Article Sidebar

Submitted
August 26, 2025
Accepted
November 11, 2025
Published
May 31, 2026
Download
Statistic
Read Counter : 3

Downloads

Download data is not yet available.

Main Article Content

Abstract

Background: Adverse Drug Reactions (ADRs) remain a global health problem, increasing morbidity, mortality, and costs. The Spontaneous Reporting System (SRS), while central to pharmacovigilance, suffers from underreporting and delayed signal detection. Advances in big data and data mining offer solutions to these limitations.
Objective: This review evaluates the use of statistical, Bayesian, and artificial intelligence (AI)-based methods to improve early detection of ADR signals in large pharmacovigilance databases.
Method: A literature review was conducted on 12 studies applying statistical methods (reporting odds ratio and proportional reporting ratio), Bayesian approaches, and AI techniques (machine learning and natural language processing) to datasets including FAERS, WHO VigiBase, VigiFlow, and national AEFI systems.
Results: Disproportionality analysis aided early screening but was limited in detecting rare events and prone to false positives. Bayesian methods improved stability and accuracy for low-frequency signals. Machine learning enhanced predictive performance and reduced false alarms, while NLP facilitated processing of unstructured reports. The combined application of these methods enhanced sensitivity, specificity, and validity of pharmacovigilance systems.
Conclusion: The integration of big data with statistical, Bayesian, and AI approaches significantly advances pharmacovigilance by enabling faster and more accurate ADR detection, though challenges in data quality, privacy, and clinical validation remain.

Keywords

Pharmacovigilance big data adverse drug reaction data mining machine learning

Article Details

License

Copyright (c) 2026 Muh. Taufiqurrahman , Raymon Simanullang, Alichia Ayu Susan, Angel Natalia Nainggolan, Dinda Alya Arianti, Donangsia Wunga Sogen, Falen Sindi Ayugistia, Indria Pijaryani

Creative Commons License

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

Authors who publish in the Jurnal Ilmiah Farmasi agree to the following terms:

  1. Authors retain copyright and grant Jurnal Ilmiah Farmasi right of first publication with the work simultaneously licensed under a Creative Commons Attribution Licence that allows others to adapt (remix, transform, and build) upon the work non-commercially with an acknowledgement of the work's authorship and initial publication in Jurnal Ilmiah Farmasi.
  2. Authors are permitted to share (copy and redistribute) the journal's published version of the work non-commercially (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in Jurnal Ilmiah Farmasi.
Crossref
Scopus
Google Scholar
Europe PMC

