You develop a screening test to be used for children with autism to detect serum antibodies from mild protein consumption and have the follwoing 2x2 table.

 

disease No disease totals

 

positive test 10 2 12

negative test 3 220 223

totals 13 222 235

 

 

Specificity?

 

Negative Predictive Value?

 

If early treatment helps, is this a good screen?

 

Specificity = 99.099%

Negative predictive value = 98.65%

This is a good screen

Step-by-step explanation

Specificity = True negatives/Total non-diseased *100

True negatives = 220

Total non-diseased = 220 + 2 = 222

Specificity = 220/222 x 100

=0.9909909 x 100

= 99.099%

Negative predictive value = True negatives/ True negatives + False negatives *100

False negatives = 3

Negative predictive value = 220/ (220 + 3)

= 220/223 *100

= 0.986547*100

= 98.65%

If early treatment helps, this is a good screen because it has a high specificity and high negative predictive value. High specificity means that the test has few false positive and false negative results. Negative predictive value is the probability that an individual does not have a disease, following a negative test result. This screen will therefore, accurately identify the diseased individuals for early treatment.