What's Up with Tech?
Tech Transformation with Evan Kirstel: A podcast exploring the latest trends and innovations in the tech industry, and how businesses can leverage them for growth, diving into the world of B2B, discussing strategies, trends, and sharing insights from industry leaders!
With over three decades in telecom and IT, I've mastered the art of transforming social media into a dynamic platform for audience engagement, community building, and establishing thought leadership. My approach isn't about personal brand promotion but about delivering educational and informative content to cultivate a sustainable, long-term business presence. I am the leading content creator in areas like Enterprise AI, UCaaS, CPaaS, CCaaS, Cloud, Telecom, 5G and more!
What's Up with Tech?
AI-Powered Patient Replicas: The Future of Drug Development
Interested in being a guest? Email us at admin@evankirstel.com
The race to develop life-saving medications has always been constrained by time, cost, and the challenge of gathering enough patient data. But what if we could create AI-powered replicas of trial participants that accurately predict how they would respond to treatment?
Chief Executive Officer Steve Herne from Unlearn.AI joins us to reveal how digital twins technology is revolutionizing clinical trials by creating virtual patient forecasts that run alongside actual participants. This breakthrough approach enables researchers to compare observed versus predicted outcomes, dramatically reducing statistical noise and allowing true treatment signals to emerge more clearly. The results are nothing short of remarkable—Alzheimer's trials with 33% smaller sample sizes while boosting statistical power by 10%, Parkinson's disease studies completed nearly 10 months faster than traditional methods, and rare disease research accelerated by months rather than years.
We dive deep into how regulatory bodies like the FDA are adapting to this AI revolution, with new frameworks ensuring these approaches meet rigorous scientific standards. Steve shares fascinating insights into how pharmaceutical companies are transitioning from reluctance to enthusiasm, increasingly reaching out to Unlearnat the earliest stages of protocol development. The vision? Making digital twins standard practice across all therapeutic areas, accelerating the "miracle of medicine" to patients worldwide.
Whether you're a healthcare professional, technology enthusiast, or simply curious about how AI is transforming medicine, this episode offers a fascinating glimpse into a future where digital innovation and clinical research converge to create better outcomes for patients. Subscribe now and join the conversation about technology's profound impact on healthcare's most challenging problems.
More at https://linktr.ee/EvanKirstel
Hey everybody, fascinating discussion and important discussion today, as we talk about AI-powered replicas, or digital twins, that are revolutionizing how we run clinical trials, and joined by a true insider and thought leader in the space from unlearnai Steve, how are you?
Speaker 2:I'm doing very well. Thank you for having me today.
Speaker 1:Well, thanks for being here. I'm doing very well. Thank you for having me today. Well, thanks for being here. Yes, Evan and Irma here from Avira Health Really fascinated. Maybe we'll start from the beginning. What's your background and how did you land at unlearnai?
Speaker 2:Sure, no, absolutely. So I'm coming up around 30 years in the clinical trial space. I started my life out of academia, getting into clinical trials on the operations side and then spent a lot of my career in the commercial marketing and then for the last 10-15 years I've been spending more of my time on the clinical technology side in supporting clinical trials and the kind of advantages that technology can really do to shape our clinical trials going forward. And that really fast forwards to my journey over the last year here at Unlearn AI, where technology AI meets clinical trials. So for me it's an exciting hopefully near end of my career where I can really take everything I've learned over the last three decades in clinical trials and see if we can really start to make a difference using artificial intelligence and technology out there in the market.
Speaker 3:Fantastic. So today we will be diving into the world of digital twins and for our listeners, who may not be familiar or new to the term, what exactly is a digital twin, and particularly in the context of medicine?
Speaker 2:is a digital twin and particularly in the context of medicine Sure, no, absolutely, to make it nice and simple and very easy for the listeners, a digital twin is basically an AI-generated forecast of a patient's clinical outcomes, predominantly in our world, obviously in a clinical trial. So that really helps us forecast how that patient will progress with their disease along the life cycle of the clinical trial. So we're spending a lot of technology behind the scenes, a lot of algorithmic activity to really forecast that longitudinal activity of that individual. So you go into that clinical trial and your twin comes in with you. So we create that digital twin that runs along with you throughout the clinical trial.
Speaker 1:Amazing, and this has moved from the sort of lab into the real world. How are you actually applying these digital twins at Unlearn to medical research and what are the different use cases?
