van der Schaar Lab
Adaptive clinical trials

Next-generation clinical trials

Please note: this page is a work in progress. Please treat it as a “stub” containing only basic information, rather than a full-fledged summary of our lab’s vision for ML for next-generation clinical trials and our research to date.

This page is co-authored by Nick Maxfield and maintained by its author Mihaela van der Schaar and Andreas Bedorf

Randomized controlled trials: the current gold standard

Randomised controlled trials (RCTs) are the gold standard for evaluating new treatments. Phase I trials are used to evaluate safety and dosage, Phase II trials are used to provide some evidence of efficacy, and Phase III trials are used to evaluate the effectiveness of the new treatment in comparison to the current one.

A typical question that a Phase III RCT is intended to answer is “In population W is drug A at daily dose X more efficacious in improving Z by Q amount over a period of time T than drug B at daily dose Y?”

Traditional free-standing parallel-group RCTs may, however, not always be the most practical option for evaluating certain treatments, since they are costly and time-consuming to implement, and they do not always recruit representative patients. This last point makes external validity an issue for RCTs, as findings sometimes fail to generalise beyond the study population. This may be due to the narrow inclusion criteria in RCTs compared with the real world, where historically, population restrictions with respect to disease severity, co-morbidities, elderly patients, and ethnic minorities can be under-represented. By contrast, when drugs approved by regulators such as the U.S. FDA after the clinical trials stage, they start being administered to a much larger and varied population of patients.

Although there is increasing awareness of such issues and global regulatory authorities are encouraging wider inclusion criteria in clinical trials, it remains an issue that is unlikely to be solved by RCTs and associated integrated and model-based analyses alone.

Next-Generation Clinical Trials

As we can see, clinical trials are complex projects involving multiple data sources, design choices and analytical methods. Some of these aspects are detailed in other research pillars: individualised treatment effect, clustering, survival analysis, etc. In what follows, we focus on next-generation trial designs.

(The figure above was designed together with our collaborator Dr Eoin McKinney)

Next-generation clinical trials are gaining increasing attention as an alternative to RCTs, since they utilise accumulated results to dynamically modify the future trajectory of a trial for better efficiency and ethics, while preserving the integrity and validity of the study. Instead of randomising patients to fixed treatment arms in fixed proportions throughout the trial, adaptive designs use interim analyses to reconfigure patient recruitment criteria, assignment rules and treatment options. More specifically, aspects of the trial that may be modified adaptively include dosage, basis of patient selection, sample size, drug being trialed, and “cocktail” mix.

Studies such as the phase I trial in Acute Myeloid Leukaemia in (published in 2013) and Cancer Research UK study CR0720-11 (published in 2012) have suggested that even some simple forms of adaptive design lead to better usage of resources and require fewer participants. These promising results have spawned the interest in developing adaptive clinical trial methodologies in recent years, which is of great importance because running an actual clinical trial on human subjects is expensive and ethically sensitive. A well-designed trial methodology with thorough theoretical and simulated investigation is widely acknowledged as a crucial first step.

The potential of machine learning for clinical trials

In recent years, there has been a growing trend to leverage ML approaches, especially tools from reinforcement learning (RL) such as Markov decision processes and multi-armed bandits, to improve and expedite clinical trial designs.

The framework of multi-armed bandits is particularly useful in the context of clinical trials because it fits easily and well and because there is an enormous literature on multi-armed bandits. All of this work is designed to address the exploration-exploitation trade-off, which can be interpreted as a trade-off between clinical research (to discover knowledge about treatments) and clinical practice (to benefit the participants) in clinical trials, by assigning new patients to treatment arms on the basis of information from previous patients.

These methods have been shown to speed up learning and identify subgroups for which different treatments might be employed and different treatment responses might be expected. Because these methods are automatic, they are easy to implement (when trial logistics permit). Moreover, the Bayesian nature of many of these algorithms permits smooth incorporation of previously discussed observational evidence as prior information.

Learning in adaptive clinical trials still faces several unique challenges that have not been well addressed, which may have contributed to their lack of adoption in actual clinical trials. In particular, the safety constraints resulting from ethical and societal considerations have been insufficiently researched.

Furthermore, constructing actual trials using adaptive methods powered by machine learning will require convincing both those who conduct the trials (e.g. pharmaceutical companies) and those who assess the results of the trials (e.g. regulatory agencies) that the substantial improvements that are possible justify the changes to the way trials are presently conducted.

Our lab’s publications related to next-generation clinical trials

Next-generation clinical trial design and implementation is one of our lab’s key research priorities, and our lab has developed an array of novel approaches. Much of this work extends on a solid foundation of roughly 10 years of expertise with multi-armed bandits (related publications can be found here).

As mentioned previously, this page is a work in progress and only presents a basic and partial view of our lab’s vision and research to date. A few of our existing publications are provided below, but our work is ongoing. If you would like to track our publications related to next-generation clinical trials on an ongoing basis, you can do so using this URL.

SDF-Bayes: Cautious Optimism in Safe Dose-Finding Clinical Trials with Drug Combinations and Heterogeneous Patient Groups

Hyun-Suk Lee, Cong Shen, William R. Zame, Jang-Won Lee, Mihaela van der Schaar



SyncTwin: Treatment Effect Estimation with
Longitudinal Outcomes

Zhaozhi Qian, Yao Zhang, Ioana Bica, Angela Mary Wood, Mihaela van der Schaar

NeurIPS 2021


Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression

Zhaozhi Qian, William R. Zame, Lucas M. Fleuren, Paul Elbers, Mihaela van der Schaar

NeurIPS 2021


Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification

Hyun-Suk Lee, Yao Zhang, William R. Zame, Cong Shen, Jang-Won Lee, Mihaela van der Schaar

NeurIPS 2020


Contextual Constrained Learning for Dose-Finding Clinical Trials

Hyun-Suk Lee, Cong Shen, James Jordon, Mihaela van der Schaar



Sequential Patient Recruitment and Allocation for Adaptive Clinical Trials

Onur Atan, William R. Zame, Mihaela van der Schaar



Machine learning for clinical trials in the era of COVID-19

William R. Zame, Ioana Bica, Cong Shen, Alicia Curth, Hyun-Suk Lee, Stuart Bailey, James Weatherall, David Wright, Frank Bretz, Mihaela van der Schaar

Statistics in Biopharmaceutical Research, 2020


Learning for Dose Allocation in Adaptive Clinical Trials with Safety Constraints

Cong Shen, Zhiyang Wang, Sofia Villar, Mihaela van der Schaar

ICML 2020


Learn more and get involved

Our research related to adaptive clinical trials is closely linked to the problem of individualized treatment effect (ITE) inference—another of the lab’s core areas of focus. To learn more about our work on ITE inference, visit our dedicated research pillar page.

We would encourage you to stay abreast of ongoing developments in this and other areas of machine learning for healthcare by signing up to take part in one of our two streams of online engagement sessions.

If you are a practicing clinician, please sign up for Revolutionizing Healthcare, which is a forum for members of the clinical community to share ideas and discuss topics that will define the future of machine learning in healthcare (no machine learning experience required).

If you are a machine learning student, you can join our Inspiration Exchange engagement sessions, in which we introduce and discuss new ideas and development of new methods, approaches, and techniques in machine learning for healthcare.

A full list of our papers on this and related topics can be found here.