The role of digital technologies in the pharmacovigilance system

Background. Dozens of drugs enter the pharmaceutical market annually; their complete safety profi le, however, is established not during pre-registration clinical trials but through years of post-marketing surveillance of heterogeneous patient cohorts. Pharmacovigilance provides continuous «benefit/risk» ratio monitoring throughout the full lifecycle of a medicinal product; yet the volume of incoming safety data continues to grow, generating an analytical burden that traditional methods address only partially. Under these conditions, artificial intelligence (AI), machine learning, and natural language processing methods are being considered as scalable instruments for pharmacovigilance data analysis.

Objective. To consolidate and systematize current data on the application of digital technologies in pharmacovigilance, identify existing gaps, and outline directions for their resolution.

Materials and methods. A narrative review of scientifi c publications, regulatory documents, and methodological guidelines on the application of digital technologies in the pharmaceutical sector was conducted. The search was performed in PubMed, Scopus, Web of Science, eLIBRARY, and ConsultantPlus databases; the time frame covers the period from 2000 to 2026.

Results. It was established that the full-scale implementation of AI methods is currently limited by a number of factors: heterogeneity and insufficient standardisation of input data, inadequate interpretability of algorithms in the regulatory context, the absence of agreed validation procedures for AI tools, and the unresolved state of the regulatory framework across EAEU member states. To address the identified gaps, the need for a transition from a task-oriented to a systemic approach was substantiated; for example, an approach encompasses the full lifecycle of a medicinal product and provides for coordination at the technological, organisational, and regulatory levels.

Conclusion. Digital technologies demonstrate considerable potential for improving the efficiency of drug safety monitoring. It can be assumed that overcoming existing methodological and regulatory barriers requires coordinated efforts of the scientific community, regulatory authorities, and marketing authorisation holders towards the development of a unifi ed system of AI tool validation standards, ensuring algorithmic transparency, compliance with GPp requirements, and reproducibility of results within the applicable legal framework.

1. Federal Law No. 61-FZ of April 12, 2010 «On the Circulation of Medicines». (In Russ.)

2. Decision of the Council of the Eurasian Economic Commission No. 81 of May 19, 2022 «On Amendments to the Good Pharmacovigilance Practice Rules of the Eurasian Economic Union». (In Russ.).

3. Pharmacovigilance / edited by Kolbin A. S., Zyryanova S. K., Belousov D. Yu. – 2nd ed. (revised and supplemented). – Moscow: OKI Publishing House: Buki Vedi, 2025. – 276 p. (In Russ.).

4. Haerian K, Varn D, Vaidya S, et al. Detection of pharmacovigilance-related adverse events using electronic health records and automated methods. Clin Pharmacol Ther. 2012 Aug;92(2):228-34. doi: 10.1038/clpt.2012.54

5. Davis SE, Zabotka L, Desai RJ, et al. Use of Electronic Health Record Data for Drug Safety Signal Identification: A Scoping Review. Drug Saf. 2023 Aug;46(8):725-742. doi: 10.1007/s40264-023-01325-0

6. Pontes H, Clément M, Rollason V. Safety signal detection: the relevance of literature review. Drug Saf. 2014 Jul;37(7):471-9. doi: 10.1007/s40264-014-0180-9. PMID: 24895178

7. Sorbello A, Ripple A, Tonning J, et al. Harnessing scientific literature reports for pharmacovigilance. Prototype soft ware analytical tool development and usability testing. Appl Clin Inform. 2017 Mar 22;8(1): 291-305. doi: 10.4338/ACI-2016-11-RA-0188

8. Palffy E, Lewis DJ. Real-World evidence revelations: Th e potential of patient support programmes to provide data on medication usage. PLoS One. 2024 Feb 8;19(2):e0295226. doi: 10.1371/journal.pone.0295226

9. Farooq H, Niaz JS, Fakhar S, Naveed H. Leveraging digital media data for pharmacovigilance. AMIA Annu Symp Proc. 2021 Jan 25;2020:442-451.

