CRO/Sponsor

Clinical Trial Supply Chain

Decentralized Clinical Trials

Early Phase Development

Investigative Sites

Protocol Design

Risk-Based Monitoring

Study Start-Up

Trial Design

Clinical Operations & Strategy

Diversity Action Plans

Industry Initiatives

Recruitment

Analytics

Electronic Data Capture

Metrics & Benchmarks

Real World Evidence

Data Management

CRAACO

Enrollment

Integrated Research

Patient Participation

Institutional Review Board & Ethics Committee

Regulatory

Artificial Intelligence/Machine Learning

eClinical

mHealth

Technology

News

Academy

Publications

All Publications

E-Books

Media

Editorial Podcasts

Editorial Videos

Peer Exchange

Practice Academy

Conferences

Conference Coverage

Conference Listing

Columns

All Columns

A Closing Thought

Clinical Trial Insights

View from Brussels

View from Washington

Resources

Advertise

Blogs

Events

Front & Center

Partner Perspectives

White Papers

Webcasts

Subscribe

Applied Clinical Trials is the thought leader in pharmaceutical drug development operations and clinical trial design, management, and monitoring.

About

Contact Us

Editorial Contacts

Do Not Sell My Personal Information

Privacy Policy

Terms and Conditions

Applied Clinical Trials Online

LinkedIN

Instagram

Facebook

Youtube

Soundcloud

Threads

Spotlight

DE&I

Topic

1rem

Despite ambitions to streamline regulatory review, FDA’s Elsa platform has been prone to hallucinations, prompting internal scrutiny and questions about AI reliability and governance.

FDA’s Elsa AI Tool Raises Accuracy and Oversight Concerns

A new global report finds that clinical research teams are making progress but still lack the skills and tools needed to keep pace with growing trial complexity and emerging technologies.

 Empowering the Workforce of the Future: The Trends and Training That Will Drive the Future of Drug Development

Why a fundamental reimagining of how clinical studies operate is still necessary to achieve a true paradigm shift—and shed the cycle of reliance on incremental gains.

The 50-Year Technology Drought in Clinical Trials: How AI Teammates Will Finally Bring Us Into the Modern Era

How the application of artificial intelligence, broader use of real-world evidence, decentralized clinical trials, master protocols, and risk-based quality monitoring, together with strong ethical oversight and increased collaboration, are contributing to better healthcare delivery and strengthening the role of clinical research in driving global health progress.

Effect of AI/ML, Real World Evidence and Master Protocols on Trial Success

Why future-ready pharma companies must embrace AI-driven, real-time decision-making. 

From Automation to Self-Optimization: The Next Leap in Clinical Trial Delivery

In this video interview, Kyle McAllister, co-founder, CEO, Trially, shares real-world examples of AI transforming clinical trial recruitment.

AI Levels the Playing Field in Trial Recruitment

, Kyle McAllister, co-founder, CEO, Trially, discussed the impact of funding cuts on underrepresented populations in medical research, emphasizing the importance of diversity-focused research. He highlighted the challenges created by budget cuts, particularly in patient recruitment and retention, due to reduced support staff. McAllister noted that artificial intelligence (AI) and new technologies like telemedicine are crucial for addressing these challenges by automating tasks and improving efficiency. He provided examples of AI's success in reducing chart review time and increasing patient enrollment in studies.

ACT: Are there examples you've seen where AI or digital tools have already made an impact on trial recruitment efficiency or targeting?

Absolutely, we're watching it every day. Like I said, the patient screening capability that we're rolling out to sites, we've seen sites decrease their chart review time by 90%. We also stack rank patients, so we can say, “Hey, these are the patients that fit,” and stack rank them based on their fit. That alone cuts 60-70% of the screen fail rate, because we're not spending time talking to patients that won't be a good fit for the study. Those are two really quick hit outcomes we've seen.

