SCOPE Summit 2025: Rajneesh Patil of IQVIA Highlights the Use of AI/ML in Improving Overall Cycle Times and Clinical Development

ACT: Can you share a few examples of how artificial intelligence/machine learning (AI/ML) can mitigate risks that have traditionally impacted clinical trial success?

Patil: Sure, while there are quite a few areas which can help improve the overall cycle time and clinical development, we are seeing some specific areas around trial feasibility, so site selection, patient selection, types of algorithms, which are AI driven, are helping us improve on metrics of patient recruitment rates, non-enrolling sites is another key metric, so a lot of our sponsors are looking to solve for these problems. Those are a couple areas. In the pharmacovigilance space which relates to patient safety, monitoring, etc., there is a huge opportunity, and we are seeing some value there in terms of automating some of those workflows in pharmacovigilance. Signal detection is one. These models are great at detecting safety signals if we can prompt them adequately and following that even the workflow automation of some of these next best action types of capabilities is another area where we're seeing significant improvements. There's also something to be said about the clinical operations efficiency overall. We do have, as an industry, looking at productivity and efficiency as goals, so there are several use cases within clinical operations, starting from monitoring at the sites. The administrative burden of document management, for example, is another area we can use AI to do compliance management, do escalation management in terms of working with sites, etc. The clinical operations world, where we see monitoring document compliance, and other administrative processes, those could get a solid benefit from the AI type of use cases.