Study design

Question 1

Randomisation

Answer 1

The process of assigning trial subjects to treatment or control groups using an element of chance, so that each participant has an equal chance of being allocated to either group.

This is to reduce allocation bias and balance known and unknown possible confounding factors, such that any difference between the two groups is purely by chance.

Question 2

Stratified randomisation

Answer 2

Prevents imbalance between treatment groups for known factors that influence prognosis or treatment responsiveness. As a result, stratification may prevent type I error and improve power for small trials (<400 patients), but only when the stratification factors have a large effect on the prognosis.

Question 3

Allocation concealment

Answer 3

Refers to masking the randomisation code or sequence before patients are recruited so that investigators don’t know what group the next patient will be randomised to, thus avoiding selection bias

Question 4

Blinding

Answer 4

Involves masking the allocation of the treatment group after randomisation, so one or more parties involved in the trial are not aware whether the participants are in the intervention or control group. This aims to remove bias, including performance and observer bias.

Question 5

Efficacy

Answer 5

The capacity for the therapeutic effect of a given intervention, e.g. whether a drug demonstrates a health benefit over a placebo or other intervention when tested in an ideal situation. These are called explanatory trials.

Question 6

Effectiveness

Answer 6

How well an intervention works in practice, i.e. in the real world outside a clinical trial. This tends to be lower than the efficacy. There are called pragmatic trials.

Question 7

Placebo

Answer 7

Traditionally refers to a substance or treatment with no active therapeutic effect. In medical research, it is unethical to give a substance without therapeutic effect when one is available. Hence, a placebo refers to the control used, for example, the gold-standard intervention in which the intervention of interest is being measured against.

Question 8

Surrogate endpoint

Answer 8

A variable that is relatively easily measured and which predicts a rare or distant outcome of the intervention tested. It is not a direct measure of either harm or clinical benefit.

Question 9

Surrogate outcome

Answer 9

Markers that are substituted in for a clinical outcome e.g. ejection fraction as an indicator of disease severity in heart failure

Question 10

Composite outcome

Answer 10

A combination of variables e.g. a scoring tool. Useful when each variable in the scoring tool is rare as it gives power to the study. Difficult to interpret.

Question 11

Internal validity

Answer 11

the degree to which the causal relationships found in a study can be trusted (with bias reducing this).

Question 12

Secondary research

Answer 12

E.g. systematic review/literature review. This means research that amalgamates the results of many studies, largely negating the influence of bias on the results.

Question 13

Systematic review definition

Answer 13

Assesses all the published literature on a
research question, using a structured protocol to review each paper. This is useful for establishing the current evidence base for a particular research question.

Question 14

Meta-analysis definition

Answer 14

A meta-analysis is the statistical analysis of the results of several trials, which are combined in order to minimise bias, reach a more accurate ‘true’ population effect, and increase the statistical power of the evidence.

(May accompany a systematic review and involves the
statistical analysis of the results of many research trials. By combining the results of several trials together and increasing the population size, it may be possible to detect statistical differences that previously could not be found. Results of a meta-analysis are presented as a forest plot.)

Question 15

Advantages of SR and MA

Answer 15

1. More accurate assessment of the ‘true’ population effect.
2. Larger patient numbers lead to increased power and reduce type II error (which is the erroneous conclusion that an intervention has no effect).
3. Less bias (funnel plot → publication bias assessment, heterogeneity analysis → method and data collection)

Question 16

Disadvantages of SR and MA

Answer 16

1. Direct comparisons between studies are difficult, due to differing methodology.
2. It can introduce types of bias (selection, publication (consider grey literature), and language bias (non-English articles), selective reporting bias)

Question 17

Steps followed in a SR

Answer 17

1. Check for existing reviews/protocols
2. Identify your research question
3. Define inclusion/exclusion criteria
4. Search for studies
5. Select studies for inclusion based on pre-defined criteria
6. Extract data from included studies
7. Evaluated risk of bias of included studies
8. Present results and assess quality of evidence

Question 18

Funnel plot:

Answer 18

Scatter plot of the intervention effect estimates from
individual studies against some measure of each study’s size or precision.

Question 19

Steps followed in a MA

Answer 19

1. Frame a question (based on a theory):
   PICOK method.
2. Run a search
3. Screen
4. Extract data
5. Determine the quality of information in the articles (assess internal validity but also use GRADE criteria). Critically appraise the information contained within each study. You must decide if the study meets the internal validity criteria. A method to ascertain the quality of each outcome within an article is to use the GRADE criteria (grading recommendations assessment,
   development, and evaluation).
6. Determine the extent to which these articles are heterogeneous.
7. Estimate the summary effect size in the form of ORs and using both fixed and random effects models.
8. Construct a forest plot
9. Determine the extent to which these articles have publication bias and run a funnel plot.
10. Conduct subgroup analyses and meta regression to test if there are subsets of research that capture the summary effects.