One really interesting, specific example that I love talking about, because I think it's just such a perfect example of how AI can be helpful in this space, is we have a, I would say, mid-size cardiology clinic that we work with. They have this really complex heart failure study that they've been recruiting for years. They've been on the study for—before we got connected—a year and a half, they had one patient recruited. The study was really struggling. The sponsor is breathing down their necks trying to get more patients into the study. After we got connected, it's been four months, they've now got seven enrollees in the trial, and now the sponsor is coming back like, “How did you do this? How could you possibly make this happen?” The really cool part, the part that gets me really excited, having spent time in the site world myself, is that was one research coordinator at one mid-sized site, and the second-best recruiting site on the study after her, is a giant academic institution with 20 CRCs coming through a huge database of people. It just really shows the power of really leveraging these tools can up-level a single individual to cover a lot of ground. Back to all the talk we've had about resourcing, it does take some lift off and make it so one person can achieve more. That’s just a handful of examples we've seen on the ground.

Videos

In this video interview, Kyle McAllister, co-founder, CEO, Trially, explains how AI is stepping in to fill staffing gaps in clinical research—streamlining patient identification, real-time feasibility assessments, and automated prescreening to help sites stay operational and efficient despite budget cuts.

How AI Can Ease Recruitment Burdens in Resource-Strained Trials

ACT: How can AI help address some of the recruitment challenges caused by reduced funding?

It's a difficult time in the industry for a lot of folks, but in a lot of ways, it's kind of AI's time to shine. We're seeing decreased human resources, but that's where AI is really supposed to pick up the lift, so I think AI can really augment a lot of basic tasks. It can leave, and ultimately, hopefully leave research teams to practice more at the top of their license. “Let's take the let's take the dirty work off your plate and let you focus on the things you came here to do, which is see patients and care for patients.” This is going to be very slanted based on a lot of the things we work on at Trially, but some of the big, big, exciting things that I see folks getting excited about for AI are, one, AI-powered patient identification. AI can sift through large amounts of data from EHRs, from CTMS systems, even from PDF documents, taking what is, 30 plus minutes, hours of time, reading through patients’ charts down to moments. That’s huge. We've had sites where we have teams that do 90% less chart review than they did before the system gets implemented. Quick example, I spent my entire career before this, before basically OpenAI and Sam Altman happened, telling physicians that if you write it in a note, it's gone forever. In the time I spent at Epic and Cerner, that was the message, it's got to be documented discretely. That's just not true anymore. We can sift through a lot of that information and do it really quickly, which is powerful, that's industry shifting capability, so that's one.

The other would be, if we're already in there sifting through all that data, you are resource constrained as a site. Picking the right study, picking the studies that you're going to crush it on, is really important, so the ability to actually do real-time feasibility on that data set, and understand, do I have a population that supports our research? Us taking on this study is really big, so real-time feasibility, real-time business development and site select, or trial selection without guesswork, are really big things.

Then the last I'd call out is, you hear a lot about automated prescreening and engagement of patients with AI voice in call screen, and actually engage these patients directly with very human like capability, and that's a huge lift for sites. In my time actually working at a site network, it was a massive pain for all of our research coordinators to have to call, say we're doing a vaccine study and we have 10,000 potential candidates. How do you call 10,000 of those people to try to screen them into a trial. AI can really take the front-end lift of that, take the initial outreach, and then hand it off to a human to really close the deal and bring them in for the study. There's probably a thousand more use cases that I didn't hit, but those are some of those that are closest to our hearts.

How AI and Machine Learning Can Improve Patient Reported Outcomes in Clinical Trials

, Brian Ongioni, chief product officer, uMotif, discussed how the company actively incorporates patient and site feedback throughout the digital health product lifecycle to ensure its tools are both accessible and intuitive. By involving end users early in the development process, uMotif aims to reduce burden on patients and clinical sites alike, while also ensuring that digital endpoints are usable, meaningful, and capable of standing up to regulatory scrutiny. Ongioni shared insights into the company's co-design strategies, real-world examples from clinical trials, and his perspective on the evolving role of artificial intelligence in enhancing patient-reported outcomes.

ACT: Looking ahead, how do you envision AI and machine learning playing a role in refining patient-reported outcomes to reflect what truly matters to patients?