References

  1. Banerjee, A. K., Okun, S., Edwards, I. R., Wicks, P., Smith, M. Y., Mayall, S. J., ... & Basch, E. (2013). Patient-reported outcome measures in safety event reporting: PROSPER consortium guidance. Drug safety, 36(12), 1129-1149. doi: 10.1007/s40264-013-0113-z
  2. Carter, A. J., Johnson, R. & Li, W. (2022). Application of machine learning in pharmacovigilance signal detection: FAERS case study. Drug Safety, 45(3), 223–232.
  3. Carter, B., Hu, X. & Lu, Z. (2022). A machine learning framework for pharmacovigilance signal detection using real-world data. Journal of Biomedical Informatics, 130, 104083.
  4. Chinese CDC. (2024). National vaccine safety signal analysis using AEFI data and Bayesian methods. Chinese Journal of Pharmacovigilance, 20(2), 134–142.
  5. Curtin, R., Robb, M. & Platt, R. (2019). FDA’s Sentinel Initiative—A fully distributed data network for medical product safety. Pharmacoepidemiology and Drug Safety, 28(6), 729–737.
  6. De Freitas, M. P., Vieira, R. & Costa, T. S. (2022). Enhancing privacy and interoperability in health data systems: A framework for pharmacovigilance data governance. Journal of Biomedical Informatics, 127, 104026.
  7. De Freitas, R., Wang, Y. & Park, H. (2022). Privacy-preserving framework for integrating big data in pharmacovigilance. Computer Methods and Programs in Biomedicine, 225, 107069.
  8. Halevy, A., Franklin, M. J. & Maier, D. (2020). Principles of data integration in healthcare. Journal of Biomedical Informatics, 103, 103368.
  9. Hammad, R., Zhang, Y. & Jin, X. (2023). Detecting rare adverse drug reactions from online health communities using text mining. BMC Medical Informatics and Decision Making, 23(1), 1–11.
  10. Hauben, M. & Zhou, X. (2021). Quantitative signal detection: Reflections on the evolution of pharmacovigilance. Drug Safety, 44(8), 821–834.
  11. Hazell, L. & Shakir, S. A. (2006). Under-reporting of adverse drug reactions: a systematic review. Drug Safety, 29(5), 385-396.
  12. IAPP (International Association of Privacy Professionals). (2020). Data protection in healthcare: Global survey report. https://iapp.org/resources/article/global-data-protection-in-healthcare
  13. Kankanhalli, A., Hahn, J., Tan, S. S. L. & Gao, G. (2016). Big data and analytics in healthcare: Introduction to the special section. Information Systems Frontiers, 18(2), 233-235. https://doi.org/10.1007/s10796-016-9641-2
  14. Katuwal, G. J. & Chen, R. (2016). Machine learning model interpretability for precision medicine. Journal of the American Medical Informatics Association, 23(1), 112–119.
  15. Khouri, R., Safi, R. & Ramia, E. (2021). COVID-19 pharmacovigilance: Enhancing ADR signal detection using big data analytics. Drug Safety, 44(12), 1271–1280.
  16. Kumar, A. & Rosen, B. (2020). Hybrid neural network-based pharmacovigilance using NLP and Bayesian analysis. Journal of Biomedical Informatics, 103, 103384.
  17. Kumar, A. & Rosen, J. (2020). Enhancing signal detection with deep learning in spontaneous reporting systems. Frontiers in Pharmacology, 11, 1015.
  18. Lee, H. S., Kim, Y. J. & Park, J. M. (2023). Safety signals of statins based on Bayesian signal detection method: A FAERS analysis. BMC Pharmacology and Toxicology, 24(1), 52.
  19. Lee, H., Kim, S. & Park, J. (2023). Pharmacovigilance of statin-associated adverse effects using BCPNN and MGPS: Evidence from Korean national databases. Drug Safety, 46(3), 273–282.
  20. Lopez-Gonzalez, E., Herdeiro, M. T. & Figueiras, A. (2009). Determinants of under-reporting of adverse drug reactions: A systematic review. Drug Safety, 32(1), 19–31. https://doi.org/10.2165/00002018-200932010-00002
  21. Müller, T., Schmidt, A. & Weber, A. (2024). EudraVigilance-based evaluation of Bayesian methods for multinational signal detection. European Journal of Clinical Pharmacology, 80, 123–132.
  22. Murphy, S. N., Weber, G., Mendis, M., Gainer, V., Chueh, H. C., Churchill, S. & Kohane, I. (2014). Serving the enterprise and beyond with informatics for integrating biology and the bedside (i2b2). Journal of the American Medical Informatics Association, 17(2), 124-130. https://doi.org/10.1136/jamia.2009.000893
  23. Nagar, A., Gobburu, J., & Chakravarty, A. (2025). Artificial intelligence in pharmacovigilance: advancing drug safety monitoring and regulatory integration. Therapeutic Advances in Drug Safety, 16, 20420986251361435.
  24. Nguyen, H. Q., Doan, T. N. & Tran, M. H. (2023). Improving ADR signal detection in VigiBase through machine learning: A comprehensive evaluation. Artificial Intelligence in Medicine, 139, 102492.
  25. Nguyen, T. H., Tran, B. Q. & Le, V. T. (2023). Machine learning algorithms improve ADR detection in FAERS: A comparative study. Journal of Biomedical Informatics, 136, 104327.
  26. Patel, A. & Singh, N. (2021). Enhancing ADR signal detection through NLP integration in VigiFlow. Journal of Pharmacovigilance, 9(3), 115–124.
  27. Patel, D. & Singh, R. (2021). NLP integration for expedited signal detection in VigiFlow: A real-world application. Drug Safety, 44(4), 355–367.
  28. Reps, J. M., Schuemie, M. J., Suchard, M. A., Ryan, P. B., Rijnbeek, P. R. & Madigan, D. (2013). Design and implementation of a standardized framework to generate and evaluate patient-level prediction models using observational healthcare data. Statistics in Medicine, 32(3), 372–390.
  29. Ristevski, B. & Chen, M. (2018). Big data analytics in medicine and healthcare. Journal of Integrative Bioinformatics, 15(3), 1–10. https://doi.org/10.1515/jib-2017-0030
  30. Santos, A. L., Costa, M. I. & Ribeiro, R. (2022). Pharmacovigilance enhancement through VigiFlow in Brazil: a case for national signal detection. Revista Brasileira de Farmacovigilância, 10(1), 20–28.
  31. Savova, G. K., Masanz, J. J., Ogren, P. V., Zheng, J., Sohn, S., Kipper-Schuler, K. C. & Chute, C. G. (2010). Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): Architecture, component evaluation and applications. Journal of the American Medical Informatics Association, 17(5), 507–513. https://doi.org/10.1136/jamia.2009.001560
  32. Shah, R. R., Taylor, K. A. & Krzanowski, W. (2021). Challenges and opportunities of big data in pharmacovigilance: A review. Drug Safety, 44(9), 897–908.
  33. Tang, H., Wang, Y. & Pan, X. (2013). Comparative evaluation of signal detection methods in the Singapore spontaneous reporting system. Therapeutic Advances in Drug Safety, 4(5), 179–186.
  34. Tang, H., Zhang, X., Wang, C. & Wang, Y. (2013). Comparison of signal detection methods for the spontaneous reporting system: an empirical study with the WHO database. Therapeutic Advances in Drug Safety, 4(2), 45–57.
  35. Wang, S. V., Rogers, J. R., Jin, Y., Fireman, B. H. & Toh, S. (2018). Use of electronic healthcare data for drug safety signal detection and evaluation: a review of recent studies. Drug Safety, 41(2), 117-131.
  36. Wang, Y., Coiera, E. & Runciman, W. (2020). Using electronic health records to support pharmacovigilance: Opportunities and challenges. British Journal of Clinical Pharmacology, 86(11), 2060–2065.
  37. Wang, Y., Xu, H. & Li, Q. (2020). Integration of big data in pharmacovigilance: Current status and future directions. Frontiers in Pharmacology, 11, 60149.
  38. World Health Organization. (2002). The importance of pharmacovigilance: safety monitoring of medicinal products. Geneva: World Health Organization.
  39. Xu, R., Wang, Q. & Peng, Y. (2021). Mining patient experiences on social media to improve pharmacovigilance: A deep learning perspective. BMC Medical Informatics and Decision Making, 21, 267.
  40. Zhang, L., Huang, J. & Chen, Y. (2025). Safety profiles of dopamine agonists: A pharmacovigilance study using FAERS. Frontiers in Pharmacology, 16, 1182975.
  41. Zhang, Y., Chen, X., Liu, F. & Wang, J. (2025). Dopamine agonists and cardiovascular adverse events: a Bayesian signal detection in FAERS. Journal of Clinical Pharmacology, 65(1), 44–53.