Question 20

What is the problem with surrogate outcomes?

Answer 20

May not reflect outcomes that are important to patients

Question 21

RCT

Answer 21

Study where participants are randomly allocated to an experimental or comparison group. Outcomes in each group are compared to determine the effect of the intervention

Question 22

RCT pros

Answer 22

1. Gold standard for studying treatment effects
2. Random allocation reduces selection bias and equally distributes confounding factors between arms
3. Prospective: allows one to conclude causation between intervention and outcome (and outcomes determined a priori)
4. Reliably measures efficacy
5. Allows for meta-analyses

Question 23

RCT cons

Answer 23

1. Difficult
2. Time-consuming
3. Expensive
4. May be prone to underpowering
5. Ethical problems in giving different treatments to the groups

Question 24

Prospective cohort study definition

Answer 24

Observational, prospective. Two groups selected on basis of differences in their exposure to a particular agent and followed up to see how many in each group develop a particular disease.

Question 25

Prospective cohort study pros

Answer 25

1. Can answer questions about aetiology and prognosis
2. Direct estimation of disease incidence rates
3. Can assess temporal relationships and causal links
4. Can assess multiple outcomes (that may be associated with multiple exposures…)
5. Good for rare exposures
6. Can estimate risk ratios and odds ratios

Question 26

Prospective cohort study cons

Answer 26

1. Can take a long time from exposure to measured outcomes
2. Cannot be used if diseases have long latency period
3. Expensive to set up and maintain
4. Bias is an issue if subjects drop out over time (often a large cohort is needed)

Question 27

Advantage of prospective vs. retrospective cohort studies

Answer 27

Prospective: able to control design, sampling, data collection and follow-up methods, and can measure all variables of interest.

Retrospective: time efficient and inexpensive, and easy to obtain large samples.

Question 28

Case-control study definition

Answer 28

Patients with a particular disease or condition are identified and ‘matched’ with controls. Data is then collected on past exposure to a possible causal agent.

Question 29

Case-control pros

Answer 29

1. Good for studying rare disease
2. Useful when there is a long latency period between a risk factor and an outcome
3. Quick and cheap as few subjects required
4. Requires fewer patients - no loss to follow up

Question 30

Case-control cons

Answer 30

1. Can be difficult to match to the control group (a potential source of bias is the precise definition of who counts as a case. Subject to selection bias.)
2. Rely on recall and records to identify risk factors (recall bias)
3. Temporal relationship difficult as subjects forget about sequence of events (symptom appearance) - relies on reverse causation

Question 31

Retrospective design is susceptible to reverse causation. What is this?

Answer 31

A form of protopathic bias - this is when the applied treatment for disease appears to cause the outcome

Question 32

What is a cross-sectional study?

Answer 32

This is a type of observational study where data is analysed at a specific moment in time e.g., how many deep veins thromboses are present in a hospital?

Question 33

What do cross-sectional studies aim to do?

Answer 33

Cross-sectional studies aim to take an overview of the whole population (entire hospital population) and not a subgroup which is seen in case-control studies (pregnant women).

Question 34

What is a downside to cross-sectional studies?

Answer 34

It is purely descriptive and can only show correlation, not causation (e.g. pregnancy shown to correlate with deep vein thrombosis but not cause it).

Question 35

What is a case report?

Answer 35

An account of the presentation, diagnosis, treatment, and follow-up of an individual patient. Case reports often combine the accounts of multiple patients with similar presentations or diagnoses.

Question 36

What is the purpose of a case report?

Answer 36

They are often used to describe unusual associations between symptoms and disease, novel treatments, and new insights into the pathogenesis of a disease. The evidence produced is anecdotal and for that reason is often used as a springboard for more robust research e.g., a case-control study.

Question 37

The registration of clinical trials has been a formal condition of

Answer 37

Research Ethics Committee approval

Question 38

Registration of a trial should ideally occur

Answer 38

Before the first participant is recruited

Question 39

Randomisation techniques

Answer 39

Fixed randomisation: simple, block, stratified. Other: cluster, adaptive

Question 40

One difference between retrospective cohort and case-control studies?***

Answer 40

RC: People without the outcome are chosen at the start and the natural course of each group is observed over time. - uses RR

Case control: People with the outcome have been chosen from the start. Uses OR - to measure the strength of association between the exposure and the outcome.

BUT Odds/risk ratios: odds ratio for retrospective studies, risk ratio for prospective
studies???

https://ard.bmj.com/content/case-control-or-retrospective-cohort-study-comment-article-martinez-zamorra-et-al

In retrospective studies, the total number of exposed people is not available → RR can’t be
calculated; an OR is used instead
▪ In prospective studies (e.g. cohort studies), where the number at risk is available, either RR or
OR can be calculated