It’s definitely a hot topic, and I think there are several areas where AI can help. From an electronic adaptation standpoint, AI can be a major benefit in terms of speed and scalability—like translating materials from paper to electronic formats. More importantly, as it relates to capturing participants’ views, AI has the potential to elevate their voices and enable more meaningful feedback throughout the entire lifecycle of a trial. We're still in the early stages of applying AI in this space, and while there's healthy skepticism and criticism, I think it will be interesting to see how we continue to iterate and incorporate these technologies moving forward.

uMotif integrates patient and site feedback throughout the product development lifecycle to ensure its digital health tools are accessible, intuitive, and truly reflective of end-user needs. This is achieved through dedicated patient and site committees that collaborate with product teams early in the software design process. Whether it involves evaluating new features or reviewing early-stage prototypes, these stakeholders provide input that is incorporated before study-specific implementations, ensuring accessibility is embedded from the outset rather than added later.

A notable example of this co-design approach occurred during a Parkinson’s disease trial. Patients were given access to the platform before the study launched, allowing uMotif to make critical adjustments to accommodate their specific motor challenges. This included redesigning screen navigation and repositioning measurement tools to reduce burden and ensure data could be reliably collected for the intended endpoints.

Balancing patient usability with site workflows is also a core focus. uMotif developed a “hub model” to streamline the experience for clinical sites, consolidating disparate systems into a unified platform. By observing and incorporating site input—such as understanding their daily routines and workflow priorities—the company optimized functionality to reduce administrative burden. This site-and-patient-first mindset extends to the validation of digital endpoints, where uMotif organizes separate workshops for patient and site committees to provide feedback on new instruments, ensuring their relevance, usability, and potential regulatory acceptability.

Looking ahead, uMotif sees artificial intelligence and machine learning playing an increasingly important role in refining patient-reported outcomes. These technologies could support the transition from paper to electronic formats and enhance scalability. While there’s ongoing skepticism, AI has the potential to help surface what matters most to patients by amplifying their voices throughout the development lifecycle, provided it is implemented thoughtfully and iteratively.

Brian Ongioni, chief product officer, uMotif, discusses how AI and machine learning can enhance patient-reported outcomes by capturing meaningful feedback at scale and ensuring patient voices are reflected throughout the clinical trial lifecycle.

Latest Conference Coverage

Video Series

2025 DIA Annual Meeting: How AI and Machine Learning Can Improve Patient Reported Outcomes in Clinical Trials

2025 DIA Annual Meeting: Preparing Operational Teams for AI Workflows in Drug Development

At the DIA Annual Meeting, Peter Ronco, CEO, Emmes, emphasized the underrecognized but impactful role of the public sector—particularly the NIH and FDA—in advancing tech-enabled clinical development. These agencies have pioneered the use of AI and large language models for tasks such as automating IND submissions, optimizing protocol design, and leveraging decades of complex data to improve trial execution and patient recruitment. Ronco also dispelled common misconceptions about AI, stressing that while it enhances efficiency, human oversight remains essential. To fully realize AI’s potential, organizations must invest in education, culture change, and talent development. Looking ahead, the vision is for AI-driven workflows to become standard practice, helping reduce animal testing, improve regulatory processes, and address health disparities, all while establishing clear ethical and privacy standards globally.

ACT: How are you at Emmes preparing operational teams to work with AI-driven workflows—what’s the cultural or training investment needed to enable that shift?

The first part of your question was about the cultural shift, and that’s really where it all starts. We need to ensure that we're positioning AI across the entire company in a transparent and strategic way—by setting ambitious goals and clearly defining the expected time savings and efficiency gains. It has to be integrated into every program, every client conversation, and every internal discussion. We should constantly ask: 

How are we leveraging AI-driven workflows and approaches in our studies?

The second key piece is education. Everyone—whether you're a clinician, statistician, data manager, or in business development—needs to become fluent in how AI and large language models can be applied across the full drug development value chain.

