Back to News
PolicyAI Understanding briefing

HHS launches SURPASS program to accelerate clinical trials with AI

The U.S. Department of Health and Human Services announced a five‑year SURPASS initiative that will use AI‑driven simulation and real‑time data platforms to streamline the design and execution of clinical trials.

4 min readRead the original reporting
Source-provided image accompanying HHS launches SURPASS program to accelerate clinical trials with AI
Attributed reportingSource recorded
Publisher
statnews.com
Source link
statnews.comhttps://www.statnews.com/2026/09/30/hhs-arpa-h-clinical-trials-artificial-intelligence-surpass-program/
Source type
Reporting by a news outlet — not a first-party document.

What we could not confirm independently: This claim is attributed to the named outlet. We did not verify it against a first-party document. (statnews.com)

ContextUnderstand this in 60 seconds

Start here

Key terms

Embedding
A numeric vector representation that captures semantic meaning of text, images, or other data.
Test yourselfAI Models Explained Quiz

What happened

The Department of Health and Human Services (HHS) unveiled a new five‑year effort called SURPASS – Simulation‑augmented, Real‑time Platform Adaptive Seamless Trials – aimed at speeding up clinical research by integrating artificial‑intelligence models and computational simulations into trial design. Launched through the agency’s Advanced Research Projects Agency for Health (ARPA‑H), the program will begin accepting proposals later this fall from interdisciplinary teams that include statisticians, AI researchers, and clinical trial experts. The initiative seeks to move away from the traditional, rigid phase‑by‑phase structure of drug studies, instead allowing adaptive, data‑driven adjustments throughout a trial’s lifecycle. The announcement did not disclose the total budget allocated to SURPASS, nor did it specify whether participating groups will receive dedicated funding, technical resources, or regulatory flexibility.

The SURPASS initiative was announced on September 30, 2026, as a five‑year effort coordinated by HHS’s ARPA‑H office. The program’s name reflects its focus on simulation‑augmented, real‑time platforms that enable adaptive, seamless trial designs.

According to the program’s website, SURPASS will solicit “ground‑breaking ideas from cross‑disciplinary teams in statistics, AI, and clinical trial design, operations, and regulation.” Proposals are expected to be submitted later this fall, with the first cohort of projects slated to launch in early 2027.

No specific funding amount was disclosed in the announcement, and the release did not detail whether participants will receive direct financial support, access to specialized computing resources, or regulatory leeway beyond existing FDA pathways.

Source details: statnews.com ↗

Why it matters

Accelerating clinical trials has long been a priority for both public health and the pharmaceutical industry, as delays can increase costs, postpone patient access to therapies, and limit the ability to respond to emerging health threats. By AI‑based simulation and real‑time analytics, SURPASS could reduce the time required to evaluate safety and efficacy, enable more efficient patient recruitment, and allow investigators to modify protocols on the fly based on emerging data. If successful, the program could set a new regulatory precedent for adaptive trial designs, potentially reshaping how the FDA and other agencies evaluate investigational products. However, key details remain unknown, including the amount of federal funding, the criteria for selecting pilot projects, and how the program will coordinate with existing trial infrastructure. These gaps create uncertainty about the program’s immediate impact and its scalability across diverse therapeutic areas.

Traditional clinical trials often follow a linear, phase‑based approach that can take years to complete. AI‑enabled simulation can model patient responses and trial outcomes before enrolling participants, potentially identifying inefficiencies early.

Adaptive trial designs, which allow modifications based on interim data, have been shown to reduce sample sizes and shorten study durations, but they require sophisticated data infrastructure and regulatory acceptance. SURPASS aims to provide a federal framework that encourages such designs.

If the program demonstrates tangible speed‑ups, it could influence global standards for drug development, encouraging other governments and private sponsors to adopt similar AI‑centric methodologies.

Interactive Mechanism

Interactive Mechanism: How It Actually Works

Explore the underlying technology behind this development interactively.

System Requirements:
Best ArchitecturePure RAGRecommended pattern
Hallucination RiskVery LowGrounding efficacy
Update Cost$0 (Vector sync)Ongoing maintenance
Core takeaway: Fine-tuning teaches models how to speak (form, style, syntax); RAG teaches models what to say (verifiable facts). Never use fine-tuning alone for factual memory.
Interactive Concept Check+10 Points
AI Models Explained Quiz

In AI, what are a model's "parameters"?

What to watch next

Future HHS releases that clarify SURPASS’s budget and selection process; pilot studies that demonstrate AI‑driven adaptive trial designs; regulatory guidance from the FDA on accepting AI‑generated data for trial endpoints; partnerships between ARPA‑H and biotech firms or academic institutions; and any measurable reductions in trial timelines or costs reported by early participants.

Announcements from HHS or ARPA‑H regarding the budget and selection criteria for SURPASS.

Results from the first cohort of pilot projects, especially any reported reductions in trial duration or cost.

FDA guidance or policy updates that reference AI‑driven adaptive trial designs, which would signal regulatory acceptance.

Collaborations between SURPASS participants and industry partners, indicating broader uptake of the program’s tools.

Related guides & quizzes

AI Models ExplainedFuture of AIAI EthicsTest what you know — try a free AI quizLook up an AI term in our glossaryFollow the AI regulation tracker
Found this useful?