10. Stergiopoulos S, Fehrle M, Caubel P, et al. Adverse Drug Reaction Case Safety Practices in Large Biopharmaceutical Organizations from 2007 to 2017: An Industry Survey. Pharmaceut Med. 2019 Dec;33(6):499-510. doi: 10.1007/s40290-019-00307-x. Erratum in: Pharmaceut Med. 2020 Feb;34(1):81. doi: 10.1007/s40290-019-00319-7

11. Pharmaceutical industry 4.0. Digital transformation / edited by A.L. Khokhlov, N.V. Pyatigorskaya. – Moscow: OKI Publishing House, 2025. – 312 p.: color ill. 37. ISBN 978-5-4465-4468-4.

12. Federal Law No. 429-FZ of December 22, 2014 «On Amendments to the Federal Law On the Circulation of Medicines». (In Russ.).

13. Davies EC, Green CF, Taylor S, et al. Adverse drug reactions in hospital in-patients: a prospective analysis of 3695 patient-episodes. PLoS One. 2009;4(2):e4439. doi: 10.1371/journal.pone.0004439

14. Lepakhin V.K., Olefi r Yu.V., Merkulov V.A., Bunyatyan N.D., Romanov B.K. et al. History of the establishment and development of the drug regulatory system in Russia. Bulletin of the Scientific Center for Expertise of Medical Products. 2016;1:3–10. (In Russ.)/

15. Karpov O.E., Khramov A.E. Information technologies, computing systems and artificial intelligence in medicine. M.: DPK Press, 2022. 480 p. (In Russ.).

16. Poroikov V.V. Computer-aided drug design: from the search for new pharmacological substances to systems pharmacology. Biomedical chemistry. 2020;66(1):30–41. (In Russ.)

17. Decree of the President of the Russian Federation No. 490 of October 10, 2019 (as amended on February 15, 2024) «On the development of artificial intelligence in the Russian Federation». (In Russ.).

18. Federal Law No. 258-FZ of July 31, 2020 «On Experimental Legal Regimes in the Field of Digital Innovations in the Russian Federation». (In Russ

19. PNST 961-2024. Artificial intelligence systems in healthcare. Ethical aspects. (In Russ.).

20. Code of Ethics for the Application of Artificial Intelligence in Healthcare. Version 2.1 (approved by the Interdepartmental Working Group under the Ministry of Health of Russia, Minutes No. 90/18-0/117 of February 14, 2025). (In Russ.).

21. Amann J, Blasimme A, Vayena E, et al; Precise4Q consortium. Explainability for artificial intelligence in healthcare: a multidisciplinary perspective. BMC Med Inform Decis Mak. 2020 Nov 30;20(1):310. doi: 10.1186/s12911-020-01332-6

22. Sadovskaya L.D., Timofeeva S.V. Modern technologies in pharmacovigilance. Youth Innovation Bulletin. 2025;14(S1):273–276. (In Russ.)

23. Loginova A.E. Modern information technologies in the control and supervision of drug circulation. Bulletin of the Lobachevsky University of Nizhny Novgorod. 2020;3:126- 131. (In Russ.)

24. Order of the Federal Service for Health Surveillance No. 3518 of June 17, 2024 «On Approval of the Procedure for Pharmacovigilance of Medicinal Products for Medical Use». (In Russ.).

25. Decision of the Council of the Eurasian Economic Commission No. 87 of November 3, 2016 (as amended on May 19, 2022) «On Approval of the Good Pharmacovigilance Practice Rules of the Eurasian Economic Union». (In Russ.).

26. Klabukova D.L., Davydovskaya M.V. Implementation of the international MedDRA terminology in pharmacovigilance practice in the Russian Federation. Moscow Medicine. 2020; 3:64. (In Russ.)

27. Shubnikova E.V. Post-registration pharmacovigilance: a review of open sources of drug safety data. Safety and risk of pharmacotherapy. 2024; 12(3):309–330. (In Russ.)