Third, we need to acknowledge the evolution of talent. You might have been a highly successful statistician for 15, 20, or even 30 years, but the reality is your skill set must continue to evolve. These tools are changing the game, and we need to make sure teams aren’t working around them or duplicating efforts. Instead, we should be fully embracing them—streamlining processes and SOPs to make them truly fit for purpose in this new era.

Finally, we must measure success and impact. When all these pieces come together, they can drive a real cultural shift—where AI is no longer feared or viewed as a threat to our jobs. Instead, it becomes a tool that frees us from some of the more routine or tedious aspects of our work, allowing us as scientists and development leaders to focus on building and executing better studies.

 At the DIA Annual Meeting, Peter Ronco discussed how the public sector is quietly but effectively driving innovation in tech-enabled clinical development, often outpacing private industry in applying AI and data science. While commercial entities tend to be louder about their AI capabilities, public agencies like the NIH and FDA have led groundbreaking efforts in automating regulatory processes, leveraging large-scale longitudinal datasets, and supporting experimental applications of AI in protocol design and patient recruitment.

Specific NIH-led initiatives include the automation of IND submissions and protocol generation, as well as the use of legacy registries to identify trial participants and optimize study designs. These innovations have not only enhanced efficiency but also introduced a more scientifically rigorous approach to clinical research.

However, Ronco emphasized that several misconceptions around AI need to be addressed. One is the belief that AI can fully replace human oversight, whereas in reality, human judgment remains crucial for decision-making. Another is the assumption that AI is only useful for automating routine tasks; in fact, it also drives better protocol design and research methodology. Additionally, while some believe AI adoption will be slow, its rapid uptake may in fact be underestimated.

To integrate AI into operations, organizations must embrace a cultural shift. This includes transparent goal setting, cross-functional education on AI applications, talent development to support evolving skillsets, and a focus on measuring impact. Rather than being feared, AI should be viewed as a tool that removes tedious tasks and empowers researchers to focus on high-value work.

Looking ahead, Ronco envisions AI becoming a standard part of clinical research. Long-term goals include reducing animal testing, transforming regulatory reviews, improving post-market surveillance, addressing health disparities, and establishing global standards for ethical data use.

Peter Ronco, CEO, Emmes, explains how the company is investing in transparent goal setting, comprehensive education, and evolving talent strategies to embed AI-driven workflows across all teams—transforming the culture to embrace technology as a catalyst for innovation and efficiency in clinical development.

2025 DIA Annual Meeting: Designing Patient Friendly Digital Health Solutions 

Brian Ongioni, chief product officer, uMotif, discussed how the company actively incorporates patient and site feedback throughout the digital health product lifecycle to ensure its tools are both accessible and intuitive. By involving end users early in the development process, uMotif aims to reduce burden on patients and clinical sites alike, while also ensuring that digital endpoints are usable, meaningful, and capable of standing up to regulatory scrutiny. Ongioni shared insights into the company's co-design strategies, real-world examples from clinical trials, and his perspective on the evolving role of artificial intelligence in enhancing patient-reported outcomes.

ACT: How does uMotif integrate patient and site feedback during the product development lifecycle to ensure digital health tools are accessible and intuitive for both stakeholders?

We have several dedicated committees—both site and participant or patient groups—that our product teams regularly engage with for feedback. This might involve reviewing a completely new scale or functionality, or it could mean taking a prototype or mock-up and gathering early input. By incorporating that feedback early in the software development lifecycle, we ensure that accessibility and usability are baked into the product from the start, rather than being added as an afterthought during study implementation.

ACT: Can you share an example of how co-designing with patients and sites has directly improved a feature or function of a uMotif platform?

One example that comes to mind is a trial we ran for patients with Parkinson’s disease. Before launching the study, we gave participants the opportunity to test the solution. That early engagement allowed us to design the platform in a way that significantly reduced their burden. For instance, Parkinson’s patients often struggle with small screens and precise navigation, so we adjusted the layout and allowed repositioning of specific application elements. These changes were instrumental in making the data collection process more accessible and ensuring the measurements could reliably support the study’s endpoint.