Speaker 2:Sure, and what are the different use cases? Sure, so again, I think most digital twins we're really using to enable us to compare observed outcomes versus predicted outcomes. So in clinical terms, that lets us really look at the variability, helping to reduce the noise so that we can really see true signals in the data by lowering that variance. That allows us to really start to really see true magnified signals that people can then make much more effective what we call, in clinical trial language, go-no-go decisions. So people want to shorten the length of a clinical trial as quickly but as effectively as they can.
Speaker 2:So the quicker we get to those go-no-go decisions ie, is the therapeutic working well? Are we seeing the response we like to those go-no-go decisions? Ie, is the therapeutic working well? Are we seeing the response we like to see, then the happier everybody is. And we do that obviously by reducing sample size, which basically means we're bringing the number of patients on the trial or the number of volunteers that are in the clinical trial. We bring that down because we can obviously run a digital trial sorry, a digital twin along with a patient at the same time. So smaller sample sizes equals faster enrollment and therefore we're boosting what we call the power of the study, reducing the error and making that trial much more effective and much quicker.
Speaker 3:Wow, wow, that's right. There are already great benefits of using digital twins compared to just the traditional clinical trial methods. Can you elaborate a little bit more? Do you have advantage in terms of geographical area you can cover or any other benefits to using this approach versus traditional clinical trials?
Speaker 2:So I think again, main main benefit again just for everybody listening is reducing. You know endpoints with fewer patients and you know obviously shorter durations. That is definitely equals, you know, digital twin period. But from a geography perspective, across the board we're pretty agnostic in both geography and in therapeutic area. We're trying to, as we work with companies and customers right at the beginning of the clinical trial development program, in analyzing the protocols and understanding different ways to work with them, we're obviously trying to maximize how they can run that trial as effective as possible.
Speaker 2:So we have lots and lots and lots of data out there that we obviously learn these models through so that we can really help predict the future for these trials. So in particular areas we might say go into this geography or look at this type of population. We also might say examine this endpoint along with this endpoint because you will see maximum benefit that we've seen maybe as we've supported other trials or done other work with other customers. So again, it's case by case on each situation, but the main main thrust obviously we're reducing sample size and we're decreasing clinical timelines. That's amazing.
Speaker 1:And we all know the cost and time associated with drug development. It's hard to believe drugs get to market, given the challenges. Can you walk us through how they help reduce time and cost, and can you quantify that at all?
Speaker 2:Sure, so we've spent a lot of time in the evolution of Unlearn in what we call the neurodegenerative disease space, or sometimes known as the central nervous system, cns. So evolution over the last seven, eight years in the company we've spent a lot of time predominantly in Alzheimer's disease. So again, this is public and on our website and publicly available data, so I'm not sharing anything too confidential today. But as we managed an Alzheimer's drug with a customer, we managed to reduce the sample size of up to 33% in that particular trial and we boosted the power over 10%. So we went from just under 80% to over 90% in power and brought the trial in at least four months earlier than the original plan date. So that was a phase two trial.
Speaker 2:These are slightly smaller than the larger phase threes but seeing that type of activity on a phase two is very exciting. To obviously get us into that no-go decision for phase three and some of the rare diseases or some of the more rare CNS profiles like ALS, we did see a recent trial that we ran with one of our customers where we reduced our sample size by 18% and cut those timelines by around three to four months. And the last one that we just actually not long ago finished actually was in Parkinson's disease and again we actually increased our sample size there by about 33% and increased the power by about 65%, cutting about nine, 10 months off the entire journey on that one too. So again, obviously the larger trials that we get into, the larger cuts that we can make in time and also, hopefully, the stronger boost we can make in power. But some of these things for phase two are very, very important for customers and very, very lucrative for them to move forward.
Speaker 1:Exciting.
Speaker 3:These are great advancements, and also from regulators like the FDA, specifically to your approach and maybe kind of in general to the growing use of AI in medicine and clinical trials.
Speaker 2:Sure, and I think it's evolving for all of us and every day, you know, sometimes tongue in cheek every day we see, is a school day in the world of clinical trials, meeting AI. I think from the customer side, very much engagement. Most large pharma companies at the moment are exploring artificial intelligence in some shape or form to really help decrease these timelines. Many, many of them are under big, big pressure from their stakeholders to make sure that they can bring some of these drugs to market way quicker than original plans and methodologies of trying to do that obviously are engaging AI and tech companies to try and help catalyze that. At the same time, they want to make sure that the companies that they choose to partner with are very credible and that they have what we would call in our industry, validated solutions. And that's where it kind of links into your question with regards to the kind of FDA and EMA some of the large governing bodies worldwide out there that support clinical trial development. They have to make sure that we're doing things proper and correct.
