Re: Concerns about composite reference standards in diagnostic research
Composite reference standards (CRFs) are used in the absence of specific standards for the test in question. Combining multiple imperfect test results may result in or may lead to a more perfect reference standard is the rationale behind such an approach.
In clinical or lab diagnosis, sensitivity of the test is defined as the ability of a test to correctly identify those with the disease (true positive rate), whereas test specificity is the ability of the test to correctly identify those without the disease But with the use of CRFs specificity is compromised.
The use of CRF combined results from multiple imperfect tests ignores information and therefore is not guaranteed to improve over a single imperfect reference unless each component test has perfect specificity.
Likelihood ratios (LRs) are used to assess two things: 1) the potential utility of a particular diagnostic test, and 2) how likely it is that a patient has a disease or condition. LRs are basically a ratio of the probability that a test result is correct to the probability that the test result is incorrect.
Therefore a way to take account of sensitivity, specificity, and prevalence in interpreting test scores is to calculate LRs. How this can be used or introduced in such CRFs needs to be discussed.
Rapid Response:
Re: Concerns about composite reference standards in diagnostic research
Composite reference standards (CRFs) are used in the absence of specific standards for the test in question. Combining multiple imperfect test results may result in or may lead to a more perfect reference standard is the rationale behind such an approach.
In clinical or lab diagnosis, sensitivity of the test is defined as the ability of a test to correctly identify those with the disease (true positive rate), whereas test specificity is the ability of the test to correctly identify those without the disease But with the use of CRFs specificity is compromised.
The use of CRF combined results from multiple imperfect tests ignores information and therefore is not guaranteed to improve over a single imperfect reference unless each component test has perfect specificity.
Likelihood ratios (LRs) are used to assess two things: 1) the potential utility of a particular diagnostic test, and 2) how likely it is that a patient has a disease or condition. LRs are basically a ratio of the probability that a test result is correct to the probability that the test result is incorrect.
Therefore a way to take account of sensitivity, specificity, and prevalence in interpreting test scores is to calculate LRs. How this can be used or introduced in such CRFs needs to be discussed.
Competing interests: No competing interests