Definitions for Dr. Cluxton's Material

Question 1

Clinical Significance

Answer 1

Study results that are important enough to implement in clinical practice. Some studies are so large that very small differences between groups are statistically significant. But the magnitude of the benefit may be so small that it isn’t worthwhile to adopt in clinical practice.

Question 2

Absolute Risk Reduction (ARR)

Answer 2

• The absolute difference in rates of an outcome between treatment and control groups in a clinical trial.
• Ex: A hypothetical clinical trial compares the effect of a new statin and placebo on the incidence of stroke. Over the course of the study, the incidence of stroke is 4% with the statin and 6% with the placebo. The ARR with the statin is 2%

Question 3

Alpha

Answer 3

• The probability of concluding there is a difference between groups when there really is no difference between them
• AKA Type I Error
• Rejecting the null hypothesis when it’s actually correct
• false positive

Question 4

Beta

Answer 4

• The probability of concluding that there is no difference between treatment groups when there really is a difference
• AKA Type II Error
• Accepting the null hypothesis when it’s incorrect
• False Negative

Question 5

Bias

Answer 5

• Flaws in the design or operation of a study that lead to overestimation of the efficacy of treatment
• more easily introduced into studies that are not blinded

Question 6

Publication Bias

Answer 6

Investigators tend not to publish studies with negative outcomes. This can lead to overestimation of efficacy in meta-analysis when studies with positive outcomes are overly represented

Question 7

Recall Bias

Answer 7

People may remember things differently than how they occurred

Question 8

Selection Bias

Answer 8

• Differences between treatment and control groups that result from the way patients were selected
• Randomization and blinding should help prevent selection bias

Question 9

Case-Control study

Answer 9

A study which selects patients who have the outcome of interest (cases) and patients without that outcome (controls), and looks back in time to identify characteristics that are linked to the outcome in case patients. Case-control studies are retrospective

Question 10

Confidence Interval(CI)

Answer 10

An estimate of the range within which the true treatment effect lies. The 95% CI is the range of values within which we are 95% certain the true values lie.

Question 11

Confounder

Answer 11

a third factor in a study that affects the statistical relationship between the other two factors. A confounding variable can make it appear that there is a direct relationship between two factors when, in reality, the confounder is responsible for the relationship

Question 12

Effectiveness

Answer 12

How well a drug works in every day real-world use

Question 13

Efficacy

Answer 13

How well a drug works under ideal circumstances, like a RCT

Question 14

Endpoint

Answer 14

The outcome that is used to measure drug efficacy in a clinical trial

Question 15

Heterogeneity

Answer 15

In a meta-analysis or systematic review, when the results of individual studies are compatible with one another they are considered to be homogenous. Heterogeneity occurs when there is more variation between the study results than would be expected to occur by chance alone. A test for heterogeneity helps determine if it’s appropriate to combine studies

Question 16

Intention-to-treat analysis

Answer 16

A statistical analysis for randomized trials that includes all of the patients who were randomized to a treatment arm regardless of whether or not they finished the study. An intention-to-treat analysis is considered to mimic clinical practice more closely than an analysis that includes just the patients who completed the study

Question 17

Meta-analysis

Answer 17

The first step in a meta-analysis is the identification of all studies, published and unpublished, that address a clinical question. Criteria for study inclusion in the analysis are established beforehand. In a two-phase process, a result (point estimate or summary statistic with CI) is calculated for the data from each study. Then, if appropriate, data is pooled and a pooled mean result is calculated. Weight is given to studies with the most data. Meta-analysis can be used to increase sample size and statistical power, as well as provide enough patients for subgroup analysis

Question 18

Null Hypothesis

Answer 18

Hypothesis that there is no difference between treatment groups in a study

Question 19

Number Needed to Harm (NNH)

Answer 19

The number of patients treated with a specific therapy in order for one of them to have a bad outcome (1/absolute risk)

Question 20

Number Needed to Treat (NNT)

