WASHINGTON, D.C. — The Department of Health and Human Services is backing a new clinical-trial model that would use predictive simulations, real-time statistical analysis and automation to reduce the time, cost and number of participants required to evaluate drugs and biologics.
The Advanced Research Projects Agency for Health, or ARPA-H, launched the Simulation-augmented, Real-time Platform Adaptive Seamless Trials program, known as SURPASS, alongside three related projects addressing clinical sites, health data and patient participation.
The effort targets a drug-development process that HHS estimates can take more than a decade, cost as much as $2 billion on average and fail more than 90% of the time.
SURPASS would replace parts of the conventional sequential clinical-trial process with continuous adaptive platform trials. The model is intended to allow researchers to evaluate accumulating data and modify trials without waiting for traditional stages to conclude.
The program will combine predictive computational models, shared infrastructure, common control groups and real-time analysis. ARPA-H is seeking methods that could produce regulatory-grade evidence while reducing reliance on large conventional control groups.
“Today’s clinical trial system often requires too many stops, too much duplicated infrastructure, and too much time before researchers can understand whether a trial is on the right track,” SURPASS Program Manager Daria Fedyukina said.
One component will develop a “phaseless” design engine incorporating digital twins and other predictive models. Researchers would simulate clinical and operational outcomes before trials begin and develop evidence intended to establish regulatory confidence in those methods.
A second component will develop a continuous inference system capable of analyzing trial results in real time or on demand. The approach is designed to support faster modifications while maintaining statistical rigor.
The third will use agentic technology to automate portions of trial startup and operations, including adding treatment arms and accelerating data collection, cleaning and dataset construction.
ARPA-H is pairing SURPASS with three projects targeting infrastructure problems that can delay trials even when study designs are established.
STACK will use artificial intelligence to accelerate activation of clinical-trial sites and help facilities without research experience develop the capacity to conduct studies. Expanding the number of domestic sites could also increase patient access to trials closer to home.
COMMONS will focus on nationwide data infrastructure, including a privacy-focused architecture for patient consent and access to regulatory-grade data. Such infrastructure could support enrollment and the computational models envisioned under SURPASS.
CINCH will focus on patient-generated real-world data and navigation, with the goal of making it easier for patients to contribute information while identifying clinical trials that may be appropriate for them.
Together, the four efforts target trial design, site capacity, fragmented data systems and patient participation — separate bottlenecks that can extend development timelines and increase costs.
HHS is also seeking to make resulting regulatory documents, validated standards and demonstrations publicly available, potentially allowing drug developers, research sites, regulators and technology companies to use methods developed through the programs.
The initiative is part of a broader federal effort to accelerate clinical development and retain more clinical-trial activity in the United States. Whether the proposed technologies can materially shorten development timelines will depend in part on their ability to generate evidence that meets regulatory standards.
Support the local news that supports Chester County. MyChesCo delivers reliable, fact-based reporting and essential community resources—free for everyone. If you value that, click here to become a patron today.