van der Schaar Lab

CBER OBPV Training Seminar Series

Event details

Mihaela van der Schaar will deliver a talk as part of the CBER OBPV Training Seminar Series.

Title

Can Machine Learning Revolutionize Clinical Trials?

Location and local date/time

This event will take place on May 23 at 17:00 BST.

Talk Abstract

Since their initial use in the 1940s, randomized controlled trials (RCTs) have become the gold-standard supporting the practice of evidence-based medicine. However, the increasing complexity of regulations and protocols means they are both expensive and difficult to run. In addition, restrictive inclusion criteria also mean that half of clinical trials exclude numerous patients they aim to treat. Although novel approaches to clinical trial design have emerged —including various flavors of adaptive designs—conventional RCTs have remained the dominant approach despite their acknowledged flaws. This situation presents a huge opportunity for innovation. Given the scale at which clinical trials are operated, even small improvements to how clinical trials are run could have a tremendous impact on healthcare. 

In this talk, I will argue that machine learning forms a strong foundation to start tackling some of the RCT challenges: it can provide the fundamental tools and techniques that are necessary to precisely formulate what is needed and reason about potential solutions. I will also discuss how some existing machine learning methods can already help improve trials by enabling better ways of harnessing available information to make data-driven decisions that make successful studies more likely. Finally, I will discuss the way forward since current machine learning tools and techniques are not always able to fully address the unique nature of various complex RCT challenges and new solutions are needed. However, I argue that this need presents an exciting opportunity for machine learning to grow further as well, together with the next-generation trials it enables.

The event is finished.

Date

May 23 2024
Expired!

Time

17:00