Gain perspective on how agentic AI can bridge eCOA, EDC, IRT, and CTMS platforms to reduce manual effort and improve operational efficiency.
In a recent video interview with Applied Clinical Trials, Michelle Longmire, MD, co-founder and CEO of Medable, discussed the role of agentic artificial intelligence (AI) in clinical trials. She highlighted that 45% of clinical development time is wasted due to delays and siloed data. Agentic AI aims to reduce this by leveraging technology in areas previously untouched, freeing up human resources for strategic work. The human-in-the-loop concept ensures that AI supports, rather than replaces, human decision-making. Integration of AI across legacy systems is facilitated by model context protocols, reducing manual effort. Automation handles routine tasks, while critical decisions remain human-controlled. No-code platforms for AI tools require clear job descriptions and validation similar to human training.
ACT: As clinical trials become more data-intensive and multi-platform, what are the biggest challenges to integrating AI systems across existing eCOA, EDC, IRT, and CTMS platforms? How should they be addressed?
Longmire: When I look at the first horizon of agentic AI and some of the value, it's actually to reduce the burden of legacy technology, and what I mean by that is today, a lot of the layering in of legacy technology has only meant more work for clinical operations experts and clinical drug developers, so agents are able to do work across these systems using MCP or model context protocols. Really, I think if there's a system that has been integrated before, MCPS bring leverage to those existing integrations and existing frameworks. So far, what I mean is, I think people often wonder, ‘Well, can I integrate this?’ I think the real question is, have you ever integrated it before, and if you have, then MCPs offer a whole new type of leverage to that problem. The operational aspects of working across systems is one of the ultimate and early value props for agentic AI. I really see that some of these first horizon value is just going to be, ‘Hey, now you know how to log into 50 different things and aggregate the data in a bunch of different places.’ You can use the agents to access those systems, retrieve critical data and provide critical insights, really reducing the manual effort of the current legacy technology environment.
