Behavior/Biostats Flashcards
Collects data from a group of people to assess frequency of disease (and related risk factors) at a particular point in time
Cross sectional study (observational)
“what is happening?”
Compares a group of people with disease to a group without a disease looking for prior exposure or risk factor
Case-control study (observational/retrospective)
eg: patient with COPD had higher odds of a history of smoking than patient without COPD
Odds Ratio
Case-control measure. (A/C)/(B/D)
Compares a group with a given exposure or risk factor to a group without such exposure. Looks to see if exposure increases likelihood of disease
Cohort study (observational and prospective or retrospective) eg: patient who smoked has higher risk of COPD than pt who didnt smoke
Relative risk
cohort study measure. Risk of developing disease in exposed group. (A/(A+B))/(C/(C+D))
Measures heritability/environmental influence
Twin concordance/Adoption studies
Drug trial
Phase I: safety (healthy pt)
Phase II: efficacy (diseased pt)
Phase III: compare to current meds on market (RCT)
Phase IV: long term SE
Probability a test detects disease when it’s present
Sensitivity = TP/(TP+FN)
|
Probability that a test indicates non-disease when disease is absent
Specificity = TN/(TN+FP)
|
Probability person has the disease given a positive test
Positive predictive value = TP/(TP+FP)
Probability that person is disease free given a negative test result
Negative predictive value = TN/(TN+FN)
number of new cases/population at risk in a time period
incidence
number of existing cases/population at risk in a time period
prevalance
1-RR
relative risk reduction
Difference in risk between exposed/unexposed groups
attributable risk
number of patients who need to be treated for 1 patient to benefit
number needed to treat 1/ARR
number needed to harm
number of patients who need to be exposed to a risk factor for 1 patient to be harmed 1/AR
unexposed risk - exposed risk
absolute risk reduction (ARR)
increased precision
decreased standard deviation
systematic error
decreased accuracy