In this episode of AI For Pharma Growth, Dr Andree Bates speaks with Tom Coates, CEO of Presentient, about why interim analysis in clinical trials is ready for a major upgrade.
Interim analyses allow sponsors to look at trial data mid-flight and assess whether a study is likely to succeed or fail, using pre-specified rules. But Tom explains that many phase two and three commercial trials still do not include a pre-planned interim analysis, meaning sponsors often wait far longer than necessary to detect futility or act on early signs of success.
The conversation explores how Presentient is working on next-generation interim analysis and readout strategies, including the BRX platform, which is designed to handle unblinded data while protecting trial integrity. Tom explains why it is not enough to have a powerful algorithm. Sponsors also need secure architecture, audit trails and methods that regulators and data monitoring committees can trust.
Tom also discusses where AI does and does not belong. For high-stakes stop or go decisions, explainability, reproducibility and regulatory confidence matter more than hype. But model-based methods, synthetic data and subgrouping engines may help sponsors better understand which patients benefit, who does not, and how to design trials around more meaningful treatment signals.
The key message is that interim analysis should not be an underused checkpoint. Done well, it can help sponsors stop failing trials earlier, prepare for success sooner and make better decisions with greater confidence.
Topics Covered
Why interim analysis is underused
Stopping trials early for futility or success
Protecting blinding and trial integrity
Secure handling of unblinded data
What data monitoring committees need to see
Where AI fits, and where it does not
Subgrouping and individual treatment effects
Synthetic data and trial simulation
Regulatory confidence and audit trails
The future of continuous trial monitoring
Eularis helps pharma and biotech leaders turn AI activity into board-defensible governed strategy and measurable commercial outcomes.
If your CFO asked tomorrow for the projected return of each major AI initiative - by year, across three years, with explicit adoption, operating cost and redeployment assumptions - could you produce an answer that survives scrutiny?
And if you could: would you know which of those initiatives most moves the company toward the outcomes it's exposed on over the next three years? Those are two different questions, and most organisations can't answer either. A strong initiative-level ROI tells you a project is defensible. It doesn't tell you it belongs among your top five. Capital spent on a second-order opportunity is capital no longer available for a first-order one — and no amount of downstream rigour recovers value that was never strategically prioritised.
The Eularis AI Strategic Blueprint models both levels: a financial case for every prioritised initiative, and a rigorously modelled ranking of which ones create the most material value against your commercial objectives — then sequences them by dependency rather than enthusiasm, with governance designed for pharma's regulatory reality. See what a board-defensible AI strategy contains → eularis.com/ai-strategic-blueprint-for-pharma
About the Podcast
AI For Pharma Growth is the podcast from Dr Andree Bates, helping pharma, biotech and healthcare organisations understand how AI-based technologies can save time, grow brands and improve company results. The show demystifies AI for biopharma leaders, from start-up biotech through to Big Pharma.
Dr. Andree Bates LinkedIn | Facebook | X
