TITLE: Evidence-Based Clinical Trial Design: When the Power of AI Meets
SPEAKERS: Will Ma, HopeAI
MODERATOR: Jerry Li
Abstract :
Clinical trial design decisions — from endpoint selection to sample size estimation to comparator arm construction — are only as good as the evidence informing them. Yet in practice, development teams often face fragmented literature, incomplete data, and limited access to patient-level information from prior studies, leading to designs built more on convention than on evidence.
This talk presents a framework where AI and statistical rigor converge to enable truly evidence-based clinical trial design. The approach, developed at HopeAI, integrates three core capabilities: (1) systematic, human-curated synthesis of clinical outcome data across indications through the PURE Evidence platform; (2) generation of synthetic individual patient data (SynthIPD) from published aggregate results, enabling trial-level simulations grounded in real-world evidence; and (3) agentic AI tools — including an AI Clinician and an AI Statistician — that work alongside biostatisticians to translate synthesized evidence into actionable design parameters.
We illustrate this framework through oncology case studies, demonstrating how AI-curated evidence and synthetic patient-level data can inform adaptive designs, optimize randomization strategies, and strengthen regulatory submissions by grounding design assumptions in a more complete evidence base. Critically, each AI-generated output is validated through established statistical methods — ensuring that AI amplifies, rather than replaces, statistical judgment.
When AI meets statistical rigor, the result is clinical trial designs that are both innovative and defensible — built on evidence, not convention.
Instructors’ Biography:
Will Ma is the founder and CEO of HopeAI, a Mayo Clinic Platform_Accelerate company on a mission to bring hope to patients through AI-accelerated clinical development. HopeAI has developed AI teammates that combine clinical insights with statistical innovations, enabling faster and more precise clinical trials. Prior to founding HopeAI, Will had over 10 years of experience in clinical development, including working as a statistician at Sanofi and BMS, and serving as a faculty member at Moffitt Cancer Center. Will is also a serial entrepreneur who co-founded Learnta, an AI learning company, and grew it to over 1,600 learning centers.