In clinical research, Bayesian statistics provide a framework in which information beyond that collected in a particular clinical trial can be used to make statistical inferences about the treatment outcomes. Prior information (from previous trials, scientific research or “expert opinion”) can be combined with information as it is accrued during a trial, as well as with the usual data available on completion of the trial, to make efficient and timely inferences about the safety and/or efficacy of a treatment or therapy.
Due to the expensive nature of clinical trials, more and more pharmaceutical companies are becoming interested in Bayesian methods; and with on-going algorithmic development and improved computational speeds, these methods are becoming increasingly accessible and accepted.
HERE'S WHY:
At Quanticate our statistical consultants are experienced in clinical study designs and have delivered multiple trial analyses using Bayesian methods. We can provide expert advice on Bayesian adaptive designs with an approach that typically includes:
The choice of an appropriate prior based on previous studies and other existing knowledge of the treatment/therapy
Statistical modelling to inform safe and efficient dose escalation towards a MTD
The collection of robust data to demonstrate the safety/efficacy of a treatment; employing an adaptive approach to allow budgets to be used more efficiently
An adaptive design to keep sample sizes low whilst treating patients as effectively as possible
Interim Analyses using predictive probabilities to stop a trial either if the treatment is proving to be ineffective (futility) or if the treatment has already proven itself to be effective before completion (efficacy)
Best advice on the suitability of an adaptive design or Bayesian methodology to the particular research programme and design stage of that programme