Dr. dr.
Juliandi Harahap, MA
Establishingdiagnosies is an imperfect
process, resulting in a probability rathar than
a certainty of being right.
A simple way of looking at the relationships
between a test’s results and the true
diagnosis is shown in table below:
Thetest is considered to be either positif or
negatif and the disease is either present or
absent.
The test has given the correct answer when
it is positive in the presence of diseses or
negative in the absence of the disease.
Thetest has been misleading if it is positive
when the disease is absent or negative when
the disease is present
PARALEL TEST: TEST A and TEST B and TEST C ARE POSITIVE
A
B
C
SERIAL TEST: TEST A or TEST B or TEST C IS POSITIVE
A BC
Target disorder Totals
(iron deficiency anemia)
Present Absent
Diagnostic Positive 731 270 1001
test result (< 65 mmol/L) a b a+b
(serum Negative 78 1500 1578
ferritin) ( 65 mmol/L) c d c+d
Totals 809 1770 2579
a+c b+d a+b+c+d
Sensitivity = a/(a+c) = 731/809 = 90%
Specificity = d/(b+d) = 1500/1770 = 85%
Likelihood ratio for a positive test result = LR+ = sens/(1-spec) = 90%/15% = 6
Likelihood ratio for a negative test result = LR - = (1-sens)/spec = 10%/85% = 0.12
Positive Predictive Value = a/(a+b) = 731/1001 = 73%
Negative Predictive Value = d/(c+d) = 1500/1578 = 95%
Pre-test probability (prevalence) = (a+c)/(a+b+c+d) = 809/2579 = 32%
Pre-test odds = prevalence/(1-prevalence) = 31%/69% = 0.45
Post-test odds = pre-test odds LR
Post-test probability = post-test odds/(post-test odds +1)
Sensitivity:the percentage of persons with
the disease of interest who have positive test
results.
= a/(a+c) x 100
Specificity:the percentage of persons
without the disease of interest who have
negative results.
= d/(d+b) x 100
PPV: the percentage of persons with positive
test results who actually have the disease of
interest.
= a/(a+b) x 100
NPV: the percentage of persons with negative
test results who do not have the disease of
interest.
= d/(d+c) x 100
Likelihood is the probability of a particular
test result for a person with the disease of
interest divided by the probability of that
test result for a person without the disease
of interest.
Likelihood Ratio for a positive test result
(LR+)
Likelihood Ratio for a negative test result
(LR-)
(LR+)is the probability of a positive test result
for a person with the disease of interest divided
by the probability of a positive test result for a
person without the disease.
LR+ = Sensitivity / (1-Specificity)
LR+ > 1: persons affected with disease of
interest are more likely to have a positive test
result than unaffected persons.
The larger the value of the LR, the stronger the
association between having a positive test
result and having the disease of interest.
LR+ value of 10 or greater is perceived as
indication of a test of high diagnostic value.
LRs >10 or <0.1 cause large changes in
likelihood.
LRs 5-10 or 0.1-0.2 cause moderate
changes.
LRs 2-5 or 0.2-0.5 cause small changes.
LRs between <2 and 0.5 cause little or no
change
Pretestprobability of disease: the probability that a
person has the disease of interest before the test is
performed.
= prevalence
Pretest odds of disease: the estimate before
diagnostic testing of the probability that a patient
has the disease of interest divided by the
probability that the patient does not have the
disease of interest.
Pretest odds= pretest probability/(1-pretest
probability)
Posttest odds of disease: as the estimate after
diagnostic testing of the probability that a patient has
the disease of interest divided by the probability that
the patient does not have the disease of interest.
Posttest odds= pretest odds x LR +
Posttest probability = posttest odds/ (1+posttest odds)
a result of obtaining a positive test result, the
estimated probability of the presence of disease has
risen from 0.08 (pretest probability) to 0.76 (posttest
probability).
Diagnostic tests that produce big changes from
pretest to post-test probabilities are important and
likely to be useful to us in our practice
Another way to express the relationship between
sensitivity and specificity is to construct a curve
RECEIVER OPERATOR CHARACTERISTIC
(ROC) CURVE plotting the true positive rate
(sensitivity) against false positive rate (1 –
specificity) over a range of cut-off values
Roc curve-1
Test that discriminate well toward the
upper left corner of the roc curve as the
cut-off point is lowered sensitivity is
progressively increased and there is little
or no loss of specificity
Can be used to decide the best cut-off
point near the “shoulder” of the roc
curve
Particularly valuable ways of comparing
alternative tests for the same diagnosis
The overall accuracy of a test can be
describe as the “area under the roc curve”
the larger the area the better the test
Roc curve--2
