. Author manuscript; available in PMC: 2011 Oct 1.

Published in final edited form as: Artif Intell Med. 2010 Jun 20;50(2):75–82. doi: 10.1016/j.artmed.2010.05.008

Table 5.

Comparison of experts with a Bayesian network in two test sets.

Expert Number	Test Set	AUC (± S.E.)		Z-test (p-value)
Expert Number	Test Set	Expert	Bayes Net	Z-test (p-value)
1	1	0.68 (± 0.08)	0.93 (± 0.04)	2.83 (p < 0.05)
2	1	0.79 (± 0.07)	0.93 (± 0.04)	1.99 (p < 0.05)
3	1	0.74 (± 0.07)	0.93 (± 0.04)	2.33 (p < 0.05)
4	1	0.84 (± 0.06)	0.93 (± 0.04)	1.55 (p = n.s.)
5	1	0.76 (± 0.07)	0.93 (± 0.04)	2.37 (p < 0.05)
6	2	0.78 (± 0.06)	0.86 (± 0.05)	1.20 (p = n.s.)
7	2	0.70 (± 0.07)	0.86 (± 0.05)	2.25 (p < 0.05)
8	2	0.71 (± 0.07)	0.86 (± 0.05)	2.07 (p < 0.05)
9	2	0.85 (± 0.05)	0.86 (± 0.05)	0.17 (p = n.s.)
10	2	0.67 (± 0.07)	0.86 (± 0.05)	2.97 (p < 0.05)
11	2	0.76 (± 0.07)	0.86 (± 0.05)	1.48 (p = n.s.)