Epidemiology Chapter 5
Percent (%) agreement =
((# of tests in which two people agree)/ total number of tests done) × 100 =
Kappa
((percent of agreement observed) - (percent of agreement expected by chance alone)) / (100% - (Percent agreement by chance alone))
percent agreement formula
(a/ (a+b+c)) × 100
To be included in the numerator for net specificity for two tests used simultaneously...
...a person must be identified as negative by both tests.
To be considered positive and therefore included in the numerator for net sensitivity for two tests used simultaneously...
...a person must be identified as positive by test A, test B, or both tests
Kappa expresses...kappa quantifies...
...the extent to which the observed agreement exceeds that which would be expected by chance alone...the extent to which the observed agreement that the observers achieved exceeds that which would be expected by chance alone
In simultaneous testing, because an individual who tests positive on any one or multiple tests is considered positive...
...there is a gain in net sensitivity.
Why are false negatives important?
If a person has the disease but is erroneously informed that the test result is negative, and if the disease is a serious one for which effective intervention is available, the problem is indeed critical.
Net sensitivity in simultaneous testing=
Population = 200 Test senitivity of test A (80%) (200*.8 =160 people) Test sensitivity of test b (90%) (.9*160= 144 people) = (144 simultaneous test result), (but also test b's full result = 180 people) Next take the simultaneous test result and subtract from each original population (144-160 = 16 and 180-144 = 36) ((16+144+36)/200) = net sensitivity
The type of distribution in which there are two peaks is called...
a bimodal curve.
In sequential or two-stage screening
a less ex- pensive, less invasive, or less uncomfortable test is generally performed first, and those who screen positive are recalled for further testing. It is hoped that bringing back for further testing only those who screen positive will reduce the problem of false positives
percent agreement
a measure of reliability between two people in which the percentage of times that the two people agree
a unimodal curve
a single peak
Why is the issue of false positives important?
all people who screened positive are brought back for more sophisticated and more expensive tests
Net specificity in sequential testing (p. 96 of book) =
amount of people tested negative in the first round (A) + amount of people who tested negative in the second round (B) (((A+B)/ total population) *100)
Net sensitivity in sequential testing =
amount of people tested positive in the first round (A) - amount of people tested positive in the second round (B) or (B/A)
negative predictive value (NPV) of the test.
calculated by dividing the number of true negatives by all those who tested negative. the probability that a person with a negative screening test result actually does not have the antibody. = true negatives / all with negative test Algebraically, PVN = D / (C+D).
Percent agreement by chance alone =
if you have one event that occurs 50% of the time, and another that occurs 30% of the time, and the two events are independent, the likelihood of both events is 50%x30%= 15% (.5 x .3=.15). If two physicians are doing the same tests independently you calculate this by the percentage by which they agree (Ex. they have 200 tests, one doctor does 100 positive and 100 negative, the second doctor calls 150 positive and 50 negative (50% x 25%=12.5%) Thus the answer is 12.5%.
validity of a test is defined as...
its ability to distinguish between who has a disease and who does not
false positives
people who do not have the disease are erroneously called "positive" by the test
false negatives
people with the disease are erroneously called "negative"
true positives
people with the disease who are correctly called "positive" by the test
true negatives
people without the disease who are correctly called "negative" by the test
specificity of a test is defined as...also defined as...
the ability of the test to identify correctly those who do not have the disease....the proportion of nondiseased people who are correctly identified as "negative" by the test,
sensitivity of a test is defined as...also defined as...
the ability of the test to identify correctly those who have the disease... the proportion of diseased people who were correctly identified as "positive" by the test,
the positive predictive value is affected by two factors:
the prevalence of the disease in the population tested and, when the disease is infre- quent, the specificity of the test being used
Specificity=
the probability that the test result will be negative when administered to persons who are actually without the antibody. = true negatives / all without antibody Algebraically, specificity = D / (B+D). (True Negative/(True Negative + False Positive))
Sensitivity =
the probability that the test result will be positive when administered to persons who actually have the antibody. = true positives / all with antibody Algebraically, sensitivity = A / (A+C) (True Positive /(True Positive + False Negative))
interobserver variation
variation between those reading the test results
intraobserver variation
variation in the reading of test results by the same reader
intrasubject variation
variation within individual subjects
This is called the positive predictive value (PPV) of the test.
what proportion of patients who test positive actually have the disease in question? the probability that a person with a positive screening test result actually has the antibody. = (true positives / all with positive test) Algebraically: PVP = A / (A+B).
