Table 2.

The apparent diagnostic performance characteristics of a perfect biomarker as a function of disease prevalence and sensitivity and specificity of an imperfect gold standard.

Imperfect gold standard diagnostic performance	True disease prevalence	Apparent sensitivity	Apparent specificity	Lower bound of Apparent AUC- ROC	Upper bound of Apparent AUC- ROC
80% sensitive, 90% specific	5%	30%	99%	0.29	0.99
	10%	47%	98%	0.46	0.99
	20%	67%	95%	0.63	0.98
	40%	84%	87%	0.73	0.98
	60%	92%	75%	0.69	0.98
80% sensitive, 80% specific	5%	17%	99%	0.17	0.99
	10%	31%	97%	0.30	0.98
	20%	50%	94%	0.47	0.97
	40%;	73%	86%	0.62	0.96
	60%	86%	73%	0.64	0.96
25% sensitive, 100% specific	5%	100%	96%	0.96	1.00
	10%	100%	92%	0.92	1.00
	20%	100%	84%	0.84	1.00
	40%	100%	67%	0.67	1.00
	60%	100%	47%	0.47	1.00
25% sensitive, 99% specific	5%	57%	96%	0.55	0.98
	10%	74%	92%	0.68	0.98
	20%	86%	84%	0.72	0.98
	40%	94%	66%	0.63	0.98
	60%	97%	47%	0.46	0.99
100% sensitive, 25% specific	5%	7%	100%	0.07	1.00
	10%	13%	100%	0.13	1.00
	20%	25%	100%	0.25	1.00
	40%	47%	100%	0.47	1.00
	60%	67%	100%	0.67	1.00

Abbreviations: AUC, area under the receiver operating characteristic curve