Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Sep;59(5):1074-1086.
doi: 10.1007/s43441-025-00803-0. Epub 2025 May 29.

The Adoption and Use of Artificial Intelligence and Machine Learning in Clinical Development

Mary Jo Lamberti  1 , Maria I Florez  2 , Hana Do  2 , Stephanie Rosner  3 , Timothe Menard  4 , Carrie Nielson  5 , Amanda Donovan  6 , Jingjing Ye  7 , Sathish Kaveripakam  8 , Birgit Schoeberl  8 , Alette R Hunt  8 , Helen Yeardley  9
Affiliations

The Adoption and Use of Artificial Intelligence and Machine Learning in Clinical Development

Mary Jo Lamberti et al. Ther Innov Regul Sci. 2025 Sep.

Abstract

Background: The use of artificial intelligence (AI) and machine learning (ML) in drug discovery has been well documented, but measures of levels of adoption, investments, and efficiencies gained from its use in clinical development have not yet been developed, captured or published. AI/ML use in clinical development is expected to increase, but its impact has not yet been systematically measured until now.

Methods: The Tufts Center for the Study of Drug Development conducted a global online survey among pharmaceutical and biotechnology companies, contract research organizations (CROs), and data and technology vendors servicing drug developers. The survey gathered 302 responses assessing levels of AI/ML implementation across 36 distinct clinical trial planning and design, trial execution, and regulatory submission activities. The survey collected data on US dollar investment, time savings, and challenges and opportunities of AI/ML use in clinical development.

Results: Approximately one-third of the sample (36.9%) was not yet using or implementing AI/ML across 36 design and planning, execution, and regulatory submission activities; another 30.3% was beginning their AI/ML implementation (or piloting), 22.1% was partially implementing (or moving beyond pilots), and on average only 10.7% had fully implemented AI/ML (i.e., uses AI in most trials employing a repeatable process).

Keywords: Adoption maturity; Artificial intelligence; Clinical development; Clinical trial design; Clinical trials; Generative AI; Innovation adoption; Machine learning; Protocol complexity; Protocol design; Quality by design; Real-world data; Research and development.

PubMed Disclaimer

Conflict of interest statement

Declarations. Supplemental Materials: Questionnaire is available upon request. Competing Interests: The authors declare no competing interests.

References

    1. U.S. Food and Drug Administration. Using artificial intelligence and machine learning in the development of drug and biological products: Discussion paper and request for feedback. 2023; Available from: https://www.fda.gov/media/167973/download
    1. U.S. Food and Drug Administration. Considerations for the use of artificial intelligence to support decision-making for drug and biological products: Guidance for industry and other interested parties. 2025; Available from: https://www.fda.gov/media/184830/download
    1. Vazquez J, Abdelrahman S, Byrne LM, Russell M, Harris P, Facelli JC. Using supervised machine learning classifiers to estimate likelihood of participating in clinical trials of a de-identified version of researchmatch. J Clin Transl Sci. 2021;5(1):e42. - DOI
    1. Zhang B, Zhang L, Chen Q, Jin Z, Liu S, Zhang S. Harnessing artificial intelligence to improve clinical trial design. Commun Med. 2023;3(1):1–3. - DOI
    1. Harrer S, Shah P, Antony B, Hu J. Artificial intelligence for clinical trial design. Trends Pharmacol Sci. 2019;40(8):577–91. - DOI - PubMed

LinkOut - more resources