Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190149,
        author = {TOUFIQUE AHMED MOLLAH and MAHMUDUR RAHAMAN MALLICK and SUBHODIP SAHA},
        title = {Redefining Drug Safety: The Role of Artificial Intelligence in Pharmacovigilance},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {1754-1764},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190149},
        abstract = {Background: The current state and forecast: Global Pharmacovigilance Market, which is expected to see a paradigm shift, reaching a projected market value - 25.37 billion USD with an annual growth rate - 42.81% within the AI market sector. According to estimates, the no. of ADR (Adverse Drug Reaction) reports is expected an exponential increase due to support organizations, various Social Media Platforms, and Electronic Health Records (EHR), making manual analysis impossible.
Objective: Our paper introduces an overview of current applications and implementations of Artificial Intelligence (AI) within the field of drug safety, from its statistical roots associated with data mining to the current methods utilizing Large Language Models (LLMs).
Scope: It covers various AI/ML technologies like, Natural Language Processing (NLP), its use within case intake automation, use and implementation of Machine Learning (ML) Models such as Random Forrest and Bayesian Networks within signal detection analysis, and proposes and explains current and potential applications for Generative AI within risk management documentation. Results: Industry cases and current implementation examples suggest that AI/ML contributes towards a reduction of up to 60% within case intake analysis and towards an increased sensitivity factor within signal detection compared with traditional disproportionality analysis methods.
Conclusion: The industry is undergoing a shift from the ‘compliance-driven’ PV function towards a ‘data-driven’ safety and risk management paradigm. However, implementing this on a global scale is facing important challenges and obstacles such as Algorithmic Explainability (XAI), Data Biases, and issues within regulatory acceptances.},
        keywords = {Pharmacovigilance, Artificial Intelligence, Signal Detection, Generative AI, PV.},
        month = {February},
        }