PHEBP: Clinical Trials for the Treatment of Heart Disease

Question 1

Describe the key design features of clinical trials (random allocation, control group, blinding) and explain why they are important

Answer 1

1) Random Allocation:

• Random allocation is a process that assigns participants into either the experimental group or the control group randomly
• used to minimise bias and ensure that the groups are comparable in all aspects except for the intervention being studied
• Importance: minimises selection bias, balances the groups with respect to many known and unknown confounding factors, and allows for the use of probability theory to express the likelihood that any difference in outcome between groups merely reflects chance

2) Control Group:

• In a clinical trial, the control group is the group that does not receive the new treatment or intervention being studied
• Instead, they may receive no intervention, a placebo (a “fake” treatment), or a different standard treatment
• Importance: Having a control group allows researchers to compare the outcomes in those who received the new treatment against those who didn’t. This helps to determine whether any observed effects are due to the intervention or due to chance

3) Blinding:

• used to prevent research outcomes from being influenced by either the placebo effect or observer bias
• In a single-blind study, the participants do not know whether they are in the experimental group or the control group
• In a double-blind study, both the participants and the researchers do not know which individuals are in which group
• In a triple-blind study, the participants, researchers, and the statistician analysing the data are all unaware of the group assignments
• Importance: Blinding minimises bias in the study outcomes. If participants know they’re getting the new treatment, they might expect to improve and report better outcomes. Similarly, if researchers know which participants are in the experimental group, they might influence the results (intentionally or unintentionally) through their interaction with participants or bias in outcome assessment

Question 2

Outline the differences between parallel group versus crossover designs

Answer 2

Parallel Group Design:

In a parallel-group design, participants are randomly allocated to one of the treatment groups and remain in that group for the duration of the study

For example, in a trial studying the effects of a new drug, one group would receive the drug (treatment group) while the other group would receive a placebo or the standard treatment (control group).

Each participant is measured at the same time points, but they only receive one type of treatment

Advantages:

1. It is simple and straightforward to understand and implement
2. It avoids carryover effects where previous treatment could influence the outcome of the subsequent treatment, which is a major concern in crossover designs
3. It allows for studying the long-term effects of treatments

Disadvantages:

1. It may require a larger sample size compared to crossover designs because comparisons are made between subjects, not within the same subject
2. It is more susceptible to confounding due to differences between groups, even with randomisation

Crossover Design:

In a crossover design, each participant receives all treatments in a random order, with a washout period between each to minimise carryover effects

In the same example of a drug trial, participants would receive the drug for a period, followed by a washout period, and then receive the placebo or standard treatment (or vice versa)

Advantages:

1. It is statistically efficient because each participant serves as their own control. This can reduce the impact of between-subject variability and often allows for a smaller sample size.
2. It may allow for a more thorough comparison of treatments since every participant is exposed to each treatment

Disadvantages:

1. It is more complex to conduct and analyse because of the need for washout periods and the potential for carryover effects or period effects (i.e., the order of treatment influencing the outcome)
2. Participants may drop out halfway, leading to missing data for some treatments
3. It may not be suitable for treatments with permanent or long-term effects

Question 3

Explain why an intention-to-treat analysis is used and how it differs from a per-protocol analysis

Answer 3

Intention-to-Treat (ITT) Analysis:

Intention-to-treat (ITT) analysis is a principle of data analysis in randomised controlled trials where all participants are included in the analysis and are analysed in the groups to which they were randomised, regardless of whether they received or adhered to the allocated intervention

Why it’s used:

• The intention behind ITT analysis is to preserve the benefits of randomisation: to provide unbiased comparisons among the treatment groups
• By including all participants, even those who did not complete the intervention as planned, ITT analysis also reflects ‘real-world’ conditions where not all patients comply with treatment

Per-Protocol (PP) Analysis:

Per-protocol (PP) analysis, on the other hand, only includes those participants who completed the treatment originally allocated

In this case, those who did not follow the protocol – either by not completing the treatment or deviating from the protocol in any other way – are excluded from the analysis

How it differs from ITT:

• While ITT analysis includes every participant randomised regardless of their adherence to the assigned intervention
• PP analysis only includes those who followed the study protocol strictly
• This can lead to more biased estimates of the treatment effect, because the groups being compared may no longer be balanced in terms of potential confounding factors

Conclusion:

ITT analysis is considered the gold standard in randomised controlled trials because it avoids overestimating the effectiveness of an intervention that occurs with PP analysis.

However, PP analysis can provide useful information about the efficacy of the treatment under ideal conditions where all protocol is followed

Question 4

How to Interpret relative risk and absolute risk differences in treatment effects and how to estimate number needed to treat

Answer 4

Relative Risk (RR):

Relative Risk (also known as Risk Ratio) is a measure to quantify the association between an exposure (like a treatment or risk factor) and an outcome

It’s the ratio of the risk of the outcome in the exposed group to the risk in the non-exposed group

Interpretation:

• If RR = 1, the risk of the outcome is the same in both groups. If RR > 1, the risk is higher in the exposed group, indicating a potential risk factor or harmful treatment
• If RR < 1, the risk is lower in the exposed group, suggesting a protective factor or beneficial treatment

Absolute Risk Difference (ARD):

Absolute Risk Difference, also known as Risk Difference (RD), is the absolute difference in outcome rates between the control and treatment groups

Interpretation:

• If ARD = 0, there’s no difference in risk between groups
• If ARD > 0, the treatment group has a higher risk, indicating a harmful treatment
• If ARD < 0, the treatment group has a lower risk, suggesting a beneficial treatment

Number Needed to Treat (NNT):

refers to the estimated number of patients who need to be treated to prevent one additional bad outcome

Estimation:

• NNT is the inverse of the absolute risk reduction, ARR (which is the difference in risk between the control group and the treatment group)
• So, NNT = 1 / ARR

Interpretation:

• For instance, if the NNT is 5, that means you need to treat 5 people with the intervention for one person to benefit
• Smaller NNTs are better, implying that fewer people need to be treated to prevent one adverse event