At SCOPE Europe 2025, we spoke with Dominique Demolle, CEO of Cognivia, about how behavioral AI is helping sponsors predict—and prevent—patient dropouts in clinical trials.
Demolle noted that 25–30% of participants drop out, and one-third of these are due to behavioral factors like anxiety or loss of motivation. Yet, this is rarely treated as a measurable, preventable risk.
She explained how Cognivia’s tool, ComplAI, uses psychometric data to flag high-risk participants before randomization. One study predicted 100% of dropouts in advance.
Demolle emphasized that dropout isn’t just a financial problem—each lost patient distorts intent-to-treat analysis and delays drug development. She believes proactive engagement, centered on individual risk profiles, is the future.
As AI and digital health converge, she envisions integrating real-time behavioral signals—like tone, frequency of contact, or biometrics—while balancing simplicity, ethics, and trial burden.
She stressed that retention hinges on meaning: when patients understand their “why,” adherence improves. Behavioral AI, she said, can scale that understanding across diverse populations.
This content is sponsored by Cognivia.
Moe Alsumidaie, MBA, MSF, is founder and Chief Editor of Vanguard Publications, which publishes Clinical Trial Vanguard, Pharma Vanguard and BullScope, and Head of Research at CliniBiz. He has two decades in clinical trial operations and data science, with earlier roles at Genentech, Abbott Vascular and Stanford University Medical Center, and is a guest lecturer in clinical trial sciences at Rutgers University.