Speaker 2:So we went through, obviously, creditations with the EMA and FDA to get alignment and agreement that we're very valid in what we do and very credible that we're very valid in what we do and very credible.
Speaker 2:And actually pretty recently the FDA has published a seven-step framework for AI in drug development, setting very clear expectations on how AI companies should be working with pharma companies to make sure that they provide the right things.
Speaker 2:So it's a structured approach that really emphasizes on transparency, risk assessment and continuous evaluation and integration of AI into the drug development spectrum. And if that gets a tick box or gets a green light, then you know we all go off to the races and apply AI in that clinical trial. So we've produced a few white papers and some case studies recently on how you know we're interacting with FDA also how we're managing to help validate and be credible through that process. And we go to a lot of meetings with our customers at the FDA so that when we're having those intense discussions about the clinical trial impacts of AI, we're their hand on, we're right beside the customer having those discussions. So a lot of things are changing and we will continue to see change. If we look back in the mirror, over the last year, four years, we've really came on leaps and bounds and I'm sure the next year four years in this space are going to continue to really accelerate dramatically.
Speaker 1:Yeah, exciting times. I mean zooming out big picture. You do have a lot of different stakeholders, obviously clinical development ecosystem, the researchers that you mentioned, payers, patients. How do you think about that balancing act with all of those different interested and involved parties?
Speaker 2:No, absolutely, and I think the luxurious position we have here at Unlearn is we do get a chance to interact with most of that ecosystem in some shape or form. If I take it big picture and then come to probably a day in the life of Unlearn, obviously in big picture I spend as the CEO of Unlearn, with fellow CEOs or fellow C-suite members of the team on the pharma side in looking at how we can reduce that risk and cost and how we can help with our trial timelines so that ultimately, those stakeholders are getting a chance to really accelerate key decisions with confidence. At the same time, we are obviously supporting that regulatory world that I just spoke about. So we're interfacing with those regulatory teams to make sure that if there's areas of their business that we need to fine tune or get back on track for with regards to how AI is being interpreted with the regulators, we're supporting that with the team across the board. And that sometimes encapsulates many, many projects that are in flight time.
Speaker 2:But probably in a day in the life of Unlearn we spend a lot of our time with what we call our clinical development team or the research and development team, who are really, you know, looking at the intimacy of that protocol, wondering where, how patients are performing, how things are just running in the health and just the life cycle of that study in its entirety.
Speaker 2:So as we transgress through that, we do peak and trough with different of the more specialist roles in clinical development and in this occasion we spend a lot of time with what we call biostatisticians, so people that are looking at the statistical outcomes and the statistical evidence that's prevalent in that clinical trial, because data is how ultimately we are making decisions on how things go forward. So we have to make sure that that data is well addressed and obviously analyzed. So we spend an intimate amount of time with the data management and biostats teams and nine times out of ten it's been seen as an extension to their team, but sometimes we run solo on certain projects and then bring that back in-house. So a lot of ecosystem we touch which makes the job very, very exciting and at different parts of the clinical trial process obviously many, many others are involved.
Speaker 3:Wow thanks for that great overview of kind of behind the scenes. How much is involved in getting all this data to provide useful insights and actionable insights, expected or exciting use cases that you had found in applying Digital Twin's approach to real-world drug development or clinical trials?
Speaker 2:Again, I think it's a little cliched, but probably the most exciting thing is the actual adoption curve that we are seeing. So you know, as we look at the beginning of our journey here at Unlearn, you know probably AI might have been seen as that spooky word or you know not sure what that really means and what's happening to my data, what's going to happen to this trial overall and what I've definitely seen, and especially in my own time here at Unlearn the adoption and the understanding. I think the industry is really moving, which is very, very exciting for us. Obviously, we had a much more earlier onsite or early excitement about the adoption of AI in clinical trials. Hence the reason we started the organization and the company.
Speaker 2:But that's not necessarily. You know, the pharmaceutical industry, without sounding terribly derogative, you know are a little bit more of a lagger industry. They like to make sure others have tried and tested and seen before they move in. Sure others have tried and tested and seen before they move in. So I'm very excited to see that we spend a lot of our time in the top 30, 50 pharma surgical companies in the world who are leading drug development. And then, you know, what's even more exciting for me is now that they're picking up the phone and calling us and saying we're just about to start trial X and we know that we need Unlearn with us in this situation because we are really focused in on getting this done properly, excited, but at the same time we're trying to reduce our numbers and we're trying to bring in our timelines and we know that unlearn will be able to help.
