Randomized controlled trials are considered the current gold standard when it comes to the comparison of medical interventions. Despite their appeal, trials are not without a number of limitations:
- Given the logistical complexity involved in conducting most trials, study completion can take a substantial amount of time, often times stopping short of reaching completion since the total sample size is not attainable.
- For trials designed in the most traditional manner -- referred to as frequentist trials -- a statistical penalty is applied every time an interim analysis is conducted to evaluate intervention effectiveness. In other words, most trials will avoid "looking under the hood" while the trial is ongoing, keeping participating sites, patients, and the scientific community in the dark for years until the trial is concluded.
- Trial analyses are fairly restricted. Specifically, trials are often designed to answer very specific questions, with additional analyses being deemed exploratory and interpreted with caution.
- Since trials usually avoid interim analyses to check which intervention might be performing better, trial participants will keep receiving an intervention that might not be in their best interest, ultimately decreasing the potential benefit they could derive from participating in the study.
- Traditional trials are conducted under the assumption that nothing is known about the intervention, meaning that a lot of what has been learned in the past about that intervention is essentially discarded.
- When a traditional trial is completed, most of the time the research team across different institutions is completely disbanded. This means that all the lessons learned as a team are lost, and mistakes will likely be repeated when a new trial is initiated.
Bayesian Adaptive Trials
Bayesian Adaptive Trials provide alternatives to the issues with their traditional, "frequentist cousins." Namely:
- Compared to traditional frequentist trial, Bayesian Adaptive Trials can be conducted with 30% less patients, on average. This reduction in sample size can be translated into a substantial reduction in time to trial completion, significant cost savings, and the ability to bring an intervention more quickly to clinical practice.
- Provided that Bayesian Adaptive Trials are appropriately planned -- a process that involves a series of heavy-duty simulations -- the final design can incorporate a number of interim analyses without any statistical penalties. This ability to look at which intervention might be "winning" while the trial is still ongoing leads to a number of advantages, such as the ability to update participating sites, patients, and other stakeholders about the study results and keeping them excited about the progress the study is making in terms of knowledge regarding the intervention. In other words, by not keeping sites, patients, and others in the dark, the trial will avoid the traditional periods when the excitement regarding the trial simply wears off while the trial completion is still far away.
- Bayesian analyses allow for the exploratory of far more detail than their frequentist counterparts. This ability to drill down into the data allows for richer analyses, looking at clinical questions that are of interest to clinicians without being overly restricted by frequentist boundaries.
- Since interim analyses allow clinical researchers to have an initial feeling for which intervention might be the most effective, Bayesian Adaptive Trials can have their protocol changed, i.e. adapted, while the trial is ongoing. While these changes are all planned during the initial design rather than conducted at random, possible adaptations could include the increase in the proportion of subjects receiving a given intervention. For example, if an intervention A is found to have be doing better than B during an interim analysis, but the evidence is still not strong enough to declare it a winner, in a Bayesian Adaptive Trial it is possible to change the allocation ratio to 2 subjects receiving intervention A for every subject receiving intervention B. This change in allocation ratio maximizes the average benefit to participants in the trial, thus providing an ethical benefit while not compromising its scientific integrity.
- Bayesian Adaptive Trials are particularly well-suited for sequential trials since they can use information from one trial to enhance the design of the next trial. For example, imagine that in trial 1 we compare two doses of a given intervention, dose A versus dose B. Once this trial is completed, if we now want to initiate a second trial to now text a dose C, the trial would have to start from scratch. In a Bayesian Adaptive Trial, however, we can use the information from the first trial as "prior information" while designing the second trial. The use of prior information usually reduces sample size and improves trial effectiveness.
- Because Bayesian Adaptive Trials can be designed in sequence, a number of other logistical benefit will also ensue, such as the ability to keep the same high performance sites as members of the network, not having to train all sites regarding common protocols across trials, knowing all Institutional Review Boards and their specific requirements, ultimately providing an edge that is associated with maintaining a well-functioning team intact across projects.