BS - Epi/Biostat (Evaluation of diagnostic tests)

Question 1

What is the basic premise on which the evaluation of diagnostic tests is based? What are the 4 major measures of evaluation? Draw a visual defining each of them.

Answer 1

Uses 2x2 table comparing test results with the actual presence of disease. TP = true positive; FP = false positive; TN = true negative; FN = false negative; See p. 51 in First Aid 2014 for visual at top right corner

Question 2

Which properties of a test are fixed?

Answer 2

Sensitivity and specificity are fixed properties of a test (vs. PPV and NPV).

Question 3

What is another name for Sensitivity? What is its definition?

Answer 3

Sensitivity (true-positive rate); Proportion of all people with disease who test positive, or the probability that a test detects disease when disease is present

Question 4

What is the equation for Sensitivity? How does it relate to false negative rate?

Answer 4

Sensitivity = TP / (TP + FN) = 1 - false negative rate

Question 5

For what is a sensitivity value approaching 100% desirable? What does it indicate, and how is that understood using equations?

Answer 5

Value approaching 100% is desirable for ruling out disease and indicates a low false-negative rate; If sensitivity is 100%, TP / (TP + FN) = 1, FN = 0, and all negatives must be TNs; Think: “SN-S-OUT = highly SeNsitive test, when Negative, rules OUT disease.”

Question 6

For what is a high sensitivity test used?

Answer 6

High sensitivity test used for screening in diseases with low prevalence

Question 7

What is another name for Specificity? What is its definition?

Answer 7

Specificity (true-negative rate); Proportion of all people without disease who test negative, or the probability that a test indicates non-disease when disease is absent

Question 8

What is the equation for Specificity? How does it relate to false positive rate?

Answer 8

Specificity = TN / (TN + FP) = 1 - false positive rate

Question 9

For what is a specificity value approaching 100% desirable? What does it indicate, and how is that understood using equations?

Answer 9

Value approaching 100% is desirable for ruling in disease and indicates a low false-positive rate.; If specificity is 100%, TN / (TN + FP) = 1, FP = 0, and all positives must be TPs; Think: “SP-P-IN = highly SPecific test, when Positive rules IN disease”

Question 10

For what is a high specificity test used?

Answer 10

High specificity test used for confirmation after a positive screening test

Question 11

What defines the positive predictive value (PPV)? What is another way to state or conceptualize this?

Answer 11

Proportion of positive test results that are true positive; Probability that person actually has the disease given a positive test result

Question 12

What is the equation for positive predictive value (PPV)?

Answer 12

PPV = TP / (TP + FP)

Question 13

With what does PPV vary, and how so?

Answer 13

PPV varies directly with prevalence or pretest probability: high pretest probability => high PPV

Question 14

What defines negative predictive value (NPV)? What is another way to state or conceptualize this?

Answer 14

Proportion of negative test results that are true negative; Probability that person actually is disease free given a negative test result

Question 15

What is the equation for negative predictive value (NPV)?

Answer 15

NPV = TN / (FN + TN)

Question 16

With what does NPV vary, and how so?

Answer 16

NPV varies inversely with prevalence or pretest probability: high pretest probability => low NPV

Question 17

Draw a graph (x axis = test results & y axis = number of people) depicting the following possible cutoff values related to the evaluation of diagnostic tests: (A) 100% sensitivity cutoff value (B) Practical compromise between specificity and sensitivity (C) 100% specificity cutoff value.

Answer 17

See p. 51 in First Aid 2014 for visual at bottom of page