Epidemiology/Biostats Flashcards
Cross-sectional Study
Observational, collects data from a group of people to assess frequency of disease (and related risks) at a particular point in time.
“What is happening?” Disease prevalence
Case-Control Study
Observational and retrospective
compares a group of people with the dx vs without
looks for prior exposure or risk factor
Odds Ratio
What type of study is this: “patients with COPD have higher odds of hx of smoking than those without COPD”
Case-Control Study
Relative Risk is associated with what type of Study?
Cohort Study
Compares a group with a given exposure or risk factor to a group without such exposure. looks to see is exposure increases likelihood of disease
Cohort study (can be prospective or retrospective
Twin concordance study
compares the frequency with which both monozygotic and dizygotic twins develop the same disease
measures inheritability and influence of environmental factors
Adoption Study
compares siblings raised by biological vs adoptive parents (measures heritability vs environmental influence)
Compares therapeutic benefit of 2+ tx or tx and placebo.
randomized, controlled, and double blinded (or triple blind)
Clinical trial
Phase I Drug Trial
small number of healthy volunteers to determine how safe the drug is
Phase II Drug Trial
small number of patients with dx of interest to see is tx works.
asses efficacy, optimal dosing, and A/E
Phase III Drug Trial
Lg # of patients randomly assigned either experimental tx and a placebo (or known outcome tx)
compares new tx to current std of care
Phase IV Drug Trial
Postmarketing surveillance trial of patients after approval
detects rare or LT A/E
Sensitivity
true-positive rate, high sensitivity test used for screening disease with low prevalence
TP/(TP+FN)
Specificity
True-negative rate, the probability that a test indicates non-dx when dx is absent
high specificity used for confirmation after +screening test
TN/(TN+FP)
Positive Predictive Value
probability that person actually has the dx when receives a + test result
TP/(TP+FP)
Negative Predictive Value
Probability that person is actually dx free when give a (-) test result
TN/(FN+TN)
Incidence
New Cases (#new cases)/(pop at risk at same time)
Prevalence
ALL CURRENT CASES
(#existing cases)/(pop at risk)
or (incidence rate) * (av dx length)
Odds ratio
used in case-control
odds that group with dx was exposed to risk factor divided by odds that group w/o dx was exposed
Relative Risk
Cohort studies
risk of developing a dx in exposed group divided by risk in unexposed group
Relative Risk Reduction
proportion of risk reduction attributable to the intervention as compared to a control
RRR= 1-RR
Attributable RIsk
difference in risk between exposed and unexposed groups, or proportion of dx occurrences that are attributable to exposure
Absolute Risk Reduction (ARR)
The difference in risk attributable to the intervention as compared to the comtrol.
Number Needed to Tx
number of patients who need to be treated for 1 patient to benefit is 1/ARR
Number Needed to Harm
number of patients who need to be exposed to risk factor to 1 patient to be harmed.
1/AR
Reduces Precision in a test
Random Error
Reliability, consistency and reproducibility of a test
Precision
absence of random variation in a test
increase precision
decrease std deviation
Validity, Trueness of test measurements
Accuracy
Absence of systemic error or bias in a test
Accuracy
Nonrandom assignment to particpate in a study group.