Answer 20

The number of patients needed to treat with a specified therapy in order for one patient to benefit from treatment. The NNT is the inverse of the absolute risk reduction (1/ ARR)

Question 21

Odds Ratio (OR)

Answer 21

An odds ratio can be used to determine risk in case control studies, as well as prospective cohort studies. In case control studies, the odds ratio is the odds of exposure in cases divided by the odds of exposure in controls. Odds ratios and relative risk are comparable when the outcome is rare. But the odds ratio can make risk appear greater when the disease or outcome is more common. In case-control studies evaluating the risk of an adverse effect, an odds ratio of 1 indicates that exposure to the drug is equally likely in cases and controls. If the odds ratio is greater than 1, the risk of exposure is greater in cases than controls. If OR < 1, the risk of exposure is smaller in cases than controls.

Question 22

p-value

Answer 22

• the level of statistical significance.
• A value of p <0.05 means that the probability that the result is due to chance is less than 1 in 20.
• The smaller the p-value the greater the statistical significance

Question 23

Power

Answer 23

• The ability of a study to detect a significant difference between treatment groups
• the probability that a study will have a statistically significant result (p<0.05)
• power = 1-beta

Question 24

Prospective study

Answer 24

Studies that begin in the present and will evaluate events as they occur in the future

Question 25

Randomization

Answer 25

• The process of assigning patients to treatment groups in a clinical trial.
• Each patient should have an equal chance of being assigned to any of the groups
• The goal of randomization is to avoid selection bias in the assignment of patients to treatment groups

Question 26

Relative Risk

Answer 26

• The risk of an event in individuals with a particular characteristic compared with the risk of that event in individuals who don’t have that characteristic.
• the probability of an event in the treatment group divided by the probability of that event in the placebo group

Question 27

Relative Risk Ratio

Answer 27

• Statistical method for reporting relative risk in cohort studies
• ratio of event rates with treatment vs. control group
• a relative risk ratio of 1 indicates a positive association between treatment and outcome
• a relative risk less than 1 indicates a negative association between treatment and outcomes

Question 28

Relative Risk Reduction

Answer 28

Relative risk subtracted from 1

Question 29

Retrospective Study

Answer 29

Studies that look back in time to evaluate events that occurred in the past

Question 30

Sample Size

Answer 30

• The number of patients required for a study to have valid results
• if there is only 1 sample in a study, the letter “N” is used to designate sample size.
• if there is more than one sample in a study, the size of these samples is designated with “n”.
• the sample size of a study should be calculated before the study begins
• sample size should increase when differences between treatment groups are small (as in studies comparing the efficacy of two drugs), as study power increases, as statistical significance increases, and if there is more variability in the outcome being measured.
• The larger the sample size, the more narrow the CI

Question 31

Sensitivity

Answer 31

• The ability of a test to reliably detect the presence of a disease
• the proportion of patients with the disease who have a positive test.
• Sensitivity = 100 x true positives/ (true positives + false negatives)

Question 32

Sensitivity analysis

Answer 32

• A statistical method to determine how sensitive the results of a study or systematic review are to changes in the data or methodology.
• particularly important to perform in meta-analyses

Question 33

Surrogate Endpoint

Answer 33

• A surrogate endpoint is an endpoint that stands in for another endpoint.
• Ex: measurement of BP as a surrogate for reducing CV events in patients with HTN

Question 34

Subgroup analysis

Answer 34

• Examination of outcomes in specific groups within a study in order to predict who benefits or is harmed the most by treatment
• Large clinical trials will often look at subgroups based on age, sex, or concomitant medical conditions
• Ideally, subgroup analyses should be defined before the study starts. Studies usually do not have enough power to perform subgroup analyses.
• With repeated subgroup analyses, false-positive results will eventually occur due to chance
• In general, subgroup analysis should only be used to identify research questions to be addressed in future clinical trials

Question 35

Systematic review

Answer 35

• Collection, review, and presentation of available studies addressing a particular clinical question
• Studies are reviewed according to specific criteria and methods
• may include meta-analysis as a method of analyzing and quantifying the results