Innovating Clinical Trials
Welcome to Innovating Clinical Trials, the podcast designed for clinical research professionals eager to deepen their understanding of clinical trials through concise, insightful segments. Join your hosts, Liam Eves and Ted Trafford, as they uncover the core issues in clinical research, reflect on the industry, and challenge conventional wisdom.
Ted Trafford - https://probitymedical.com/
With 30 years of experience in clinical research, Ted serves as the Director of Business Development, driving business growth and leading Feasibility and Site Relationship teams at Probity Medical Research, a clinical trial site administrative support company with a consortium of 75+ sites across four countries. As a writer and speaker, Ted contributes to thought leadership and strategic initiatives in the clinical trials industry, leveraging his extensive experience and creative approach to drive meaningful discussion and progress for Sponsors, CROs, Sites and Technology Vendors.
Liam Eves - https://www.theendpointpodcast.com/
Liam's held executive roles in SMOs and CROs, and led all major functions of trial delivery. His journey into the field began unexpectedly after an injury ended his career as a professional footballer. Over the years Liam has optimized trial delivery methods / systems for effective enrollment and trial delivery. Currently, he focuses on building and advising companies in the clinical trial space.
Opinions expressed are those of the participants and not their employers.
Innovating Clinical Trials
Ep 2.30: Scott Burgher on Where AI Actually Helps Patient Recruitment (Part 3/3)
Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.
In the final part of this three-part conversation, Liam and Ted close things out with Scott Burgher, Director of Patient Operations at Quest Diagnostics, looking ahead at where AI genuinely moves the needle in recruitment, and where the industry still gets feasibility wrong.
Scott breaks AI's near-term impact into two practical buckets. The first is administrative: compressing study startup from six to twelve months down to weeks by automating document collection, regulatory submissions, IRB correspondence, and budget negotiations, work that's repetitive by nature and ripe for automation. The second is data-driven: using EHR and lab data to flag genuinely qualified patients rather than relying on broad disease prevalence, cutting down what used to take a coordinator six weeks of manual review.
They Explore:
1. Where AI can realistically compress study startup timelines, and where it can't
2. Why mining EHR and lab data beats broad disease-prevalence estimates for site and patient feasibility
3. Why the human element becomes the differentiator as software gets commoditized
4. Why most feasibility processes are still solving the wrong problem
Scott's closing thoughts on data, predictive medicine, and the road to digital twins. The conversation closes on feasibility, which Scott calls broken at its core, working backward from protocol specifics to find the real "needle in the haystack" instead of the whole haystack. A thoughtful close to the series.