81) 0.11 (0.09, 0.12) 0.19 (0.16, 0.21) 0.08 (0.07, 0.09) 0.27 (0.24, 0.29)
6) Both worse S2 = 60, C2 = 80 True 0.82 0.80 0.02 0.01 0.00 0.01
Estimated 0.84 (0.83, 0.84) 0.80 (0.80, 0.81) 0.03 (0.03, 0.04) 0.02 (0.02, 0.03) 0.01 (0.007, 0.01) 0.03 (0.02, 0.04)
7) No better S2 = 70, C2 = 90 True 0.85 0.80 0.05 0.05 0.02 0.07
Estimated 0.86 (0.85, 0.87) 0.80 (0.80, 0.81) 0.06 (0.05, 0.07) 0.08 (0.07, 0.10) 0.04 (0.03, 0.04) 0.12 (0.10, 0.14)
8) No value S2 = 70, C2 = 30 True 0.84 0.80 0.04 0.01 0.01 0.02
Estimated 0.84 (0.83, 0.86) 0.80 (0.79, 0.80) 0.04 (0.03, 0.06) 0.02 (0.01, 0.02) 0.01 (0.004, 0.01) 0.02 (0.02, 0.04)
  1. T1 = test 1; T2 = test 2; S 2  = sensitivity of T2; C2 = specificity of T2.
  2. *IDI is sum of IDIevents and IDInon-events.