Sensitivity, Specificity, and Predictive Values

Question 1

Sensitivity and specificity are independent of . . .

Answer 1

. . . prevalence of disease and patient pre-test probability.

Question 2

Positive predictive value

Answer 2

True +

_________

True + and False +

Question 3

Negative predictive value

Answer 3

True -

________________

False - and True -

Question 4

Post-test probability negative

Answer 4

Likelihood of having disease if I have a negative test

1 - NPV

Question 5

Predictive values vary depending on . . .

Answer 5

. . . prevalence within a given population at a given time

Question 6

Likelihood ratio

Answer 6

LR = Probability of patient with a condition having a test result

____________________________________________

Probability of patient without condition having test result

Question 7

To rule something out, you want a test with a ____.

Answer 7

To rule something out, you want a test with a low negative likelihood ratio.

Question 8

To rule something in, you want a test with a ___.

Answer 8

To rule something in, you want a test with a high positive likelihood ratio.

Question 9

Setup of Fegan’s nomogram

Answer 9

Left: Pre-test probability

Middle: Likelihood ratio

Right: Post-test probability

Question 10

Calculating odds from probability

Answer 10

Odds = p / (1 - p)

Question 11

Calculating probability from odds

Answer 11

p = odds / ( 1 + odds)

Question 12

Test reference standard or gold standard

Answer 12

Test to which potential screening or diagnostic tests are compared to calculate sensitivity and specificity

Question 13

Threshold probability

Answer 13

The probability above or below which you will take action (e.g., order an additional test, prescribe a treatment)

Question 14

Receiver Operating Characteristic (ROC) Curves

Answer 14

An ROC curve is a plot of the true positive rate (sensitivity) against the false positive rate (1-specificity; recall that specificity reflects true negatives) for the possible cutpoints of a diagnostic test. The closer the curve follows the left-hand border and the top border of the ROC space, the more accurate the test.

Question 15

If we change our cutoff to increase sensitivity, then ___. If we change our cutoff to increase specificity, then ___.

Answer 15

If we change our cutoff to increase sensitivity, then specificity goes down. If we change our cutoff to increase specificity, then sensitivity goes down

Question 16

Lead time bias

Answer 16

People with the disease who get screened and then get treatment survive longer than people with the disease who do not get screened.

You may mistakenly conclude that screening + treatment cause improved survival, when what is really going on is that patients diagnosed earlier have more time to survive, even if treatment isn’t helpful and their actual life expectancy may be no different.

Question 17

Length bias

Answer 17

Cases of a particular condition that are progressing more slowly will be more prevalent in a screened population than those that are rapidly progressing. So if some patients with the disease spend more time “having it without being sick from it,” they are the ones you’ll find by screening.

In contrast, patients with rapid disease progression spend less time “having it without being sick from it.” That means that patients with positive screening tests appear to have better outcomes, but it is not because screening + treatment is better – instead it’s because the disease in patients detected by screening is different from that in patients who present with symptoms

Question 18

Which test parameters are stable with changes in disease prevalence?

Answer 18

Sensitivity

Specificity

Likelihood ratio

Question 19

Can long-term follow-up be used as a gold standard when assessing the validity of a diagnostic test?

Answer 19

Yes!!!

Question 20

LR+ and LR-

Answer 20