Decentralized Trials That Scale Globally Without Compliance Risks - with Emma Vitalini of Amgen

**Daniel Faggella** (0:16)
Today's guest is Emma Vitalini, head of Global Digital Health Technology Innovation at Amgen. Emma joins me on today's show to explore how AI and decentralized trial technologies are reshaping patient recruitment, screening, and global trial accessibility across highly regulated healthcare environments. Our conversation also examines practical workflow shifts, from using AI to surface unstructured genomic and clinical data to API based hypothesis testing that reduces data movement and modular consent and compliance platforms that help sponsors scale trials faster while maintaining regulatory trust and patient transparency. Just a quick note for our audience that the views expressed by Emma Vitalini on today's program do not reflect that of Amgen or its leadership. For our solutions partners, position your brand alongside the Fortune 500 leaders defining the enterprise AI roadmap. For the opportunity to showcase your solutions to the executives currently funding and scaling global initiatives, partner with Emerge to reach the decision-makers holding the strategic mandate. Secure your partnership at go.emerge.com/partner. That's go.emerge.com/p-a-r-t-m-e-r. Now our conversation with Emma.
Emma, welcome to the show, so happy to have you with us today.

**Emma Vitalini** (1:39)
Thank you so much, Marilyn, happy to join you.

**Daniel Faggella** (1:41)
Emma, when we look at clinical trials, one of the biggest ongoing challenges is enrollment. Up to 80% of trials don't hit their patient recruitment targets on schedule, which can cause significant delays in bringing new treatments to market, and ultimately limits patient access to potentially life-changing therapies. Traditional recruitment methods often rely on heavily on-site networks and manual outreach, which can miss the right patients, especially those in diverse or underserved populations. But now, with AI-driven approaches, combined with decentralized trial technologies, we're starting to see scalable solutions that identify eligible patients more quickly, improve outreach efforts, and help sponsors meet enrollment goals faster and more efficiently. Recruitment remains a critical barrier for many trials. How, Emma, is AI improving patient identification and outreach, particularly for speeding enrollment and boosting diversity?

**Emma Vitalini** (2:33)
Yeah, it's a great question. And I think there are multiple ways to look at it. AI is certainly enabling us to truly understand the mechanism of action of our molecules, our medicines, much better, which means that we can more appropriately identify the exact patients. That coupled with the decreasing costs of genomic sequencing, proteomics, that means that we can look more deeper into the patients in front of us. And again, truly identify, leveraging AI, those trends that if we had to analyze all of this ourselves, it would take a lot longer. So truly identifying this within patient populations becomes easier with AI. I think where we still are looking to advance is that for many patients in their records, if they have got or if they have gone through genomic sequencing, that data at the moment is still within more note fields. They're not necessarily within a specific structured field. So again, AI allows that to surface more readily and consistently, whereas in the past, potentially, it was harder because you would have to go through all of the written notes and determine if that information existed. So from an efficiency perspective in existing sites, in existing ways of working, it allows us to do that. But coupled on to that, there are many health care providers and systems, particularly in the US, also in the Middle East, India, where they're starting to look at leveraging that generally across their hospital systems and then they're able to identify patients more rapidly and readily.
So this means that it can happen at scale. So if you have an opportunity to potentially partner with some of those systems, then you can certainly access or identify that patient information faster. I think this allows us that kind of ability to accelerate patient screening potentially, and then reduce that time. And I think you mentioned also that opportunity with decentralized or digital studies equally helps to accelerate this on a different level. So patients, if they are able to be part of that study, regardless of where they're located, I think this is an exciting opportunity. There are studies that have attempted at large scale to do this, and this is not a new concept. I think what we've seen in the past, the challenges have been that you then still need to associate a patient with a site. There still needs to be a physician that is going to sign off on the requirement for blood work. So even when you maybe enable something to be decentralized, and a patient based anywhere can join, they may still need to have blood collected. They still may need samples, and maybe that can be done with a primary healthcare physician locally. But if in the case that it can't, the challenge has always been sites that will be willing to take a patient that's not necessarily within their catchment area or their area. So there's always been limitations on how this has been successfully implemented. But I think now, again, AI can help to drive this and make it a lot easier. There are numerous at home self-sampling kits that are available now. So we can also do a lot more.