Brian Ongioni, chief product officer, uMotif, shares how early collaboration with patients and clinical sites helps shape intuitive, accessible digital health tools—and why co-design is key to building effective clinical research platforms.

Public Sector Sets the Pace for AI in Drug Discovery and Approval

ACT: How is the public sector currently leading the charge in tech-enabled clinical development, and what can private industry learn from those efforts?

I’m here at DIA this week, and if you walk around the Exhibition Center, every vendor is promoting something related to AI, data science, or large language models. If you attend any of the presentations—especially those from Big Pharma—they’re all highlighting their investments in data science, spanning both discovery and development.

In contrast, the public sector hasn’t done a great job of promoting its own work. But in reality, agencies like the NIH, FDA, and others across the US have made substantial contributions. They’ve invested across the full spectrum—from discovery to development to regulatory approval—on how data science and large language models can be applied to accelerate and improve the process of bringing new medicines to market.

ACT: Can you share specific examples from NIH-led innovations that have meaningfully impacted trial design or execution using AI or large language models?

Sure—there are a few key examples. First, several NIH institutes have taken bold steps toward automation. They’re exploring how to automate IND submissions, protocol authoring, and the generation of tables, listings, and figures—essentially every aspect of the data pipeline—to make these processes more efficient.

Second, many of these institutes have access to extremely large, complex, and often decades-old datasets, including registries and long-term studies that go back 30, 40, even 50 years. These datasets are incredibly valuable for informing trial design and identifying potential trial participants.

Lastly, in my experience, the NIH is genuinely committed to experimentation. They’re actively exploring new ways of tackling challenges and are leveraging their deep data resources to train and refine AI models, which is a major strength.

At the DIA Annual Meeting, Peter Ronco discussed how the public sector is quietly but effectively driving innovation in tech-enabled clinical development, often outpacing private industry in applying AI and data science. While commercial entities tend to be louder about their AI capabilities, public agencies like the NIH and FDA have led groundbreaking efforts in automating regulatory processes, leveraging large-scale longitudinal datasets, and supporting experimental applications of AI in protocol design and patient recruitment.

Peter Ronco, CEO, Emmes, explains how public sector leaders are driving innovation in clinical development through automation, long-term data utilization, and experimental trial design—despite the private sector dominating the conversation around artificial intelligence.

2025 DIA Global Annual Meeting: Public Sector Sets the Pace for AI in Drug Discovery and Approval

In this video interview, Jim Kremidas, executive director, Association for MultiSite Research Corporations (AMRC), highlights opportunities to improve upon inefficiencies that currently exist in clinical workflows. 

Rethinking Clinical Trial Efficiency Amidst Cost Pressures on Pharma

, Jim Kremidas, executive director, Association for MultiSite Research Corporations (AMRC), discussed the Trump Administration's ‘Most Favored Nation’ pricing policy for pharmaceuticals, which aims to match the lowest global prices to reduce costs in the US. Based on his past experience at Eli Lilly, Kremidas expressed concerns about the policy’s impact on pharma companies' clinical development and NIH funding, which could lead to reduced investment in new therapies. Kremidas also highlighted the potential of multisite clinical research corporations (MCRCs) and how they can streamline clinical operations by consolidating contracts and improving efficiency.

ACT: We’re seeing increased financial pressure on pharmaceutical sponsors. Where do you think they'll look first to find cost efficiencies, and how do clinical trials fit into that equation?

There's two major areas, if you will, that a pharma company can look at. One would be in their sales and marketing or the commercialization of the products that they currently have available. I'm sure there are ways to cut costs there. I'm not going to go into that, because I think this audience is really more interested on the research and development side of the equation. As I mentioned earlier, it's going to have an impact in terms of the approach that pharma companies take to developing new drugs. Again, the area of the research side, so pre-clinical there's probably opportunities there to cut costs. I don't know if that's good or bad, probably bad, but on the clinical development side, we think that there are opportunities to reduce the costs of development. Now, a lot of effort these days is going into using new technologies in order to do that, for example, artificial intelligence and some of these other tools. One of the things that that we feel is important is to understand that the development of these of products, as you get through Phase I, II, and III for submission, technology helps, but at the end of the day, it's people who administer these studies. There are people that manage the studies, the site staff, the pharma company staff, the CRO staff, so there's going to be an awful lot—we believe—of opportunity to improve on the inefficiencies that currently exist from the way things are currently structured, in the way that we develop drugs, Phase I-III at this point in time.

