Regulatory Adoption of AI, ML, Computational Modeling & Simulation in In-Silico Clinical Trials for Medical Devices: A Systematic Review

This study explores the revolutionary potential of in-silico clinical trials (ISCTs) in medical device development, emphasizing the integration of computational modeling and simulation (CM&S), artificial intelligence (AI), and machine learning (ML). It evaluates regulatory advancements by the FD...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Therapeutic innovation & regulatory science
Hlavní autori: De, Arindam, Lohani, Alka
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Switzerland 07.10.2025
Predmet:
USFDA
EMA
Computer modelling and simulation
Medical device
Artificial intelligence
In-silico clinical trials
PMDA
ISSN:2168-4790, 2168-4804, 2168-4804
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This study explores the revolutionary potential of in-silico clinical trials (ISCTs) in medical device development, emphasizing the integration of computational modeling and simulation (CM&S), artificial intelligence (AI), and machine learning (ML). It evaluates regulatory advancements by the FDA, EMA, and PMDA, identifies barriers to global ISCTs adoption, and proposes strategies to enhance credibility, standardization, and ethical alignment. A systematic review following PRISMA 2020 guidelines reviewed 72 studies (2014-2025) from Scopus, PubMed, Web of Science, and regulatory reports. Excluding non-regulatory or non-medical device research, inclusion criteria emphasized ISCTs technologies and regulatory frameworks. ISCTs employ CM&S techniques, including finite element analysis, computational fluid dynamics, and agent-based modeling, to simulate medical device performance and generate synthetic patient cohorts, thereby reducing costs and addressing ethical concerns. AI/ML further enhances predictive accuracy and optimizes trial design. Regulatory agencies have developed advanced frameworks like the FDA's model credibility and AI guidelines, the EMA promotes its 3R Guidelines, and the PMDA supports computational validation through dedicated subcommittees. Key challenges include regulatory fragmentation, limited data accessibility, computational complexity, and ethical risks such as algorithmic bias. Proposed solutions include global harmonization of regulatory guidelines, explainable AI implementation, federated learning adoption for secure data collaboration, and hybrid trial designs that integrate ISCTs with traditional methodologies. ISCTs can revolutionize the development and assessment of medical devices. Standardized validation frameworks, regulatory standards, and interdisciplinary cooperation are required to address these issues. Clear guidelines must ensure ISCTs legitimacy and acceptance and promote safer and ethical medical innovations.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
ObjectType-Review-3
content type line 23
ISSN:2168-4790
2168-4804
2168-4804
DOI:10.1007/s43441-025-00871-2