Useful Formulae
1 5
MEDICAL EPIDEMIOLOGY
•
Yeah, can you believe this stuff actually matters?
•
The letters in the following refer to a standard 2 × 2 table presented
in Figure 4-1.
•
Sensitivity:
the percentage of patients with the target disease/
condition who have a positive result [A/(A + C)]. The greater the
sensitivity, the more likely the test will detect patients with the
disease. High sensitivity tests are useful clinically to
rule OUT
a
disease (SnOUT) (i.e., a negative test result would virtually exclude
the possibility of the disease).
•
Specificity:
the percentage of patients without the target disease/
condition who have a negative test result [D/(B + D)]. Very spe-
cific tests are used to confirm or
rule IN
the presence of disease
(SpIN).
•
Positive predictive value
: the percentage of persons with positive
test results who actually have the disease/condition [A/(A + B)].
•
Negative predictive value
: the percentage of persons with negative
test results in which the disease/condition is absent [D/(C + D)].
•
Number needed to treat
: the number of patients who need to be
treated to achieve one additional favorable outcome; calculated as
1/absolute risk reduction, rounded up to the nearest whole number
•
Number needed to harm
: the number of patients who, if they
received the experimental treatment, would lead to one additional
person being harmed compared with patients who receive the con-
trol treatment; calculated as 1/absolute risk increase