Upgrade to remove ads
Only $35.99/year

Epidemiology

Terms in this set (52)

mistakenly attributing increased survival of patients
to a screening intervention when longer survival is only a reflection of
earlier detection in the preclinical phase of disease.
Lead time bias
Recall Bias
error due to differences in accuracy or completeness of
recall to memory of past events or experiences. Particularly relevant
to case control studies (CCS).
Referral bias
- the proportion of more severe or unusual cases tends
to be artificially higher at tertiary care centers.
Selection bias
an error in patient assignment between groups that
permits a confounding variable to arise from the study design rather
than by chance alone.
Spectrum bias
occurs because of a difference in the spectrum and
severity of disease between the population where the diagnostic test
was developed and the clinical population that the test is applied to..
The disease subjects in the development population tend to be the

"sickest of the sick" with few false negatives (and so Se is over-
estimated) while the non-disease population tends to be the "wellest

of the well" with few FP results (and so Sp is overestimated)
Verification Bias
when the decision to conduct the confirmatory or
gold (reference) standard test is influenced by the result of the
diagnostic test under study. Results in overly optimistic estimate of
Se and an underestimate of Sp (a.k.a. work-up bias or test-referral
bias).
Volunteer bias
- people who choose to enroll in clinical research or
participate in a survey may be systematically different (e.g. healthier,
or more motivated) from your patients (a.k.a. response bias).
heterogeneity
Differences between patients (clinical heterogeneity) or differences in the

results of different studies (statistical heterogeneity).
Incidence
Number of new cases of disease occurring during a specified period of
time; expressed either as a percentage (or proportion) of the number of
people at risk (i.e., cumulative incidence rate [CIR]) or the number of new
cases occurring per person time (i.e., incidence density rate - IDR).
Internal Validity
The degree to which inferences drawn from a specific study are
accurate. Internal validity requires a careful assessment of the study's
methodology to determine whether the observed findings are accurate.
Internal validity implies that apart from random error the study's findings
cannot be ascribed to a systematic error or bias; in other words the study
does not suffer from confounding, selection or information bias to an
important degree (judgment is required here). Thus RCT's have high
internal validity. Contrast with external validity or generalizability.
Kappa (K)
A measure of reliability or agreement between two raters for categorical
or qualitative data (e.g., two physicians independently reading x-ray
films). Kappa adjusts for the agreement that would be expected to occur
due to chance alone, and is thus referred to a chance-corrected
agreement. Kappa is preferred over other agreement measures such as
the overall % agreement which is highly influenced by the prevalence of
the condition being evaluated. Kappa ranges from -1 to +1. Values above
0.80 indicate excellent agreement, values 0.6-0.8 indicates substantial
agreement, values 0.4-0.6 indicate moderate agreement, and values <
0.4 indicate fair or poor agreement.
Likelihood Ratio
A ratio of likelihoods (or probabilities) for a given test result. The first is
the probability that a given test result occurs among people with disease.
The second is the probability that the same test result occurs among
people without disease. The ratio of these 2 probabilities (or likelihoods)
is the LR. It measures the power of a test to change the pre-test into the
post-test probability of a disease being present.
This ratio expresses the likelihood that a given test result would be
expected to occur in patients with the target disorder compared to the
likelihood of that same result in patients without that disorder. The LR for
a given test result compares the likelihood of the result occurring in
patients with disease to the likelihood of the result occurring in patients
without disease. LRs contrast the proportions of patients with and
without disease who have a given test result.
Number Needed to Harm (NNH)
The number of patients who would need to be treated over a specific
period of time before one adverse side-effect of the treatment will occur.
It is the inverse of the absolute risk increase [ARI] (in the context of a
RCT, the ARI is calculated as the EER - CER, where the event rates are
adverse events, and by implication, adverse events are more common in
the intervention, compared to control group).
Number Needed to Treat (NNT)
The number of patients who need to be treated over a specific period of
time to prevent one bad outcome. When discussing NNTs it is important
to specify the treatment, its duration, and the bad outcome being
prevented. It is the inverse of the absolute risk reduction (ARR).
Odds Ratio
The odds ratio is most often used in case-control study (CCS) designs to
describe the magnitude or strength of an association between an
exposure and the outcome of interest (i.e. the odds of exposure in cases
compared to the odds of exposure in the controls - it is therefore
calculated as a ratio of odds). Because the actual underlying disease
risks (or CIRs) in the exposed and unexposed groups cannot be
calculated in a CCS design, the OR is used to approximate the RR. The
OR more closely approximates the RR when the outcome of interest is
infrequent or rare (i.e., <10%). As a measure of the strength of
association between an exposure and outcome the OR has the same
interpretation as the RR. The OR is calculated as the cross-product ratio
(a.d/b.c) where a, b, c, and d represent the respective cell sizes.
P-Value
The probability of obtaining the value of the test statistic at least as large
as the one observed, under the assumption that the H0 is true (i.e.
P(data|H0 true)). The smaller the p-value, the lower your degree of belief
is in the null hypothesis being true. From a hypothesis testing standpoint
the p-value is used to make a decision based on the available data.
{note that increasingly the reporting of confidence intervals (CI) are
preferred over p-values because they provide much more useful
information - including the precision of the data and their possible clinical
significance }.
Population attributable risk (PAR)
The incidence of disease in a population that is associated with a risk
factor. Calculated from the Attributable risk (or RD) and the prevalence
(P) of the risk factor in the population i.e.,
PAR = Attributable risk x P
OR, it can be calculated as:
PAR = Total Incidence minus Incidence in unexposed
Example: Thromboembolic disease (TED) and oral contraceptives (OC):
Incidence of TED in overall population = 7 per 10,000 person years
Incidence of TED in OC users = 16 per 10,000 person years
Incidence of TED in non-OC users = 4 per 10,000 person years
25% of women of reproductive age take OC
So, PAR = [16 - 4] x 0.25 = 3 per 10,000 person years. This represents
the excess incidence of TED in the population due to OC use.
Population attributable risk fraction (PARF) aka etiologic fraction
The fraction of disease in a population that is attributed to exposure to a
risk factor. Under the assumption that the risk factor is a cause of the
disease, it represents the maximum potential impact on disease
incidence if the risk factor was removed. It can be calculated from the
PAR as:
PARF = PAR/Total Disease Incidence
OR, it can be calculated directly from the RR and P as follows:
PARF = P(RR-1)/ [1 + P(RR-1)]
Example: Thromboembolic disease (TED) and oral contraceptives (OC):
PARF = PAR/Total Disease Incidence
PARF = 3 per 10,000/7 per 10,0000 = 43%
PARF = P(RR-1)/ [1 + P(RR-1)]
PARF = 0.25(4-1)/ [1 + 0.25(4-1)] = 43%. This represents the fraction of
all TED in the population that is due to OC use.
Power
Ability to detect a difference between two experimental groups if one in

