AI and innovation in clinical trials

Aarav Badani; Fabio Ynoe de Moraes; Philipp Vollmuth; Caroline Chung; Alireza Mansouri

doi:10.1038/s41746-025-02048-5

AI and innovation in clinical trials

Aarav Badani
, Fabio Ynoe de Moraes
, Philipp Vollmuth
, Caroline Chung
, Alireza Mansouri

Research output: Contribution to journal › Comment/debate › peer-review

Abstract

Clinical trials face persistent challenges in cost, enrollment, and generalizability. This perspective examines how artificial intelligence (AI), large language models (LLMs), adaptive trial designs, and digital twins (DTs) can modernize trial design and execution. We detail AI-driven eligibility optimization, reinforcement learning for real-time adaptation, and in silico DT modeling. Methodological, regulatory, and ethical hurdles are addressed, emphasizing the need for validated, scalable frameworks to enable responsible and widespread integration.

Original language	English (US)
Article number	683
Journal	npj Digital Medicine
Volume	8
Issue number	1
DOIs	https://doi.org/10.1038/s41746-025-02048-5
State	Published - Dec 2025

All Science Journal Classification (ASJC) codes

Medicine (miscellaneous)
Health Informatics
Computer Science Applications
Health Information Management

Access to Document

10.1038/s41746-025-02048-5

Cite this

@article{a36eb48260ad46f5b2d8ac4856cdd1c9,

title = "AI and innovation in clinical trials",

abstract = "Clinical trials face persistent challenges in cost, enrollment, and generalizability. This perspective examines how artificial intelligence (AI), large language models (LLMs), adaptive trial designs, and digital twins (DTs) can modernize trial design and execution. We detail AI-driven eligibility optimization, reinforcement learning for real-time adaptation, and in silico DT modeling. Methodological, regulatory, and ethical hurdles are addressed, emphasizing the need for validated, scalable frameworks to enable responsible and widespread integration.",

author = "Aarav Badani and \{de Moraes\}, \{Fabio Ynoe\} and Philipp Vollmuth and Caroline Chung and Alireza Mansouri",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2025.",

year = "2025",

month = dec,

doi = "10.1038/s41746-025-02048-5",

language = "English (US)",

volume = "8",

journal = "npj Digital Medicine",

issn = "2398-6352",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - AI and innovation in clinical trials

AU - Badani, Aarav

AU - de Moraes, Fabio Ynoe

AU - Vollmuth, Philipp

AU - Chung, Caroline

AU - Mansouri, Alireza

N1 - Publisher Copyright: © The Author(s) 2025.

PY - 2025/12

Y1 - 2025/12

N2 - Clinical trials face persistent challenges in cost, enrollment, and generalizability. This perspective examines how artificial intelligence (AI), large language models (LLMs), adaptive trial designs, and digital twins (DTs) can modernize trial design and execution. We detail AI-driven eligibility optimization, reinforcement learning for real-time adaptation, and in silico DT modeling. Methodological, regulatory, and ethical hurdles are addressed, emphasizing the need for validated, scalable frameworks to enable responsible and widespread integration.

AB - Clinical trials face persistent challenges in cost, enrollment, and generalizability. This perspective examines how artificial intelligence (AI), large language models (LLMs), adaptive trial designs, and digital twins (DTs) can modernize trial design and execution. We detail AI-driven eligibility optimization, reinforcement learning for real-time adaptation, and in silico DT modeling. Methodological, regulatory, and ethical hurdles are addressed, emphasizing the need for validated, scalable frameworks to enable responsible and widespread integration.

UR - https://www.scopus.com/pages/publications/105022218784

UR - https://www.scopus.com/pages/publications/105022218784#tab=citedBy

U2 - 10.1038/s41746-025-02048-5

DO - 10.1038/s41746-025-02048-5

M3 - Comment/debate

AN - SCOPUS:105022218784

SN - 2398-6352

VL - 8

JO - npj Digital Medicine

JF - npj Digital Medicine

IS - 1

M1 - 683

ER -

AI and innovation in clinical trials

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this