Test Statistics-BioInstrumentation

In this article, we will learn about different test parameters that are required after performing medical tests on patients to analyse statistical data.

We may define terms for test results

1. True positive (TP): 

A true positive test result is one that detects the condition when the condition is present. TP denotes the number of true positives.

2. True negative (TN):

A true negative test result is one that does not detect the condition when the condition is absent. TN denotes the number of true negatives.

3. False positive (FP):

A false positive test result is one that detects the condition when the condition is absent. FP denotes the number of true positives.

4. False negative (FN):

A false negative test result is one that does not detect the condition when the condition is present. FN denotes the number of true positives.

5. Accuracy

It is defined as the number of correct classified tests over the total number of tests.

6. Sensitivity

It measures the ability of a test to detect the condition when the condition is present. Thus,

Sensitivity = TP/(TP+FN)

7. Specificity

It measures the ability of a test to correctly exclude the condition (not detect the condition) when the condition is absent. Thus,

 

8. Predictive value positive

It is the proportion of positives that correspond to the presence of the condition. Thus,

Predictive value positive = TP/(TP+FP)

9. Predictive value negative

It is the proportion of negatives that correspond to the absence of the condition. Thus,

Predictive value negative = TN/(TN+FN)

10. Parallel combination of tests

It is a test that is positive if at least one of the combining tests is positive; otherwise, it is negative.

OR

It is a test that is negative only if all the combining tests are negative; otherwise, it is positive.

11. Series combination of tests

It is a test that is negative if at least one of the combining tests is negative; otherwise, it is positive.

OR

It is a test that is positive only if all the combining tests are positive; otherwise, it is negative.