Register Now - Beyond Recruitment: The Future of Patient Site Engagement in Oncology Clinical Trials
Commentary|Videos|June 3, 2026

SCOPE X: The COPD Case Study That Shows What AI Can Do for Enrollment

In this video interview, Liz Beatty, co-founder and chief strategy officer at Inato, shares results from a Sanofi COPD study where AI-enabled sites screened patients 33% faster and achieved 100% enrollment success—including one site that had been non-performing for over 100 days.

Full interview summary

In a recent video interview with Applied Clinical Trials, Liz Beatty, co-founder and chief strategy officer at Inato, discussed how AI-enabled sites are reshaping trial planning and execution—drawing on themes from a session she participated in at the SCOPE X conference. She opened by noting that sponsor enthusiasm for AI is high and growing, but that a clear message emerging from the conference is that sites must be active participants in this transformation, not passive recipients of it. The most meaningful opportunity, she argued, is helping sites become as data driven as sponsors have become—using AI to understand their own patient populations and position themselves more precisely for the right trial opportunities.

Beatty described the longstanding inefficiencies that real-time site and patient data can address, from unreliable feasibility questionnaires and high rates of non-enrolling sites to poor screen failure rates driven by imprecise patient identification. She shared data from Pantheon Clinical Research, a site that saved four and a half weeks of chart review time on a single GLP-1 study using Inato's technology, and also achieved a significantly better screen failure rate than peer sites by using AI to prioritize patients most likely to meet screening criteria.

On the question of practical impact, Beatty pointed to a COPD case study conducted with Sanofi at SCOPE X as a compelling proof point. Sites using the AI assessment screened patients 33% faster and achieved 100% enrollment success, including one site that had been open and non-performing for 108 days and enrolled a patient within eight days of adopting the tool.

She identified the persistence of sponsor-specific site technology as the most significant barrier to broader adoption, arguing that the industry must shift from building tools for sponsors toward enabling sites to use shared infrastructure across all their trials. She closed on an optimistic note, pointing to early signs that sponsors are moving from trial-by-trial planning toward cross-asset partnerships with sites—a shift that, she noted, makes sites three times more likely to share patient data and could fundamentally accelerate enrollment before a single site is even selected.


Related to this article

Closing the Community Access Gap: Q&A with Kent Thoelke, Paradigm Health
In this Q&A, Kent Thoelke, CEO of Paradigm Health, discusses why participation gaps in community and rural settings come down to both patient cost barriers and site infrastructure, how legacy workflows weigh on community clinics, and what policy and technology changes it would take to make clinical research a real care option for more patients.
© Grispb - © Grispb - stock.adobe.com
Mistral and OpenAI produced identical overall eligibility labels across 200 synthetic patient-study assessments, with criterion-level disagreements concentrated in inclusion criteria where models switch between “Uncertain” and “Not included” when records lack sufficient evidence, so model choice should be driven by deployment architecture, control, and cost rather than assumed interchangeability.
The Human Side of Clinical Trials: Before Burden Becomes Risk, Capturing Friction in Real Time
In Episode 4 of The Human Side of Clinical Trials, host Brian S. McGowan, PhD, FACEHP, chief learning officer and co-founder of ArcheMedX, Inc., speaks with Jason Riis, PhD, CEO and chief behavioral scientist at Behavioralize, about how capturing friction closer to the moment it happens can reveal unclear instructions, technology friction, and workarounds that retrospective surveys and debriefs tend to miss.