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{205184,
        author = {LOGESH TG and MANIKANDAN S and JACQUELINE GRACEINA J and ABISHA D},
        title = {Artificial Intelligence in Pharmacovigilance: Current Applications, Challenges, and Future Directions},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {6142-6172},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205184},
        abstract = {Artificial Intelligence (AI) has been incorporated into the field of pharmacovigilance as a vital tool to improve drug safety profile identification, assessment, prediction, and prevention of Adverse Drug Reactions (ADRs). Existing pharmacovigilance system limitations such as underreporting of ADRs, delay in signal detection, and analysis of large and complicated data are overcome through the utilization of AI technologies such as Machine learning (ML), Deep Learning (DL), and Natural Language Processing (NLP) for effective analysis of large data from structured and unstructured health information data such as spontaneous reporting system, Electronic health record (EHR), clinical trials, real-world data (RWD) and more.
In pharmacovigilance based on AI, efficient detection of drug safety signals, higher accuracy of drug safety issues detection, real-time detection of ADRs and predictive analysis and the introduction of pharmacogenomics data help develop personalized pharmacovigilance to enable individual risk assessment and prevention. Advanced decision support system developed through AI enhance clinical decision making and data-driven knowledge provide regulatory process through relevant reports.
However, data quality, algorithmic bias, a lack of interpretability of ML model and ethic-privacy concerns should be solved for effective application. Future direction also shows development of explainable AI, integration with big data and genomics, standardization of global standards, the extension of patient-oriented pharmacovigilance framework. Pharmacists can play an important role for their validation on the prediction result of AI, assurance on data quality, and for clinical application.
AI promises to transform pharmacovigilance from a reactional system into a predictive, patient-centered system. Further research and development, regulation updates, and multi-disciplinary collaboration are important to bring the capabilities of AI into practical application.},
        keywords = {Artificial Intelligence, Pharmacovigilance, Adverse Drug Reaction, Machine Learning, Personalized medicine},
        month = {June},
        }