This is Bloomberg Business Week with Carol Masser and Jason Kelly on Bloomberg Radio. This is a really interesting discussion we're about to have and it actually harkens back and thanks to Carol Masser for pointing this out on Twitter earlier to a conversation. We actually had it in j I t earlier this year when we were still out about out and about in the world. It was a really live event. Yeah, they're in Newark. We were talking about the concept of digital twins. What is that, you ask,
Let's get into it. Charles Fisher is founder and CEO of Unlearned AI. He joins us on the phone from San Francisco. Dr Fisher, thank you so much for joining us. Thank you for having me. All Right, So this is exciting in part because we are all now many experts, or at least we consider ourselves such on drug development. You know, we talked with the CEO of Teva Pharmaceuticals here on this program earlier and really got into a lot of the issues here. How does artificial intelligence play
into this? How might it help us in an age where we're all really interested in accelerating development? Here? Yeah, well, I think there are a few different ways, starting all the way from the beginning of the cycle to saying how can we discover new compounds that might be effective therapies, all the way to the end of the process, and saying how can we leverage all of the data that we have from electronic health records to make more efficient
clinical trials that can get drugs to patients faster. Well, okay, so what's interesting is, and we're hearing more and more about this, right, We've heard various time frames and what it will take to develop um a new vaccine, and the latest have been anywhere from nine months maybe the most optimistic too, maybe a couple of years. So tell us, you know, you shared with us some some some wisdom about when you normally develop a new medicine, it's between
ten and fifteen years. How can digital cloning help skip through this vaccine creation process faster and also ensure that it's safe. Yeah, I think the biggest part of the problem in terms of the time when it takes to talk about how long will it take us to get new treatments or new vaccines, whether that be for for COVID nineteen or any disease, is the amount of time it takes for us to tell if those are safe
and effective. So you know, one of the sort of bad parts about drug development is that actually about nine out of ten drugs that we try in clinical trials end up failing. So most of the time our guesses end up not working well. So it's what we'd like to be able to do is to speed that up, uh and in a variety of ways by postentially leveraging uh So, what we call these these digital patients is is leveraging data from electronic health records to make trials faster. Alright,
so tell us how it works. Sure, So, basically, when a patient enrolls in the trial, we create a digital copy of that patient that tells us what would happen to that person if they were to receive a placebo, so a dummy treatment, and then at the end of the study, you give that real person the real treatment how it affects them, and then you can compare it to the digital twins prediction for what would have happened if they had received the placebo, and then you can
estimate if that treatment was effective or not. And basically, because you can do this but these predicted placebo responses, you don't need to enroll as many subjects into a clinical trump so you can run a trial with up to half as many half as many subjects, So doing this are we doing this in this? In this you know, search um for a vaccine. I'm not aware of any
trials that are doing this in COVID nineteen right now. UM. I think one of the difficulties there is because it's such a new disease, we need to have a lot of data for, you know, to say we know how this disease will progress if you don't receive a treatment. But since COVID nineteen is new, we really don't have that that those data yet. But lots and lots of data are being collected every day, So the ability to to apply these types of technologies may that may be
something that could be done in the near future. All right, we are all aware, and you're much more aware than we are of the trials and tribulations as it were. When it comes to the regulatory side of this, and a lot of the regulatory framework exists for a reason. We want people to be safe. We want drugs when they get to the market to be as safe as they can possibly be. What is the reaction, what has been the reaction by organizations and institutions like the f
D A two plans like this mhm. The FDA is actually doing a lot of work uh these days to modernized clinical trials really across the board, and so in general they're they're quite supportive of new approaches to bring in these kinds of data to make things more efficient. You really just have to work with them to demonstrate with real evidence that the approach you're taking works well, which is really how it should be anyway, right, um, So,
so I would say that they're quite open to it. Uh. The approaches are also new, so there they have been some I think a handful now of of drugs for targeting different types of cancer where these types of evidence have been have been used. Um. And then you know, our company is applying some of these approaches in some
trials for for all disease. Now wells then talk to us a little bit about you know, maybe it's not something that's applicable as you said to COVID nineteen and the hunt for a vaccine, but there are certainly some diseases, whether it's Alzheimer's and so on, that really have plagued us and trying to figure out some kind of cure or some kind of you know, more significant treatment than we currently have. Talked to us attle bit about those types of ailments that might there might be some promise
using digital clones. Yeah, I think in you know, lots of these diseases, whether they be you know, cancer, or neurologic disease like Alzheimer's, or or rare genetic diseases. UM, the ability to leverage all of the data we have collected on those diseases to make those trials more efficient UM with digital twins is I think going to be very Uh. I think that's going to be the future
of how trials are run. It also, you know, one of the sort of side effects of COVID nineteen that since we're all sheltering in place right now, no one's participating in clinical trial right so clinical trials for all of these other diseases, for Alzheimers, for cancer, they're all
disruptive right now. And so figuring out ways to run those trials with fewer patients or where so that patients don't have to maybe go into the hospital by applying new technologies like like digital twins will really help to keep medical research going so that it's not all set back because we aren't able to participate because of COVID Night Team. All right, well, really interesting, interested to see
where this goes from. Here are thanks to Charles Fisher, founders CEO of Unlearned AI, joining us on the phone from San Francisco and the idea of digital twins. It is cool, very cool. It makes sense, yes, and we need to do more on it because I do think this is going to be a big way for the medical arena and their way forward to in terms of tackling a lot of ailments.