Abstract Over the past decade, Big Data and Artificial Intelligence (AI) have emerged as transformative forces in healthcare, particularly in pharmaceutical policy, regulation, and drug safety surveillance. These technologies enable the systematic collection, integration, and analysis of large-scale and heterogeneous data, thereby strengthening evidence-based decision-making across the pharmaceutical lifecycle. International experience demonstrates that the integration of AI and Big Data supports early detection of adverse drug reactions (ADRs), enhances pharmacovigilance systems, automates regulatory processes, and accelerates drug discovery and development. AI-driven methods, including machine learning and natural language processing (NLP), facilitate the identification of latent patterns and risk signals from diverse data sources such as clinical trials, Real World Evidence (RWE), electronic health records, and spontaneous reporting systems.
Despite these global advances, the application of AI and Big Data within Mongolia’s pharmaceutical policy and regulatory framework remains limited. Key challenges include fragmented and poorly integrated data sources, insufficient data standardization, underdeveloped information technology infrastructure, limited human resource capacity, and gaps in legal and ethical governance. International initiatives offer valuable reference models for addressing these challenges. The World Health Organization’s VigiBase employs AI and NLP techniques to identify global ADR trends, the U.S. Food and Drug Administration’s Sentinel Initiative integrates RWE to support proactive drug safety monitoring, and the Republic of Korea’s Disease Control and Prevention Agency has implemented an NLP-based pharmacovigilance system for automated risk detection.
This study aims to assess the applicability of Big Data and AI in Mongolia’s pharmaceutical policy and regulatory system through a comparative analysis of international best practices and the identification of key implementation gaps. The findings emphasize the need for integrated data systems, harmonized standards, localized AI application models, and robust regulatory and ethical frameworks. Overall, the study highlights the potential of Big Data and AI to modernize pharmaceutical policy and regulation in Mongolia and provides evidence-based directions for sustainable implementation aligned with international best practices.

Introduction: Systematic analysis of adverse drug reactions (ADRs) is essential for enhancing drug safety policies in Mongolia. This study analyzed ADR patterns and reporting trends between 2020 and 2025. Methods: This study employed a retrospective cross-sectional design using ADR reports recorded between 2020 and 2025. The dataset included variables such as drug name, drug classification, clinical manifestations of ADRs, and affected organ systems. Data were entered into Microsoft Excel and analyzed using SPSS version 25. Drugs were classified according to the World Health Organization (WHO) Anatomical Therapeutic Chemical (ATC) classification system, and ADRs were analyzed at the organ system level. Conclusion Analysis of 634 reported adverse drug reactions (ADRs) in Mongolia from 2020 to 2025 showed that antibiotics, particularly third-generation cephalosporins, accounted for the majority of ADRs. According to Hartwig’s severity assessment, 70–80% of ADRs were mild, 15–20% moderate, and 5% severe, indicating that while most reactions did not require intervention, a small proportion could be lifethreatening. These findings highlight the need to strengthen pharmacovigilance systems, improve ADR reporting, and enhance the quality of data in Mongolia.