In Silico Medicine: The Regulatory Gap in AI-Driven Drug Development
Shivanand K Mutta, Naifa Faiz, Thasmitha N., Anushree A., Abdul Kalam Azad, Lavanya R., Vishwa S., Robinraja E.Introduction:
In silico medicine, which depends on computational modeling and simulation, is becoming more popular in drug discovery worldwide. Biomedical research is being rapidly transformed by Artificial Intelligence (AI), but there are risks associated with regulatory ambiguity. The integration of AI offers significant opportunities, but at the same time, it also introduces regulatory and ethical challenges. This review emphasizes the urgent need to establish ethical standards, illustrated with a few case studies.
Methods:
This article was conducted as a narrative review examining regulatory, ethical, and operational challenges associated with AI in drug development and in silico medicine. The review was based on analysis of published literature and regulatory guidance documents relevant to in silico clinical trials and AI-driven drug development. An iterative, non-protocol-driven literature search was conducted across databases, including PubMed and Web of Science, as well as official regulatory sources such as the United States Food and Drug Administration (USFDA) and the European Medicines Agency (EMA). Additional information was obtained from recognized international initiatives and other collaborative platforms, such as the Avicenna Alliance and In Silico World. These sources were consulted to better understand emerging consensus frameworks and regulatory harmonization efforts. The search terms included combinations of keywords such as “in silico medicine,” “computational modeling,” “Model-Informed Drug Development,” "AI in drug discovery,” “AI in clinical trials,” “regulatory frameworks,” United States Food and Drug Administration (“USFDA”), European Medicines Agency (“EMA”), “global harmonization,” and “ethical challenges.” Articles and documents published between 2020 and 2026 were prioritized to capture recent scientific and regulatory developments. Sources included peer-reviewed journal articles, regulatory guidelines, white papers, consensus reports, and policy documents relevant to in silico medicine and regulatory evaluation. Since this review did not follow a predefined systematic review protocol, some relevant studies may not have been captured.
Results:
The review identified key challenges involving model validation and credibility, transparency, data bias, patient privacy, dual-use risks, and accountability. The USFDA and EMA have introduced initiatives addressing AI and modeling and simulation, but standardized validation criteria, acceptance thresholds, and globally harmonized regulatory pathways still remain limited.
Discussion:
Current regulatory approaches remain largely principle-based. Regulations have not fully addressed the rapidly evolving nature of AI-driven systems. Greater emphasis on lifecyclebased validation, transparency, human oversight, and adaptive regulatory mechanisms is needed to support safe and reliable implementation.
Conclusion:
AI-driven in silico medicine has all the potential to improve drug development, but regulatory and ethical gaps must be addressed. International harmonization and adaptive governance will be essential to ensure responsible innovation without standing in the way of scientific progress.