In this video interview, Michel van Harten, MD, CEO, myTomorrows, highlights the potential of artificial intelligence in digital twin technology. 

The Future of Drug Discovery: AI-Powered Predictions and Virtual Patient Models

, Michel van Harten, MD, CEO, myTomorrows, discussed the integration of artificial intelligence (AI) in clinical trials, highlighting its potential to reduce costs, accelerate timelines, and improve inclusion. Looking forward, advancements with AI are expected to speed up drug discovery, predict drug efficacy, and develop digital twins for personalized treatment simulations, potentially reducing trial risks and costs.

ACT: Looking forward, what are some other ways that you see AI having an impact on drug discovery?

In general, it will speed up drug discovery, which is usually a process that lasts for four years and costs billions of dollars. AI is helping, I think, scientists to go through huge datasets to identify promising drug compounds faster than ever before, and it will probably also predict which ones are likely to work, and also in which patient populations they will work, also with the level of precision we've never had before.

I think another thing that is very interesting is that we're also seeing major progress in something called digital twin technology, so that's a virtual replica of a real patient, and these models can simulate how a specific person might respond to a drug or treatment before they even ever tried it, so in the future, this could mean fewer risks and also fewer people needed for early trials.

In this video interview, Michel van Harten, MD, CEO, myTomorrows, discusses how patient education and remote monitoring can help with reducing the burden of trial participation. 

How AI Lowers the Real-World Barriers to Trial Participation

ACT: While there is potential for AI in operational aspects of trials, how can it benefit the patients participating in them?

I think it's important to lowering the barrier to actually identify and access options, and by educating them in a patient-friendly way, in their own language, and educate them. I think it's also important to support more remote monitoring to lower logistical barriers and reduce overall impact so that patients don't have to travel that much, etc. and lower the impact of participating into a trial.

In this video interview, Michel van Harten, MD, CEO, myTomorrows, highlights how artificial intelligence can be used to address logistical barriers such as access and treatment cost.

The Role of AI in Solving Clinical Trial Diversity and Access Challenges

ACT: How can AI be used to address underrepresentation in trials?

I think in general, access to clinical trials is a big deal, especially for people from underrepresented communities, and we believe that artificial intelligence plays a big role in changing that. Right now, the way to clinical trials and the way clinical trials are set up, often creates barriers that are very tough to overcome. Many trial sites are concentrated in big cities or academic medical centers, so if you live in a rural or underserved area, just getting to a trial might be out of reach, and for some people, there are also a lot of financial challenges like treatment costs or logistical challenges like transportation, and these burdens hit underrepresented populations especially hard, as well as people with lower incomes. Also, these people in those areas are not always made aware of the opportunities, not educated on the concept of clinical trials, and physicians are also not equipped to look for trials for their patients, so this leads to a situation, for example, in the US, where I think racial and ethnic minorities represent only 2% of participants in clinical trials, and that's of course a problem, because when certain groups are left out, we also miss out on crucial data, including how different people from different backgrounds respond to medications, so how can AI help? At myTomorrows, we lower the barriers for physicians and patients to identify and access trials. At the moment, we have two examples built into our product, where AI is used for treatment matching, where we save about 90% of the time that a physician is spending on matching a patient's profile to all those eligibility criteria. Second is education. As you know, the healthcare space is full of terminology which is very difficult to understand for patients and when it comes to clinical trials, it's even more complex, so AI can really help to translate consent forms, educational materials, etc. into multiple languages and use simpler terms, make it more accessible to non-English speakers and those also with low health literacy.

Artificial Intelligence/Machine Learning

Latest News