Вернуться к новостям
ПолитикаAI Understanding брифинг

HHS запускает программу SURPASS для ускорения клинических испытаний с использованием ИИ

Министерство здравоохранения и социальных служб США объявило о пятилетней инициативе SURPASS, которая будет использовать платформы моделирования на основе искусственного интеллекта и данных в реальном времени для оптимизации разработки и проведения клинических испытаний.

4 min readRead the original reporting
Source-provided image accompanying HHS launches SURPASS program to accelerate clinical trials with AI
Атрибутированная отчетностьИсточник записан
Издатель
statnews.com
Ссылка на источник
statnews.comhttps://www.statnews.com/2026/09/30/hhs-arpa-h-clinical-trials-artificial-intelligence-surpass-program/
Тип источника
Репортаж новостного агентства — не первичный документ.

Что мы не смогли подтвердить независимо: Претензия принадлежит указанному торговому центру. Мы не сверяли его с собственным документом. (statnews.com)

КонтекстПоймите это за 60 секунд

Начните здесь

Ключевые термины

Встраивание
Числовое векторное представление, которое отражает семантическое значение текста, изображений или других данных.
Проверьте себяВикторина с объяснением моделей искусственного интеллекта

Что случилось

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.

Подробности об источнике: statnews.com ↗

Почему это важно

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

Интерактивный механизм: как он на самом деле работает

Изучите технологию, лежащую в основе этой разработки, в интерактивном режиме.

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.
Интерактивная проверка концепции+10 Points
AI Models Explained Quiz

Which component of an AI application is the machine-learning model itself?

Что посмотреть дальше

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.

Сопутствующие руководства и викторины

Объяснение моделей искусственного интеллектаБудущее ИИЭтика ИИПроверьте свои знания — пройдите бесплатную викторину по искусственному интеллектуНайдите термин ИИ в нашем глоссарии.Следите за трекером регулирования ИИ
Нашли это полезным?