Looking Forward in the Feasibility/AI Space


In the fourth and final part of this video interview with ACT editor Andy Studna, Rohit Nambisan, CEO & founder of Lokavant looks into the future of feasibility studies, the integration of AI, and how they are driving more personalized approaches.

ACT: What will the feasibility/artificial intelligence (AI) space in clinical trials look like in 5 years? What excites you the most about the future?

Nambisan: I'll answer the same way in response to both questions in some senses because we are moving into a space that is much more personalized, much more precision oriented with medicine. And that's really exciting to me in a lot of ways. I actually cut my teeth in industry working in personalized medicine and diagnostics, stratifying patient population based on epigenetics, and now moving to this space, and primarily that was focused almost mostly on oncology. But now we're seeing precision immunology, we're starting to see that the rudiments of precision neuroscience as well, we're starting to see this take hold. And I think that is essentially the definition in my mind to patient centricity because we're actually meeting patients where they are, we're understanding what makes a specific group of patients or a specific patient, for that sense, unique, and that disease state unique and trying to address that.

So that's really exciting to me, of course, at the same time, given some of my responses in our discussion so far, that creates a lot of challenges, an incredible amount of challenges of being able to bring new therapies to market in an expedited fashion, because almost all indications now, all diseases that we're focused on under development are acting like they're rare, right? And so I think, in this sense, where we are going with this is, we need to not just lean on legacy processes in the past, we have to have a general purpose framework of data collection, ingestion, analysis, all in a turn key manner that allows us to be as unbiased as possible with our data intake, so we can provide as unbiased responses out on a specific disease state, right? And that may mean for example, you may have to work across the aisle with some of the disease advocacy groups and bring together those patients and they opt in some of their data that you can leverage in your models to understand where there may be opportunity in the space and how to best develop a new therapeutic, how to best actually administer a trial. And I think there are some inherent challenges with that. But what's the most exciting about that is we are actually able to customize medicine to meet patients where they are, something that we haven't typically been able to do in the past. So I think I think that's my response to that question, looking forward to the future in relation to how AI can impact in that space for feasibility. But of course, there are so many use cases, post the planning and feasibility stage that AI can make great strides to improve clinical trial progress.

Related Videos
Related Content
© 2024 MJH Life Sciences

All rights reserved.