REMEDIUMREMEDIUM1561-59362658-3534Joint-Stock Company Chicot177610.32687/1561-5936-2025-29-2-156-161Original ArticleUtilizing large language models in medical product market authorization dossier preparationKoshechkinKonstantin A.koshechkin_k_a@staff.sechenov.ruSpichakIrina V.spichak@gxp-academy.orgEurasian Academy of Good Practices, Moscow, Russia15122025215616117102025Copyright © 2025,2025Large Language Models (LLM) have emerged as powerful tools in various industries, promising to revolutionize processes through their advanced natural language processing capabilities. In the context of medical product market authorization dossier preparation, LLM offer the potential to streamline workflows, enhance efficiency, and improve compliance with regulatory standards. However, there are a number of obstacles to their adoption, including those pertaining to data security, output reliability, regulatory compliance, and the requirement for a strong infrastructure and qualified staff. This article explores the challenges and perspectives surrounding LLM usage in medical product dossier preparation, highlighting the importance of proactive measures, collaboration, and innovation in harnessing the full potential of LLM. Through a literature review, expert interviews, case studies, and analysis of regulatory guidelines, common themes, best practices, and potential solutions are identified. The findings underscore the critical role of collaboration among industry stakeholders, knowledge sharing, and the establishment of dedicated forums or consortia in overcoming barriers and driving collective innovation. Organizations can achieve efficient, compliant, and timely market authorization of medical goods, thereby enhancing patient outcomes and benefiting public health, by properly resolving hurdles and capitalizing on the benefits of LLM technology.large language modelsartificial intelligenceadministrative dossierregulatory requirementsgenerative neural networksбольшие языковые моделиискусственный интеллектрегистрационное досьерегуляторные требованиягенеративные нейронные сети1.Athaluri S. A., Manthena S. V., Kesapragada V. S.R.K.M. et al. Exploring the boundaries of reality: investigating the phenomenon of artificial intelligence hallucination in scientific writing through ChatGPT references. Cureus. 2023;15(4):e37432. DOI: 10.7759/cureus.374322.Sallam M. The utility of ChatGPT as an example of large language models in healthcare education, research and practice: systematic review on the future perspectives and potential limitations. medRxiv. 2023. P. 2023.02.19.23286155.3.Koshechkin K. A. Regulation of artificial intelligence in medicine. Patient-Oriented Medicine and Pharmacy. 2023:1(1):32—40.4.Patil P., Nrip N. K., Hajare A. et al. Artificial intelligence and tools in pharmaceuticals: an overview. Res. J. Pharm. Technol. 2023;16(4):2075—2082. DOI: 10.52711/0974-360X.2023.003415.Koshechkin K., Lebedev G., Tikhonova J. Regulatory information management systems, as a means for ensuring the pharmaceutical data continuity and risk management. Smart Innovation, Systems and Technologies. 2019;1:265—274.6.Habli I., Lawton T., Porter Z. Artificial intelligence in health care: accountability and safety. Bull. World Health Organ. 2020. Vol. 98, N 4. P. 251.7.Ke Y. H., Jin L., Elangovan K. et al. Development and testing of retrieval augmented generation in large language models — a case study report. arXiv preprint. 2024;arXiv:2402.01733. DOI: 10.2139/ssrn.47191858.Koshechkin K., Lebedev G., Tikhonova J. Regulatory information management systems, as a means for ensuring the pharmaceutical data continuity and risk management. In: Smart Innovation, Systems and Technologies. Springer; 2019;142:265—274.