[Federal Register Volume 91, Number 82 (Wednesday, April 29, 2026)]
[Notices]
[Pages 23100-23102]
From the Federal Register Online via the Government Publishing Office [www.gpo.gov]
[FR Doc No: 2026-08281]


-----------------------------------------------------------------------

DEPARTMENT OF HEALTH AND HUMAN SERVICES

Food and Drug Administration

[Docket No. FDA-2026-N-4390]


AI-Enabled Optimization of Early-Phase Clinical Trials Pilot 
Program; Request for Information

AGENCY: Food and Drug Administration, HHS.

ACTION: Notice; request for information.

-----------------------------------------------------------------------

SUMMARY: The Food and Drug Administration (FDA or the Agency) is 
issuing this request for information to solicit input on a proposed 
pilot program to assess how artificial intelligence (AI)-enabled 
technologies can improve efficiency, speed, and quality of decision-
making in early phase clinical trials. Early-phase clinical trials 
represent a critical bottleneck in drug development, often 
characterized by high uncertainty, limited patient populations, and 
inefficient decision-

[[Page 23101]]

making processes. This pilot program aims to explore how advances in AI 
and data science can improve trial efficiency, enhance safety 
monitoring, facilitate dose selection decisions, and enable more 
informed early go/no-go decisions (e.g., a regulatory decision as to 
whether a Phase 1 study may proceed) while maintaining FDA's rigorous 
scientific and regulatory standards and promoting trustworthy AI 
systems. The pilot program will be guided by principles aligned with 
the National Institute of Standards and Technology (NIST) AI Risk 
Management Framework (AI RMF).

DATES: Either electronic or written comments must be received by May 
29, 2026.

ADDRESSES: You may submit comments as follows. Please note that late, 
untimely filed comments will not be considered. The https://www.regulations.gov electronic filing system will accept comments until 
11:59 p.m. Eastern Time at the end of May 29, 2026. Comments received 
by mail/hand delivery/courier (for written/paper submissions) will be 
considered timely if they are received on or before that date.

Electronic Submissions

    Submit electronic comments in the following way:
     Federal eRulemaking Portal: https://www.regulations.gov. 
Follow the instructions for submitting comments. Comments submitted 
electronically, including attachments, to https://www.regulations.gov 
will be posted to the docket unchanged. Because your comment will be 
made public, you are solely responsible for ensuring that your comment 
does not include any confidential information that you or a third party 
may not wish to be posted, such as medical information, your or anyone 
else's Social Security number, or confidential business information, 
such as a manufacturing process. Please note that if you include your 
name, contact information, or other information that identifies you in 
the body of your comments, that information will be posted on https://www.regulations.gov.
     If you want to submit a comment with confidential 
information that you do not wish to be made available to the public, 
submit the comment as a written/paper submission and in the manner 
detailed (see ``Written/Paper Submissions'' and ''Instructions'').

Written/Paper Submissions

    Submit written/paper submissions as follows:
     Mail/Hand Delivery/Courier (for written/paper 
submissions): Dockets Management Staff (HFA-305), Food and Drug 
Administration, 5630 Fishers Lane, Rm. 1061, Rockville, MD 20852.
     For written/paper comments submitted to the Dockets 
Management Staff, FDA will post your comment, as well as any 
attachments, except for information submitted, marked and identified, 
as confidential, if submitted as detailed in ``Instructions.''
    Instructions: All submissions received must include the Docket No. 
FDA-2026-N-4390 for ``AI-Enabled Optimization of Early-Phase Clinical 
Trials Pilot Program; Request for Information.'' Received comments, 
those filed in a timely manner (see ADDRESSES), will be placed in the 
docket and, except for those submitted as ``Confidential Submissions,'' 
publicly viewable at https://www.regulations.gov or at the Dockets 
Management Staff between 9 a.m. and 4 p.m., Monday through Friday, 240-
402-7500.
     Confidential Submissions--To submit a comment with 
confidential information that you do not wish to be made publicly 
available, submit your comments only as a written/paper submission. You 
should submit two copies total. One copy will include the information 
you claim to be confidential with a heading or cover note that states 
``THIS DOCUMENT CONTAINS CONFIDENTIAL INFORMATION.'' The Agency will 
review this copy, including the claimed confidential information, in 
its consideration of comments. The second copy, which will have the 
claimed confidential information redacted/blacked out, will be 
available for public viewing and posted on https://www.regulations.gov. 
Submit both copies to the Dockets Management Staff. If you do not wish 
your name and contact information to be made publicly available, you 
can provide this information on the cover sheet and not in the body of 
your comments and you must identify this information as 
``confidential.'' Any information marked as ``confidential'' will not 
be disclosed except in accordance with 21 CFR 10.20 and other 
applicable disclosure law. For more information about FDA's posting of 
comments to public dockets, see 80 FR 56469, September 18, 2015, or 
access the information at: https://www.govinfo.gov/content/pkg/FR-2015-09-18/pdf/2015-23389.pdf.
    Docket: For access to the docket to read background documents or 
the electronic and written/paper comments received, go to https://www.regulations.gov and insert the docket number, found in brackets in 
the heading of this document, into the ``Search'' box and follow the 
prompts and/or go to the Dockets Management Staff, 5630 Fishers Lane, 
Rm. 1061, Rockville, MD 20852, 240-402-7500.

