Diagnostic tests Flashcards
probability that when the
disease is present, the test is positive.
Sensitivity (true positive rate)
probability that when the
disease is absent, the test is negative
Specificity (true negative rate)
Probability that a person who has a positive test
result actually has the disease.
Positive predictive
value
Probability that a person with a negative test
result actually does not have the disease
Negative predictive
value
Probability that a person who has a positive test
result actually donot has the disease.
reciprocal of PPV
Probability that a person who has a negative test
result actually has the disease.
reciprocal of NPV
Median survival rate is calculated in _______ or _______
Cohort study or clinical trial
Intention to treat:
Once randomized, always analyzed
Opposite of intention to treat is
as treated/ per protocol
if patient switches therapy they are counted as members of new group during analysis
Difference between descriptive and analytical study?
descriptive study is useful in generating the hypothesis but not used in drawing conclusions.
Examples of descriptive study:
Individial level: 1. case report 2. case series 3. cross-sectional study Population level: Correlational (ecological)
Nested case control studies:
start with cohort studies → followed over time → those who develop an outcome of interest become cases for a case control study
Advantage of Intention to treat:
helps to reduce selection bias (selective non-compliance) ; preserves randomization
Relative risk differs depending on ________
number of cases you choose
OR donot change with number of cases
OR = RR when
prevalence is <10%
rare disease assumption
Odds of an event occurring is defined as
probability of that event happening divided by probability of that event not happening
______ is the measure of strength of an association between an exposure and an outcome
Odds ratio
Effect of ↑ accuracy of diagnostic testing on incidence and prevalence
both increase
Effect of Research on incidence and prevalence
no effect on either
Precision (reliability)
The absence of _______ in a test.
random variation
Accuracy (validity)
The absence of _________ in a test.
systematic error or bias
Out of precision and accuracy ______ is not affected by sample size
accuracy
how much variability
exists in a set of values, around the mean of
these values
shown by?
Standard deviation =
p-value means:
p-value represents:
the probability of obtaining that result purely
by chance
the probability that null hypothesis is true (no association)
paired T-test
compares 2 means from same individual followed over time (baseline BMI vs BMI after treatment)