Speaker 2:So, having seen that adoption curve, I think is exciting and of course, like most of us who came into the clinical trial business or come from some form of medical training and some description, we're very excited about how we can get that miracle of medicine to the patient as quickly as we can. So most of us every day are getting out of bed to make sure that you know that Alzheimer's patient, that oncology patient, that you know that cardiovascular patient is getting the help and the need that they get. And the quicker we manage to get that medicine to them, the quicker that hopefully we give them a much better life going forward. So again, you know, from a much more evangelical concept or big picture, here too I do think we're making a big difference in patients lives going forward, which definitely keeps us very motivated here on them oh, it's wonderful to hear, um, some would say the drug industry, the pharmaceutical industry is sort of stuck in the Excel spreadsheet era of drug development.
Speaker 1:You're clearly on the cutting edge, the leading edge, but what has to happen to really let AI and data science take the wheel in clinical trials? Beyond working with unlearn, what else does the industry need to do to transform itself?
Speaker 2:So I think actually you know the industry need to do to transform itself. So I think actually you know the industry will transform itself. I've seen the evolution of you know things in the in 10, 15 years ago where we did what we call edc electronic data capture. So we moved from paper to electronic. Everybody thought we were crazy as an industry and everybody was worried about it. And now here we are, 15, 20 years later. I don't really think there's many, if at all any, clinical trials really done on paper out there, unless something very urgent and very quick has to be done. So I think AI will become the next part of that. It will become, hopefully in my kids' generation or in the youth of today going forward as they take clinical trials to the next stage, that AI will just be part of that protocol. We'll be part of that clinical development.
Speaker 2:I think we're just getting through, you know, some of the cycles where we can see a drug move from phase two into phase three, into post-marketing, and where was AI influencing in that? So people can get a feel for the benefit and the excitement of it. But we don't have, you know, hundreds and hundreds of cases of it and we had an industry that likes to see that. You know we there are hundreds and hundreds of cases so that we feel secure about there. So I think you know that adoption curve that I was speaking about being excited, I think overall is going to change.
Speaker 2:We are moving out of excel spreadsheet into much more trusting, you know, algorithmic based activity, um, especially the AI world, and there are many, many ways of technology touching everybody in our life today, but also in the clinical trial world. So we're a small part of that AI ecosystem. You know we've got way back at the beginning as we look at the cataloging of some of these compounds that you think you would like to target. So we call it target profiling and we're using AI at the beginning to help us profile those targets much more sophisticated, much quicker, so that we don't pick a loss leader or we don't pick out of the five drugs, we pick two that you know we had to go back and find the other three. So there's many, many, many steps of clinical development and there's definitely now many, many areas where AI has been very prevalent.
Speaker 1:Incredible.
Speaker 3:Oh, you're giving us already a little bit of a preview. Maybe future, your future focus. So, as we wrap up here, I want to ask you about, kind of like, over the next few years maybe looking forward five years what are um evidence you're going to pursue something new and exciting or are you going to just try to drill down on, on what you've already shown as as very beneficial and, uh, producing huge results? Like what's what's, in the next few years on on your radar?
Speaker 2:so definitely picking up on your last part, in the next few years I'd like to obviously continue to build our you know our profile out there. As you know, an excellent company in you know drug development with the power of ai that can support that going forward. Um, my big, big vision or one of my personal ambitions for unlearn is that we will become exceptionally agnostic to any therapeutic area in any clinical trial out there and basically every single time a clinician goes to start drafting a protocol that when they go to move their tools over in their what do, I must need list. Without question. Unlearn is right at the top of that must need list that we will then just naturally become part of every single clinical protocol out there as we go forward. So we are not at that stage at the moment.
Speaker 2:As I said, we've been journeying very much in the CNS space. We're moving now recently into oncology and into inflammation and into some of the cardiometabolic disorders out there too. So we are definitely taking our statewide approach to that. We're a small company so we have to be careful that we don't overcommit to things we can deliver. But eventually, hopefully, as we grow ourself, as we grow the industry's knowledge and as everybody embraces technology and AI and clinical trials, then Unlearn becomes the center part of that protocol and that will be very exciting for not just the industry but definitely for me personally and the team here on there.
Speaker 1:And for all of us. We are really rooting for your success and the mission and vision is amazing. Godspeed, and onwards and upwards. Thanks for joining and sharing a peek behind the curtain.
Speaker 2:Thank you very much for having me. Thanks again.
Speaker 1:And thanks for listening.
Speaker 3:Thank you everyone for watching and listening and check out our new.
Speaker 1:TV show at techimpacttv now on Bloomberg and Fox Business, and thanks for sharing everyone. Take care. Thanks, Steve.