Short steps on how to read a paper. Part 9: Randomisation and allocation concealment.

This week’s short step to reading a paper is on randomisation and allocation concealment. I hope that it supplements the information in our post on the method of a paper.

Investigators use these methods to minimise selection bias in a trial. In effect, they make it tricky for the operators to influence the treatment allocation to participants.  I will not go into the theory behind the methods but I shall try to simply explain these concepts.   The most crucial point is that the authors should clearly state their randomisation and allocation concealment methods. If they do not do this, then you may conclude that the study is at risk of bias.

Let’s look at randomisation first.

Randomisation

Investigators randomise treatments to produce an unpredictable sequence of allocations. As a result, they allocated treatment by chance. Importantly, it is not influenced by the operator. There are several methods of randomisation.

Simple: This is equivalent to fair coin tossing.  However, its main drawback is that the group sizes may be unbalanced. Furthermore, there may be differences in gender between groups.

There are two solutions to this problem. These are:

Permuted block randomisation: Investigators do this to keep the sizes of the treatment groups similar.

Stratified randomisation: This is done to make sure that the covariates are balanced between the group. For example, gender.  Again the authors should explain the method of randomisation.  If they did not, then the study may be subject to bias.

Allocation Concealment

This is a simple concept. Investigators use allocation concealment to hide the allocation of a participant from other people.  In other words, it prevents investigators from choosing or being suspected of selecting interventions.  They may do this because they have a preference for treatment for an individual participant.  If they can work out the likely intervention produced by the randomisation, and they disagreed with it, they may not enter the patient into the study.

Investigators commonly use two methods for concealment in orthodontic trials. In the first method they use sequentially numbered, opaque, sealed envelopes.  The investigator discovers the allocation when they open the envelope. Unfortunately, sealed envelopes are not totally secure. This is because investigators can open the envelopes or hold them up to the light.  As a result, it has been suggested that sealed envelopes are not acceptable. An alternative is central allocation. In fact,  most well-run clinical trials use a method of central allocation. In this method, the investigators send the participants details to an external study team, and this team randomises the patient to treatment.  The allocation is then fed back to the investigator. There are many web-based methods of doing this.  This is much more secure and minimises the risk of selection bias.

I hope that I have given you some useful information  to consider when looking at this critical part of reporting a clinical trial. Next week, Padhraig is going to cover statistics.