Suppose that your company has just developed a new screening

Suppose that your company has just developed a new screening test for a disease and you are in charge of testing its validity and feasibility.You decide to evaluate the test on 1000 individuals and compare the results of the new test to the gold standard.You know the prevalence of disease in your population is 30%.The screening test gave a positive result for 292 individuals.285 of these individuals actually had the disease on the basis of the gold standard determination.

Calculate the sensitivity of the new screening test.

95.0% 97.6% 99.0% 96.9%

How would you interpret the results of the sensitivity calculation.

Of those who tested positive, 97.6% actually have disease The test is able to detect 95% of those with disease The test is able to correctly classify(as negative) 99.0% of those without disease Of those who tested positive, 95.0% actually have disease

Calculate the specificity of the new screening test.

95.0% 97.6% 99.0% 96.9%

How would you interpret the results of the specificity calculation.

Of those who tested positive, 97.6% actually have disease The test is able to detect 95% of those with disease The test is able to correctly classify(as negative) 99.0% of those without disease Of those who tested positive, 95.0% actually have disease

Calculate the predictive value of a positive test.

95.0% 97.6% 99.0% 96.9%

How would you interpret the results of the predictive value positive calculation.

Of those who tested positive, 95.0% actually have disease The test is able to detect 95% of those with disease The test is able to correctly classify(as negative) 99.0% of those without disease Of those who tested positive, 97.6% actually have disease

What would happen to the predictive value positive if this test were administered in a population with a disease prevalence of 1% instead of 30%? (Note that the sensitivity and specificity of the test remain the same.) Would it remain the same? Increase? Decrease?

Predictive value positive would decrease. Predictive value positive would increase Predictive value positive would remain unchanged

Solution

Gold Standard Determination of Disease

Total

Results of Screening Test

Yes

No

Positive

285

7

292

Negative

15

693

708

Total

300

700

1,000

Calculate the sensitivity of the new screening test.

0.30*1000 = 300

285/300 =0.95= 95%

The test is able to correctly classify as positive 95% of those with the disease

Calculate the specificity of the new screening test.

693/700 =0.99 = 99%

The test is able to correctly classify as negative 99% of those without the disease

Calculate the predictive value of a positive test.

285/ 292 = 0.976

97.6%

probability that the disease is present when the test is positive

What would happen to the predictive value positive if this test were administered in a population with a disease prevalence of 1% instead of 30%?

Predictive value positive would decrease