FOR FURTHER INFORMATION CONTACT: Mallika Mundkur, Deputy Chief Medical 
Officer, Office of the Commissioner, Food and Drug Administration, 
10903 New Hampshire Ave., Silver Spring, MD 20993, 301-796-8800.

SUPPLEMENTARY INFORMATION:

I. Background

    This request for information provides an opportunity for interested 
parties and the public to share their input on a proposed pilot program 
to assess how AI-enabled technologies can improve efficiency, speed, 
and quality of decision-making in early phase clinical trials.

A. Challenges

    Early-phase trials face:
     Uncertainty in dosing, safety, and efficacy.
     Limited patient populations.
     Inefficient progression decisions.
     Long timelines and high resource demands.

B. Potential of AI 1
---------------------------------------------------------------------------

    \1\ 15 U.S.C. 9401(3) (also cited in FDA's Draft Guidance for 
Industry on Considerations for the Use of AI to Support Regulatory 
Decision-Making for Drugs and Biological Products):
    The term ``artificial intelligence'' means a machine-based 
system that can, for a given set of human-defined objectives, make 
predictions, recommendations or decisions influencing real or 
virtual environments. Artificial intelligence systems use machine 
and human-based inputs to--
    (A) perceive real and virtual environments;
    (B) abstract such perceptions into models through analysis in an 
automated manner; and
    (C) use model inference to formulate options for information or 
action.
---------------------------------------------------------------------------

    AI may:
     Improve patient recruitment.
     Optimize dose escalation.
     Enhance safety monitoring.
     Enable adaptive designs.
     Support earlier Phase 1 to 2 decisions.
     Improve biomarker assessment.
     Improve biomarker-based patient selection/stratification.
     Validate endpoints.

C. Trustworthy AI

     FDA supports AI use by external sponsors/investigators 
aligned with NIST AI RMF \2\ principles: valid, safe, secure, 
accountable, explainable, privacy-protective, and fair.
---------------------------------------------------------------------------

    \2\ The NIST AI RMF is available at https://www.nist.gov/itl/ai-risk-management-framework.
---------------------------------------------------------------------------

     FDA will apply considerations previously outlined in draft 
guidance

[[Page 23102]]

regarding the use of AI to support regulatory decision-making.\3\
---------------------------------------------------------------------------

    \3\ Considerations for the Use of Artificial Intelligence To 
Support Regulatory Decision-Making for Drug and Biological Products 
available at https://www.fda.gov/regulatory-information/search-fda-guidance-documents/considerations-use-artificial-intelligence-support-regulatory-decision-making-drug-and-biological.
---------------------------------------------------------------------------

D. Industry Alignment

     Industry practices include AI governance, assurance, and 
risk management frameworks. FDA aims to enhance the use of AI by 
industry in the conduct of clinical trials in line with such practices.

E. Pilot Program

     The pilot will involve the recruitment of sponsors that 
are currently or will be pursuing early phase clinical trials through 
product applications submitted to the Center for Drug Evaluation and 
Research, the Center for Biologics Evaluation and Research, and the 
Oncology Center of Excellence.
     The pilot will be coordinated by the Deputy Chief Medical 
Officer within the Office of the Commissioner.

II. Expanded Considerations for Pilot Development

    FDA seeks input on the questions below. To help FDA review comments 
efficiently, please identify the question to which you are responding 
by its associated category and number. If you are responding to more 
than one question, please identify each question to which you are 
responding, and categorize each response by question.

