Biostats Flashcards
Incidence
of NEW cases in a specified time period / population at risk during the same time period
(that is a divided by)
Prevalence
of existing cases / population at risk
Odds Ratio
OR = ad/bc
Used in case control studies (retrospective)
Relative Risk
RR = a/(a+b) / c/(c+d)
Used in cohort studies (prospective)
Relative Risk Reduction
RRR = 1 - RR
The proportion of risk reduction attributable to the intervention as compared to the control (no intervention)
Absolute Risk Reduction
ARR = Placebo Rate - Intervention Rate
The difference in risk (not the proportion) attributable to the intervention as compared to a control
Number needed to treat
NNT = 1/ARR
Number of patients who need to be treated for 1 patient to benefit
Number needed to harm
NNH = 1/AR
Number of patients who need to be exposed to a risk factor for 1 patient to be harmed
Attributable Risk
AR = a/(a+b) - c/(c+d)
The proportion of disease caused by some risk factor
Sensitivity
Sensitivity = TP / (TP + FN)
True-positive rate
- the probability that a test detects disease when disease is present
- SNOUT - when a test is highly sensitive, a negative result helps rule disease OUT
Specificity
Specificity = TN / (TN + FP)
True-negative rate
- the probability that a test indicates no disease when disease is actually absent
- SPIN - when a test is highly specific, a positive result helps rule disease IN
Positive Predictive Value
PPV = a/(a+b) - or - TP / (TP+FP)
How many positive test results are actually true positives
Negative Predictive Value
NPV = d/(c+d) -or - TN / (TN+FN)
How many negative test results are actually true negatives
In regions with a high prevalence, how are PPV and NPV effected?
PPV increases (high)
NPV decreases (low)
In regions with a low prevalence, how are PPV and NPV effected?
PPV decreases (low)
NPV increases (high)
Precision
The consistence and reproducibility of a test
If you repeated a test one million times, almost all of your results would be close to the initial test
-this speaks nothing to the ‘correctness’ of the results
Accuracy
The trueness of test measurements
If you repeated a test one million times, you’d have a lot of variety in test values, but overall the test values would be close to the actual real value
Primary vs. Secondary vs. Tertiary prevention
PST:
Prevent - prevent disease occurrence (primary)
Screen - screening early for disease (secondary)
Treat - treatment to reduce disability (tertiary)
