The flashcards below were created by user
Anonymous
on FreezingBlue Flashcards.

Sensitivity
prob that patient with a disease will have positie test result, won't miss people with a disease, rules out those without dz (few false neg)

Specificity
prob that patient without disease will have a negative test result, rules in those with disease (low false positive)

False neg and false positive ratio
False neg ratio=1sens
False pos ratio=1spec

PPV
prob that patient with a positive test actually has disease, more specific=high ppv, higher disease prevalence, higher ppv

npv
 prob that patient with neg test result doesnt have disease, more sensitive, higher nov.
 lower disease prev, higher npv

Positive likelihood radio
 sens/1spec
 Fraction of patients with a disease who have a positive test divided by those without a disease who have a positive test
 Shows the probability of a disease if the test is +

negative likelihood ratio
 1sens/spec
 shows prob of disease are dec if test neg

Cohort study
 group of people assembled none who has the outcome of interest(the disease) but all who could experience that outcome. Followed over time and incidence of outcome is compared over exposure groups
 Can be prospective or retrospective

Case control study
 series of cases identified and a set of controls sampled from the underlying pop to estimate the frequency of exposure in the population at risk of outcome. Compares frequency of exposure to a possible risk factor in two groups.
 Ex: alcohol intake among individuals with breast cancer compared to that of people without breast cancer

Relative risk
 incidence in exposed people/incidence in unexposed
 (a/(a+B))/(c/c(c+d))

Odds ratio
 estimate of relative risk that is used in case control studies
 odds that disease person is exposed/odds that non diseased person is exposed
 ad/bc

