Monday, May 14, 2007

Positive and Negative Predictive Value

Our April case study also refers to positive predictive value and negative predictive value (see this post for discussion of sensitivity and specificity), and defines them as follows:
"The positive predictive value represents the probability of a positive test result indicating the true presence of disease."

"The negative predictive value represents the probability of a negative test result indicating that the disease is truly absent."
Thus, while sensitivity refers to the likelihood of a person with a disease testing positive for disease, positive predictive value (PPV) refers to the likelihood of actually diagnosing a disease in those who have it. Likewise, while specificity refers to the likelihood of a person without a disease testing negative, negative predictive value (NPV) refers to the likelihood of the test confirming that a person without disease doesn't have the disease.

These values are calculated as follows:
Positive predictive value = (number of people who have disease and test positive for it)/(number of people who have disease and test positive for it PLUS the number of people who don't have the disease and test positive for it)
OR
The number of people who have a disease and test positive for it divided by the total number of people who test positive for the disease (regardless of whether they have it)
OR
How reliable is the test when it indicates that someone has a disease?
OR
When you test positive, how likely is it that you really have the disease?

Negative predictive value = (number of people who don't have the disease and test negative)/(number of people who don't have the disease and test negative PLUS number of people of who have disease and test negative)
OR
The number of people who don't have the disease and test negative divided by the total number of people who test negative for the disease (regardless of whether they have it)
OR
How reliable is the test when it indicates that someone does not have a disease?
OR
When you test negative, how likely is it that you really don't have the disease?

So, if a test has a PPV of 95%, then 95% of people who test positive really have the disease (so 5% test positive but really aren't). If it has an NPV of 85%, then 85% of people who test negative really don't have the disease (so 15% really have the disease but test negative).

Additional Information:
-How to read a paper: Papers that report diagnostic or screening tests
-Sensitivity and Specificity: Medical University of South Carolina (scroll down for PPV/NPV from an HIV testing example)
-Predictive Values: Michigan State University

Labels: , ,

0 Comments:

Post a Comment

Links to this post:

Create a Link

<< Home