Evidence medicine Flashcards
funnel pots
shows publication bias in meta analysis
symmetrical inverted funnel shows bias is unlikely vice versa
chi squared test
used to differentiate two independent groups + binary outcomes
kruskal wallis test
compares the means of two or more independent groups
per protocol analysis
determine if a treatment has a biological effect
prospective cohort study
constitutes the highest level of evidence
cross sectional study
only looks at one point in time, study relationship between exposure and outcome
Absolute risk reduction
CER - EER
number needed to treat (NNT)
1/ARR
sensivity - identify how effective a test is picking up the disease where it is present
True positive/ (TP+FP)
specifity - portion of patients without the condition who had a negative test
true negative/(TN+FP)
positive predictive value - change the patient has the condition if the diagnostic test is positive
true positive/ (TP+FP)
negative predictive value - change that the patient does not have the condition if the diagnostic test is negative
true negative/TN+FN
Lead time test
occurs when two tests for a disease are compared, the new test diagnoses the disease earlier, but there is no effect on the outcome of the disease
normal distribution
symmetrical i.e. Mean = mode = median
68.3% of values lie within 1 SD of the mean
95.4% of values lie within 2 SD of the mean
99.7% of values lie within 3 SD of the mean
