Micheal Abimbola Oladosu1*, Moses Adonduah Abah2, Florence Nkemehule3, Isaac Oghenenyerhovwon Imitini4, Prince Eyebira Agbajor4, Emonena Sikale Godwin4, Olaide Ayokunmi Oladosu5, Shola David Omoseeye6 and Sikiru Olayinka Aleshe7

 1Department of Chemical Sciences, Faculty of Science, Anchor University, Ayobo -Ipaja, Lagos, Nigeria

2Department of Biochemistry, Faculty of Biosciences, Federal University Wukari, Taraba State, Nigeria

3Department of Pharmacognosy, Faculty of Pharmacy, University of Lagos, Idi-Araba, Lagos State, Nigeria

4Department of Computer Science, College of Science, Federal University of Petroleum Resources, Effurun, Delta State, Nigeria

5Department of Computer Science, Faculty of Science and Technology, Babcock University, Ilisan-Remo, Ogun State, Nigeria

6Department of Anatomy, Faculty of Basic Medical Sciences, College of Medicine, Ekiti State University, Ado Ekiti, Ekiti State, Nigeria

7Department of Biochemistry, Faculty of Basic Medical Sciences, Olabisi Onabanjo University, Ago-Iwoye, Ogun State, Nigeria

() Corresponding Author

 Received: April 22, 2026/ Revised: May 22, 2026/Accepted: June 1, 2026

 Abstract

 The integration of artificial intelligence (AI) into drug delivery systems represents a paradigm shift in pharmaceutical science, promising unprecedented personalization, precision, and efficiency. However, this rapid integration has outpaced the development of ethical frameworks and regulatory oversight, creating significant challenges for clinical translation. This scoping review systematically maps the landscape of challenges and ethical considerations associated with AI-driven drug delivery systems, with particular emphasis on barriers to clinical translation. A structured literature search of PubMed, Scopus, Web of Science, and EMBASE was conducted for articles published between January 2020 and December 2024. Studies addressing AI applications in drug delivery, pharmacokinetics, nanoparticle formulation, or closed-loop dosing systems in relation to ethics, regulation, or clinical implementation were included. Thirty-two studies met inclusion criteria. Five overarching challenge domains were identified: algorithmic bias and health inequity, model transparency and explainability, data privacy and governance, regulatory fragmentation, and accountability in AI-assisted clinical decisions. Persistent gaps exist in multi-ethnic training datasets, post-market surveillance frameworks, and patient consent paradigms for AI-enabled therapies. Safe and equitable clinical translation of AI-driven drug delivery requires coordinated international regulatory harmonization, mandatory algorithmic auditing, explainability standards, and inclusive dataset policies. Interdisciplinary collaboration between pharmaceutical scientists, clinicians, ethicists, regulators, and patients is essential.

Keywords: artificial intelligence; drug delivery; ethics; clinical translation; algorithmic bias; explainability; regulatory framework; nanoparticle; personalized medicine

How to cite this article

Oladosu, M. A., Abah, M. A., Nkemehule, F., Imitini, I. O., Agbajor, P. E., Godwin, E. S., Oladosu, O. A., Omoseeye, S. D., & Aleshe, S. O. (2026). Challenges and ethical considerations in AI-driven drug delivery: A scoping review of implications for clinical translation. Science Archives, 7(2), 86–94. https://doi.org/10.47587/SA.2026.7207

This work is licensed under a Creative Commons Attribution 4.0 International License

 

View Details