Skip to main content

Table 3 Dmin scenario estimated mean and 95% confidence intervals of the sensitivity and specificity of a diagnostic test, given the test achieved 97% sensitivity and 99% specificity in the evaluation sample (Dmin), for a simulated population size of 5,000, where the evaluation sample sizes correspond to current guidelines

From: Examining the effect of evaluation sample size on the sensitivity and specificity of COVID-19 diagnostic tests in practice: a simulation study

Evaluation sample size

Sensitivity

 

Specificity

 

Positive (e+) /negative (e)

Mean

95% CI

Failure (%)

Mean

95% CI

Failure (%)

Theoretical

30/30

96.9%

88.8%

99.9%

10.5%

96.9%

88.8%

99.9%

38.9%

150/250

96.7%

93.4%

98.9%

1.7%

98.8%

97.2%

99.8%

1.9%

250/1000

96.8%

94.3%

98.6%

0.3%

99.0%

98.5%

99.3%

0.0%

Prevalence: 1%

30/30

96.9%

86.5%

100.0%

13.5%

96.9%

88.8%

99.9%

39.5%

150/250

96.8%

89.8%

100.0%

10.7%

98.8%

97.1%

99.8%

2.1%

250/1000

96.8%

90.4%

100.0%

9.6%

98.9%

98.1%

99.5%

0.0%

Prevalence: 5%

30/30

96.9%

88.5%

100.0%

11.3%

96.9%

89.1%

99.9%

38.7%

150/250

96.7%

92.5%

99.6%

3.7%

98.8%

97.1%

99.8%

2.2%

250/1000

96.8%

93.1%

99.2%

2.3%

98.9%

98.1%

99.5%

0.0%

Prevalence: 10%

30/30

96.9%

88.5%

100.0%

10.7%

96.9%

88.9%

99.9%

39.1%

150/250

96.7%

92.8%

99.2%

2.9%

98.8%

97.1%

99.8%

2.0%

250/1000

96.8%

93.7%

99.0%

0.9%

98.9%

98.1%

99.5%

0.0%

Prevalence: 15%

30/30

96.9%

88.5%

100.0%

11.1%

96.9%

88.8%

99.9%

39.5%

150/250

96.7%

93.1%

99.1%

2.3%

98.8%

97.1%

99.8%

2.3%

250/1000

96.8%

93.9%

98.9%

0.6%

98.9%

98.1%

99.5%

0.0%