fact exists (1 - beta).
Positive Predictive value
proportion of people with a positive test who have disease
Negative Predictive Value
Proportion of people with a negative test who are free of disease
Relative Risk (Risk Ratio)
The relative probability or risk of an event or outcome in one group
compared to another. In a RCT, it is calculated as the ratio of risk in the
treatment or experimental group (EER) to the risk in the control group
(CER), and is a measure of the efficacy (or magnitude) of the treatment
effect. In a cohort study, where it is similarly used to express the
magnitude or strength of an association, it is calculated as the ratio of
risk of disease or death among an exposed population to the risk among
the unexposed population.
RR = EER / CER
Relative Risk Reduction/ Increase (RRR/RRI)
The percent reduction in an outcome event in the experimental group as
compared to the control group. It is the complement of RR or the
proportion of risk that's removed by the intervention. Unlike the ARR the
RRR is assumed to be a constant entity - that is, it is assumed not to
change from one population (study) to another. It therefore represents a
fixed measure of the efficacy of an intervention (contrast with the ARR
which is responsive to changes in the baseline event rates).
RRR = 1 - Relative Risk
RRR = CER - EER / CER x 100
{Or obviously ... RRR = ARR / CER}
The relative risk increase (RRI) is the percent increase in an outcome in
the experimental group as compared to the control group, calculated as
RRI = RR - 1.
The distinction between RRR and RRI can get confusion hence many
people prefer to use the Risk Difference which is simply the absolute
difference between the EER and CER.
Sensitivity
The proportion of people with disease who have a positive test or

P(T+|D+)

SnNout When a test with a high sensitivity is negative, it effectively rules out the

diagnosis of disease.
Specificity
The proportion of people without disease who have a negative test or

P(T-|D-).

SpPin When a test is highly specific, a positive result can rule in the diagnosis.
Case Series
A collection or a report of the series of patients with

