The U.S. Food and Drug Administration’s (FDA’s) recent launch of an agency-wide large language model–powered artificial intelligence (AI) tool known Elsa and ongoing efforts to have another AI tool known as CDRH-GPT in place for speeding up reviews and approvals of medical devices by the end of June have attracted their share of both supporters and detractors. With AI seemingly also coming at full speed into the daily routines of leaders and staff at clinical trial sites, contributors to ACRP’s Clinical Researcher journal are taking a closer look at current and potential applications of AI by study teams at work in the trenches.
“The development of machine learning (ML) models has enabled professionals to perform risk prediction for events such as trial failure,” notes Aleksa Jovanovic, MD, PhD, a Scientific Engagement and Innovation Specialist with Wemedoo AG in Switzerland, in the latest issue of Clinical Researcher (June 2025). “The process starts with data engineers training ML models on data from trials that were performed in the past, the information for which is publicly available on repositories such as ClinicalTrials.gov. Another AI-driven tool—natural language processing—is used to extract unstructured data in a usable format for the ML model. The model can then be shown a new study and make a prediction based on thousands of factors on which it was taught.”
Another promising usage of AI in clinical trials is the use of chatbots for trial recruitment and patient engagement by way of facilitating the informed consent process, sending personalized reminders about upcoming visits, and providing educational material and counseling prior to visits, Jovanovic points out.
In his article, Jovanovic also describes how AI can be used in support of medical writing for protocol development and medical scribes for documenting patient encounters.
“Successful AI integration in clinical settings requires more than just adding AI tools as an afterthought,” Jovanovic cautions. “Clinical data management systems need robust validation frameworks, semantic technologies for better AI communication, and intuitive interfaces that support human oversight.”
Meanwhile, in a peer-reviewed article accepted for publication in the August issue of Clinical Researcher, Avery M. Davenport, MPH, CCRC, Director of Clinical Research at Commonwealth Pain & Spine and Chair and Founder of the ACRP Kentucky Chapter in Louisville, Ky., observes that the clinical research enterprise cannot risk dragging its feet where AI is concerned.
“Healthcare has always been slow to adapt to change,” Davenport writes. “If the industry is on time or even catching up to the latest trend in the market, rest assured, healthcare is about a decade behind. One area that healthcare cannot afford to lag behind the times in is the use of digital health—specifically, artificial intelligence. Whether it is using AI to read an X-ray or to help dictate a physician’s progress note on a patient during follow up, the conversation cannot be ignored. Those who fail to enter the discussion will be left behind.”
The slow pace of adaptation of AI in clinical research is understandable, he notes. “With strict regulatory bodies, an ‘at no risk’ approach, and worries about safety, compliance, and being sued, the fears surrounding AI are clear,” he adds. “Integration of AI into clinical trials is imperative, but faces some cultural opposition. The good thing is that resistance to change can…well…change.”
In his forthcoming article, Davenport examines factors surrounding costs, data overload, patient recruitment, trial design, regulatory and compliance issues, and competition in relation to plugging AI into clinical study sites.
AI was also a hot topic at the recent ACRP 2025 gathering in New Orleans, including in a Signature Series session covered in this blog and now available as a recording in the ACRP Course Catalog as part of a packet of Technology & Future Trends topics or in the Full Program of replays. A collection of AI-related items, including an ACRP white paper published earlier this year on “Responsible Oversight of Artificial Intelligence for Clinical Research Professionals,” can be found in the frequently updated ACRP Artificial Intelligence Resource Center.
Edited by Gary Cramer
