get healthing in your inbox with the morning checkup and weekender newsletter!

clinical trials

using ai to change the landscape of clinical trials in canada: reduced costs, stronger data and global leadership

establishing canada as a global leader for ai in clinical trials could benefit canadians and the world at large.

by angelica bottaro

published nov 25, 2024

last updated dec 02, 2024

6 minute read

join the conversation

6 minute read

join the conversation

ai could also revolutionize the digital approach to clinical trials by improving the data extracted. based on recognizable patterns, ai could better track if a drug is doing well and where it could potentially go wrong. getty images

artificial intelligence isn’t new. in fact, the invention of deep-learning-like algorithms dates as far back as the mid-1960s, and in healthcare, ai applications were implemented as early as the 1970s. of course, the digital limitations hindered it from taking off. with the digital advances of today, ai is no longer a technology waiting to get the computing system it needs to truly thrive. it is in the here and now, and many in the clinical trial space are utilizing it to advance how trials are conducted, from providing better access to patient participants to improving clinical trial success rates.

alison mitro, head of clinical trial solutions at altis labs in toronto, on, believes ai can help address one of the biggest problems in clinical trials: late-stage clinical trial failures.

“we believe that one of the biggest impacts ai can have is by helping study sponsors reduce the risk of late-stage failures,” she said. “you know, 40 to 50 per cent of drugs fail in clinical trials due to a lack of efficacy, and that’s one thing we want to help fix.”

that’s not ai’s only application in clinical trials, though. it can also automate costly processes to save money, such as paperwork, imaging analysis, and data collection.

dr. fahad razak, an internal medicine physician at st. michael’s hospital in toronto and canada research chair in healthcare data and analytics at the university of toronto, sees ai as an additional approach to clinical trials that can foster better patient care – if specific questions can be addressed first.

“how do you use health ai in a way that is safe? how do you do that in a way that is unbiased? how do you do that in a way that’s really defensible in terms of the benefit for you as a patient?” he said. “that’s where randomized trials are critical. we must test these technologies and hold them up to the same standard we use for other parts of modern medicine – proven benefit through randomize trails.”

using ai to advance clinical trial processes and success

clinical trials are costly because of all that goes into putting them together. from start-up fees for administration and site costs to patient participation and site monitoring, it’s not cheap to test a new drug for the market. grants from study sponsors typically pay these costs, along with government funding, charities, private investors, and research institutes.

the issue with costs is that, in many cases, drugs that could have the potential to make a real positive impact in the world may never get to see the light of day if they don’t receive enough funding. while ai cannot make money appear, it can lower the costs significantly for various aspects of clinical trials, making it more feasible for more of these drugs to get their chance to prove their place in the country’s medicine cabinet.

“everything costs money, and really, the challenge here is, where do you make that decision,” said dr. razak. “how do you put money towards this and not that? i think the role of scientists, people like me, and i’m one of many across the country who are making the same argument, is that this kind of innovation – harnessing the potential of ai to make the conduct of trials more efficient, using ai to select the therapeutics that are most likely to be found beneficial in trials, and using trials to test new health ai technologies that can be deployed at the bedside – is of significant value to canadians.”

“we have all of this data that’s collected in clinical trials beyond just imaging … and ai can really help in finding patterns in the data and extracting relevant interpretations that can help us predict if a drug will be effective, and can even lead to net new scientific discoveries,” said mitro. “just things that we were never able to do before without implementing ai.”

the time and cost to successfully bring a new drug to market could also be mitigated when ai is thrown into the mix. because clinical trials can take years, sometimes upwards of a decade to reach a phase iii trial where the drug’s efficacy is being determined, if something doesn’t pan out, that is a lot of time and money down the drain.

however, ai can help predict these results much earlier in phase i or ii, helping to avoid unnecessary work on the ineffective medications that can occur when using current efficacy predictors available today.

“the way that we predict if drugs are effective earlier on in the pipeline is through what are called surrogate endpoints, and they’re not always reliable predictors of efficacy,” said mitro. “there are many instances of notable trials where surrogate endpoints have underestimated or overestimated the actual efficacy of the drug.”

mitro goes on to say that there are issues with both overestimating and underestimating drug efficacy. if drug efficacy is overestimated by surrogate endpoints, it may eventually be pulled off the market when it inevitably fails to demonstrate effectiveness, and if it’s underestimated, it may never reach the hands of those who need it – both of which, she says, are “expensive decisions.”

ai can utilize data and pattern prediction to reduce these over- and underestimations. it could even go back in time and find out if other underestimated drugs were overlooked far too soon.

“you could go back today, and you could apply our ai models on a drug or on a clinical trial that failed, and you could potentially see, was this actually an effective drug? if it was an effective drug that the study sponsor just decided not to move forward with because, according to their other information, it didn’t seem effective, maybe that’s an opportunity to pick it back up,” said mitro.

vying to make canada a leader in health ai applications

from a global perspective, canada is one of the best places in the world to conduct clinical trials using ai because of its incredibly diverse population. clinical trials conducted on various groups of people will always provide more accurate and generalizable results that can be applied to more than just one subset of individuals.

dr. razak believes that if canada can establish its infrastructure for ai in clinical trials, it won’t just benefit those on home soil but the global health landscape overall.

“if you train an algorithm and develop it here in canada, it will almost always be intrinsically a better algorithm than if you train it in a more homogenous population like, for example, denmark. it means that the science and innovation of training and doing that work here in canada would have more global relevance, more likely to be beneficial if exported to places like china or india,” he said. “in other words, if you develop something here, you’ll more likely be able to take it and apply it in denmark, apply it in india, apply it in china, than vice versa.”

another significant advantage canada has over other countries is universal healthcare. canadians are granted access to healthcare with or without insurance, allowing clinical trials to extract data from a complete population, as opposed to other countries where only some with health insurance can participate.

“if you look at those characteristics together, best ai scientists, best trial scientists, most diverse population, and a single-payer system, the argument that i would make is that there isn’t a country anywhere in the world that has a better combination of those characteristics, and that’s what is the real opportunity here for global leadership,” said dr. razak.

mitro and dr. razak both hope that the understanding of ai technology and its benefits become far-reaching in canada, allowing for the infrastructure to be developed and more companies to implement the technology to make for better clinical trials and, in turn, better access to life-changing drugs for canadians.

this discussion was recently presented at clinical trials ontario’s cto conference on november 6 and 7, 2024.

angelica bottaro

angelica bottaro is the lead editor at healthing.ca, and has been content writing for over a decade, specializing in all things health. her goal as a health journalist is to bring awareness and information to people that they can use as an additional tool toward their own optimal health.

using ai to change the landscape of clinical trials in canada: reduced costs, stronger data and global leadership

establishing canada as a global leader for ai in clinical trials could benefit canadians and the world at large.

how ai is helping detect types of endometrial cancer

signs point to glp-1 drug innovation beyond wegovy and ozempic

using ai to advance clinical trial processes and success

vying to make canada a leader in health ai applications

advertisement

using ai to change the landscape of clinical trials in canada: reduced costs, stronger data and global leadership

establishing canada as a global leader for ai in clinical trials could benefit canadians and the world at large.

related stories

how ai is helping detect types of endometrial cancer

signs point to glp-1 drug innovation beyond wegovy and ozempic

the future of clinical trials: bringing hybrid and decentralized methods to all canadians

advertisement

using ai to advance clinical trial processes and success

advertisement

advertisement

advertisement

vying to make canada a leader in health ai applications

advertisement

share story