an outcome of interest. No control group is involved.
Case control study (CCS)
- Identifies patients who have a condition
or outcome of interest (cases) and patients who do not have the
condition or outcome (controls). The frequency that subjects are
exposed to a risk factor of interest is then compared between the
cases and controls. Because of the design of the CCS, disease rates
cannot be directly measured (contrast this with the cohort study
design). Thus the comparison between cases and controls is actually
done by calculating the odds of exposure in cases and controls. The
ratio of these 2 odds results in the odds ratio (OR) which is usually a
good approximation of the relative risk (RR)
Advantages: it is relatively quick and inexpensive requiring fewer
subjects than other study designs. It is often times the only feasible
method for investigating very rare disorders or when a long lag time
exists between an exposure of interest and development of the
outcome/disease of interest. It is also particularly helpful in studies of
outbreak investigations where a quick answer followed by a quick
response is required. Disadvantages: recall bias, unknown
confounding variables, and difficulty selecting appropriate control
groups.
Crossover Design
A method of comparing 2 or more treatments or
interventions in which all subjects are switched to the alternate
treatment after completion of the first treatment. Typically allocation
to the first treatment is by a random process. Since all subjects serve
as their own controls, error variance is reduced.
Cross Sectional Survey
The observation of a defined population at
a single point in time or during a specific time interval. Exposure and
outcome are determined simultaneously. Also referred to as a
prevalence survey because this is the only epidemiological
frequency measure that can be measured (in other words incidence
rates cannot be generated from this design)
Cohort Study
Involves identification of two groups (cohorts) of
patients who are defined according to whether they were exposure
to a factor of interest e.g., smokers and non-smokers . The cohorts
are then followed over time and the incidence rates for the outcome
of interest in each group are measured. The ratio of these incidence
rates results in the relative risk (RR) which quantifies the magnitude
of association between the factor and outcome (disease). Note that
when the follow-up occurs in a forward direction the study is referred
to as a prospective cohort. When follow-up is done based on
historical information it is referred to as a retrospective cohort).
Advantages: can establish clear temporal relationships between
exposure and disease onset. Are able to generate incidence rates .
Disadvantages: control/unexposed groups may be difficult to identify,
exposure to a variable may be linked to a hidden confounding
variable, blinding is often not possible, randomization is not present.
For relatively rare diseases of interest, cohort studies require huge
sample sizes and long f/u (hence they are slow and expensive).
Randomized Controlled Trial
A group of patients is randomized
into an experimental group and into a controlled group. These
groups are then followed up and various outcomes of interest are
documented. RCT's are the ultimate standard by which new
therapeutic maneuvers are judged. Randomization should result in
the equal distribution of both known and unknown confounding
variables into each group. An unbiased RCT also requires
concealment and where feasible blinding.
Disadvantages: often impractical, limited generalizability, volunteer
bias, significant expense, and sometimes ethical difficulties.
Systematic Review
A formal review of a focused clinical question
based on a comprehensive search strategy and structured critical
appraisal designed to reduce the likelihood of bias. No quantitative
summary is generated however.
Meta-Analysis
A systematic review which uses quantitative
methods to combine the results of several studies into a pooled
summary estimate.
Incidence density rate
accounts for varying time periods of follow-up
Case-fatality rate
the proportion of persons diagnosed with a specific disease who die from that disease
Attack rate
an incidence rate calculated for a particular population for a single disease outbreak and expressed as a percentage
mortality rate
number of deaths from a disease in relation to the population in a given time
cumulative incidence rate
reflects the cumulative effect of the incidence rate over the time period, whether it is a month, a year, or several years.
Absolute Risk Reduction
The difference in risk (not the proportion) attributable to the intervention as compared to a control (eg, if 8% of people who receive a placebo vaccine develop the flu vs 2%
of people who receive a flu vaccine, then ARR = 8% − 2% = 6% = .06).
Attributable Risk
The difference in risk between exposed and unexposed groups (eg, if risk of lung cancer in smokers is 21% and risk in nonsmokers is 1%, then the attributable risk is 20%).
Continuous interval
continuous if and only if it is continuous at every point on the interval
Discrete interval variable
...
nominal categorical variable
a categorical variable in which the categories do not have a natural order
Ordinal Categorical variable
a categorical variable in which the categories have a natural order
central tendency
Mean = (sum of values)/(total number of values).
Median = middle value of a list of data sorted from least to greatest.
Mode = most common value.
Most affected by outliers (extreme values).
If there is an even number of values, the median will be the average of the middle two values.
Least affected by outliers.
external validity
extent to which we can generalize findings to real-world settings
forest plot
a graph that displays the point estimates and confidence intervals of individual studies included in a meta-analysis or systematic review as a series of parallel lines.
Censoring
Loss of subjects from a follow-up study; the occurrence of the event of interest (i.e. developing a disease or death) among such subjects is uncertain after a specified time when it was known that the event of interest had not occurred; it is not known, however, if or when the event of interest occurred subsequently. Such subjects are considered censored.
Survival analysis
a class of statistical procedures for analyzing data for studies that follow subjects over time.
channeling bias
pt at highest risk gets treatment (prescribe a specific type of treatment based on underlying comorbidity or prognosis)
Type 1 error
alpha

Stating that there is an effect or difference when none exists (null hypothesis incorrectly rejected in favor of alternative hypothesis).
α is the probability of making a type I error. p is judged against a preset α level of significance (usually 0.05). If p < 0.05, then there is less than a 5% chance that the data will show something that is not really there.

Also known as false-positive error.
α = you accused an innocent man.
You can never "prove" the alternate hypothesis,
but you can reject the null hypothesis as being very unlikely.
Type 2 error
beta

Stating that there is not an effect or difference when one exists (null hypothesis is not rejected when it is in fact false).
β is the probability of making a type II error. β is related to statistical power (1 - β), which is the probability of rejecting the null hypothesis when it is false.
power andβ by:
sample size
expected effect size
precision of measurement

Also known as false-negative error.
β = you blindly let the guilty man go free.
If yousample size, youpower. There is power
in numbers.
Students also viewed