HHS announces new efforts to speed up, expand clinical trials with AI

STAT News – Wednesday, September 30, 2026
By Margaret Manto

The Department of Health and Human Services announced a set of new initiatives aimed at speeding up clinical trials by incorporating more artificial intelligence and computational models and moving away from sharply delineated trial phases.

The centerpiece five-year program, dubbed SURPASS — “Simulation-augmented, Real-time Platform Adaptive Seamless Trials” — will kick off later this fall by accepting “ground-breaking ideas from cross-disciplinary teams in statistics, AI, and clinical trial design, operations, and regulation,” reads a website about the program.

HHS is launching the program through the Advanced Research Projects Agency for Health. The initial announcement did not note how much funding was designated for the new initiatives, nor did it provide details on whether participants would be offered more flexibility or resources.

The announcement of SURPASS was coupled with the debut of three other initiatives, two of which are in partnership with the University of Texas at Austin Dell Medical School and will expand the number of clinical trials sites and develop a national research data resource. The third will allow patients to contribute their own data to clinical trials.

HHS and the Food and Drug Administration have pushed to accelerate clinical research in the U.S. to compete with China and other countries. In June, the department announced Operation TrialBlazer in an effort to shorten the FDA’s drug approval timelines; it launched a pilot program earlier this month that will pair companies with research institutions to generate more pre-FDA-review feedback.

The exact details of all the newly announced initiatives are not entirely clear. A solicitation for SURPASS proposals posted on a government website indicates that ARPA-H is casting a rather wide net for potential projects under the program, stating that proposers may select “any disease area if they demonstrate substantial unmet patient need,” but that neurodegenerative diseases are of “particular interest for SURPASS platforms.”

Participants in the program are encouraged to consider computer-based, or in-silico, methods for replacing traditional clinical trial data, the solicitation says: “Replacement of human control information with in silico information must be graduated and evidence-based.”

The solicitation also states that one phase of the project is aimed at developing and validating AI-enabled operational systems that can be applied to many elements of clinical trial operations. It includes a 23-item list of potential AI capabilities, including “participant pre-screening”; “clinical data collection and reconciliation”; “safety reporting and reconciliation”; and “training including documentation.”

Access this article at its original source.