Skip to content

Thinking of Clinical Development from a Bayesian Lens

Program and portfolio optimization creates a framework throughout the course of the clinical development journey, that enables trial sponsors to make decisions about when to continue a clinical trial. A critical factor in the ability to optimize clinical development at this high level requires the construction of decision rules that clinical trial sponsors can use to determine whether a trial should proceed from Proof of Concept to Phase 2b, and from Phase 2b to Phase 3.

According to a recent article by Cytel co-founder Nitin Patel and Chief Scientific Officer Yannis Jemiai, a key factor in the construction of such decision rules is the ability to ‘explicitly model the relationship between trial designs and performance criteria.’ [1] Their paper, a part of an award-winning book Bayesian Methods in Pharmaceutical Research, offers an overview of where Bayesian methods should be injected into the process of optimization at the program and portfolio level.

The essential motivator of this line of analysis revolves around the idea of the probability of success of a new medicine. The authors note that at each point on the clinical development journey, when a Go/No-Go decision must be made, a trial sponsor is essentially engaging in a Bayesian update about beliefs regarding probability of success. A Bayesian update is an update (or improvement) about a belief, in light of new evidence that has been generated, in this case during a clinical trial. Over time, as evidence accumulates, a series of Bayesian updates leads a statistician towards hypotheses with greater credence, and towards the truth about a state of affairs.

After a proof of concept trial, for example, when a sponsor must decide whether or not to continue to a Phase 2b trial, the evidence generated by the proof of concept can serve to update beliefs about the new therapy’s probability of success, which in turn informs the Go/No-Go decision about whether to continue to Phase 2b. After Phase 2b, evidence collected during the trial is then used to inform a belief revision about probability of success, which informs the Go/No-Go decision to proceed to Phase 3. After each phase of the trial, the uncertainty around probability of success will decrease, making the decision to engage in an NDA submission more clear.

Now imagine a parallel set of decision-criteria, where instead of looking solely at probability of success, the related costs at each decision point are also built into the Go/No-Go rules that determine whether or not to proceed with a trial. The updating of probability of success will certainly contribute to estimates of ENPV and related returns; so for example, if the results of a proof of concept trial are not as strong as expected, the ENPV can be updated for the decision to go into Phase 2b.

At this point though, there comes the following opportunity: When we say the ENPV is updated, this is not merely a reflection of the associated returns. We can also post proof-of-concept, use the results to determine how sample size and trial length must be updated to maintain a certain ENPV. A range of variables can then be used to determine whether or not to proceed.

This requires though, a mapping of the potential clinical development journey at the outset of the drug development program.

Click the button to download the award-winning book and read the paper by Nitin Patel and Yannis Jemiai.

Access Paper

Reference:

[1] Bayesian Methods in Pharmaceutical Research (link in the button above)

 

About the Author of Blog: 

Untitled_self

Dr. Esha Senchaudhuri is a research and communications specialist, committed to helping scholars and scientists translate their research findings to public and private sector executives. At Cytel Esha leads content strategy and content production across the company's five business units. She received a doctorate from the London School of Economics in philosophy, and is a former early-career policy fellow of the American Academy of Arts and Sciences. She has taught medical ethics at the Harvard School of Public Health (TH Chan School), and sits on the Steering Committee of the Society for Women in Philosophy's Eastern Division, which is responsible for awarding the Distinguished Woman in Philosophy Award.