selection bias
Berkson bias
a study looking only at inpatients, a type of selection bias
How to reduce selection bias
randomization
Recall Bias
Awareness of disorder alters recall by subjects; common in retrospective studies
Strategy to reduce recall bias
decrease time from exposure to follow up
Hawthorne Effect
Groups who know they are being studied behave differently than they would otherwise, this is a type of measurement bias
Strategy to reduce Hawthorne effect
use palcebo control groups with blinding to reduce influence of participants and researchers
Procedure Bias
subjects in different groups are not treated the same
Observer-expectancy Bias
researcher’s belief in the efficacy of a tx changes the outcome of that tx
Pygmalion effect
observer-expectancy bias
researcher expects + outcome and will more likekly see + outcome whether it be true or not
Confounding Bias
When a factor is related to both the exposure and outcome, but not on the causal pathway
factor distorts effect of exposure
Lead-time bias
early detection is confused with increased survival; seen with improved screening techniques
Mean
(sum of values)/(total # of values)
Median
Middle value of a list of data sorted from least to greatest
Mode
most common value
Standard Deviation
how much variability exists from the mean in a set of values
Standard error of the mean
an estimation of how much variability exists between the sample mean and the true population mean
SEM = SD/sqrt(N) n being sample size
SEM decreases and sample size increases
Gaussian
bell-shaped, normal distribution
mean = median = mode
68%, 98%, 99.7%
Bimodal
suggests two different populations, double hump distributions
Positive Skew
mean>median>mode
longer tail on the right
Negative Skew
mean < median < mode
longer tail on the left
Null Hypothesis (Ho)
hypothesis of no difference. There is no association between the disease and the risk factor
Alternative Hypothesis (H1)
there is some association between the disease and the risk factor
Correct Result
Stating there is an effect or difference when on exists (Ho is rejected)
Stating that there is not an effect of difference when non exists (H1 is accepted)
Type I error (alpha)
False positive error
alpha is the probability of making a type I error
p is judged by a preset alpha level of significance
p < 0.05
there is evidence against the null hypothesis, reject the null hypothesis
the test is acceptable
Type II error (beta)
false negative error
Statistical power
1-beta, beta being the probability of making a Type II error
probability of rejecting the null hypothesis when it is false
How to increase Power
increase sample size, increase expected effect size, increase precisionof measurement
Meta-analysis
Pools data and integrate results from several similar studies to reach an overall conclusion
this is limited by bias or quality of studies selected
Confidence Interval
range of value in which a specified probability of the means of repeated sample would be expected to fall
t-test
checks differences between means of 2 groups
Ex. comparing the mean BP between men and women, what test would you use’?
t-test
ANOVA
checks differences between means of 3 or more groups
Ex. Comparing mean BP between 3 different ethnic groups, what test would you use?
ANOVA
Chi-square
checks difference between 2+ percentages or populations of CATEGORICAL outcomes
Ex. comparing the percentage of members of 3 different ethnic groups who have essential HTN
Chi-square
Pearson correlation coefficient
r is always between -1 and 1. closer to absolute 1, the more linear it is. -r has negative correlation, +r has positive correlation
Primary Disease Prevention
Prevent disease from occurring
Secondary Disease Prevention
Screening Early for disease
Tertiary Disease Prevention
treatment to reduce disability from disease
Quaternary Disease Prevention
identifying patients at risk of unnecessary treatment, protecting from the harm of new interventions
Medicare
for patient >65y/o or <65 with certain disabilities, and those with end-stage renal disease
Medicaid
Joint federal and state health assistance for people with very low income
Obligation to respect patients as individuals and honor their preference in accepting/not accepting medical care
Respect of Patient Autonomy
Act in the patient’s best interest.
Beneficence
“Do no harm”
Nonmaleficience
Treat people fairly and equitably
Justice
4 think informed consent legal requires
disclosure: discussion of pertinent info
understanding: ability to comprehand
mental capacity: unless incompetent a legal determination
voluntariness: freedom from coercion and manipulation
Situations in which parental consent is usually not requires
Sex like contraception, STDs and pregnancy, Drugs like addiction, or “rock and roll” emergency/trauma
Priority of surrogates in decision making
spouse; adult children; parents; adult siblings; other relatives
general exceptions of patient confidentiality
potential physical harm to others, harm to self, no alt. means to warn ot protect those at risk
reportable disease, abuse, impaired drivers like epilepsy, suicidal/homicidal
Tarasoff Decision
California Supreme Court, physician can directly inform and protect potential victim from harm
Who lives in a pineapple under the sea?
SPONGEBOB SQUAREPANTS