A. Pilot Program Design and Implementation

    FDA seeks input on how to structure the pilot to maximize learning, 
feasibility, and impact:
1. Scope and Focus
    a. Which trial types or trial issues might benefit most from the 
application of AI (e.g., first-in-human, oncology dose escalation, rare 
disease trials)?
    b. Should the pilot target specific therapeutic areas or remain 
broadly applicable?
    c. Should priority be given to specific AI use cases (e.g., 
recruitment, safety monitoring)? If so, which?
2. Participant Selection
    a. What criteria should FDA use to select sponsors, trials, or 
technologies?
    b. How can the pilot ensure representation across organization 
size, capability, and therapeutic areas?
3. Collaboration Models
    a. What partnerships (e.g., sponsor-tech vendor-academic-FDA) are 
most effective?
    b. How can FDA facilitate pre-competitive collaboration and 
knowledge sharing?
    c. What role should patient groups and investigators play in AI 
governance?
4. Operational Structure
    a. What support (e.g., regulatory engagement, technical guidance) 
should FDA provide?
    b. What infrastructure is needed (e.g., secure data environments, 
shared tools)?
    c. How can the pilot accommodate varying levels of AI maturity 
across participants?
5. Timeline and Milestones
    a. What is an appropriate duration for the pilot?
    b. What interim milestones or checkpoints should be included (e.g., 
enrollment, safety review, interim analyses)?
    c. How should FDA balance rapid insights with rigorous evaluation?
6. Knowledge Sharing
    a. How should lessons learned be captured and disseminated?
    b. What mechanisms can promote transparency while protecting 
proprietary information?

B. Evaluation Metrics and Success Criteria

    FDA seeks input on appropriate metrics and approaches to evaluate 
the pilot program, including:
1. Trial Efficiency and Speed
    a. How should improvements in trial efficiency be measured (e.g., 
time to initiation, enrollment, or completion)?
    b. What metrics should be used to assess reductions in time from 
Phase 1 completion to Phase 2 initiation?
    c. How can improvements in participant screening, recruitment 
efficiency, and participant retention be quantified?
2. Decision Quality
    a. How can the quality and timeliness of go/no-go decisions be 
evaluated (both FDA regulatory decisions and sponsor-internal decision 
points)?
    b. What methods can assess concordance between AI-supported and 
traditional decision-making?
    c. How should reductions in late-stage trial failures attributable 
to improved early-phase decisions be measured?
3. Participant Safety and Data Integrity
    a. What metrics should be used to evaluate the detection and 
response time for safety signals?
    b. How should the impact of AI on adverse event rates or protocol 
deviations be assessed?
    c. What measures can assess improvements in data completeness, 
accuracy, and consistency?
4. AI System Performance
    a. What metrics are most appropriate for evaluating AI model 
accuracy, robustness, and generalizability?
    b. How should AI system stability over time be measured, including 
detection and mitigation of model drift?
    c. How can performance be evaluated across different patient 
populations, trial sites, and therapeutic areas?
5. Trustworthiness (Aligned With NIST AI RMF)
    a. What evidence should demonstrate that AI systems are valid and 
reliable in clinical trial contexts?
    b. How should safety and risk mitigation associated with AI systems 
be evaluated?
    c. What metrics can assess transparency and explainability for 
different stakeholders, and are there metrics available that would be 
applicable to both sponsor-developed and proprietary systems?
    d. How should privacy protections and data governance practices be 
evaluated?
    e. What approaches should be used to assess fairness across 
demographic and clinical subgroups?
6. Comparative Evaluation
    a. What comparators are most appropriate (e.g., historical 
controls, concurrent non-AI trials, simulation studies)?
    b. How should differences in trial design, complexity, or 
therapeutic area be accounted for in comparisons?
7. Qualitative Outcomes
    a. How can stakeholder trust in AI-enabled trial approaches be 
assessed (e.g., investigators, participants, regulators)?
    b. What methods can evaluate usability and integration into 
clinical workflows?
    c. How should perceived value, scalability, and operational 
feasibility be measured?

Grace R. Graham,
Deputy Commissioner for Policy, Legislation, and International Affairs.
[FR Doc. 2026-08281 Filed 4-28-26; 11:15 am]
BILLING CODE 4164-01-P