28. Hazell L, Shakir SA. Under-reporting of adverse drug reactions: a systematic review. Drug Saf. 2006;29(5):385-96. doi: 10.2165/00002018-200629050-00003

29. Imbrici P, De Bellis M, Liantonio A, De Luca A. Investigating the Benefit-Risk Profi le of Drugs: From Spontaneous Reporting Systems to Real-World Data for Pharmacovigilance. Methods Mol Biol. 2025; 2834:333-349. doi: 10.1007/978-1-0716-4003-6_16

30. Salas M, Petracek J, Yalamanchili P, et al. Th e Use of Artificial Intelligence in Pharmacovigilance: A Systematic Review of the Literature. Pharmaceut Med. 2022 Oct;36(5):295-306. doi: 10.1007/s40290-022-00441-z

31. Mishra HP, Gupta R. Leveraging Generative AI for Drug Safety and Pharmacovigilance. Curr Rev Clin Exp Pharmacol. 2025;20(2):89-97. doi: 10.2174/0127724328311400240823062829

32. Loginovskaya O.A., Kolbatov V.P., Sukhov R.V., et al. New technologies in electronic pharmacovigilance systems for marketing authorisation holders. Safety and risk of pharmacotherapy. 2022;10(3):230–239. (In Russ.)

33. Stanekova V, Inglis JM, Lam L, et al. Improving the performance of machine learning penicillin adverse drug reaction classification with synthetic data and transfer learning. Intern Med J. 2024 Jul;54(7):1183-1189. doi: 10.1111/imj.16360

34. Samsonova K.I. Safety profile of fluoroquinolones and medication errors in their use according to the national spontaneous reporting database: abstract of PhD thesis. (In Russ.).

35. Kawazoe Y, Tsuchiya M, Shimamoto K, et al. Natural language processing of electronic medical records identifi es cardioprotective agents for anthracycline induced cardiotoxicity. Sci Rep. 2025 Feb 24;15(1):6678. doi: 10.1038/s41598-025-91187-6

36. Kawazoe Y, Shibata D, Shinohara E, et al. A clinical specific BERT developed using a huge Japanese clinical text corpus. PLoS One. 2021 Nov 9;16(11):e0259763. doi: 10.1371/journal.pone.0259763

37. Kim Y, Kim JH, Lee JM, et al. A pre-trained BERT for Korean medical natural language processing. Sci Rep. 2022 Aug 16;12(1):13847. doi: 10.1038/s41598-022-17806-8. Erratum in: Sci Rep. 2023 Jun 7;13(1): 9290. doi: 10.1038/s41598-023-36519-0

38. Lieberwirth JK, Mittermaier M, Stern AD. Challenges and potential of using digital biomarkers in healthcare and clinical trials. Commun Med (Lond). 2026 Feb 21;6(1):151. doi: 10.1038/s43856-026-01450-8

39. FDA-NIH Biomarker Working Group. BEST (Biomarkers, EndpointS, and Other Tools) Resource [Электронный ресурс]. Silver Spring: Food and Drug Administration (US); Bethesda: National Institutes of Health (US), 2016. Доступно по: https://www.ncbi.nlm.nih.gov/books/NBK326791

40. Noguchi Y, Tachi T, Teramachi H. Detection algorithms and attentive points of safety signal using spontaneous reporting systems as a clinical data source. Brief Bioinform. 2021 Nov 5;22(6):bbab347. doi: 10.1093/bib/bbab347

41. Kuchkarov T.S. On methods and tools for big data analysis. Economy and Society. 2023;12(115)-2:837-841 (In Russ.)

42. Cherkas Y, Ide J, van Stekelenborg J. Leveraging Machine Learning to Facilitate Individual Case Causality Assessment of Adverse Drug Reactions. Drug Saf. 2022 May;45(5):571-582. doi: 10.1007/s40264-022-01163-6

43. Bergman E, Dürlich L, Arthurson V, et al. BERT based natural language processing for triage of adverse drug reaction reports shows close to human-level performance. PLOS Digit Health. 2023 Dec 6;2(12):e0000409. doi: 10.1371/journal.pdig.0000409

44. Aggarwal C, Bouneff ouf D, Samulowitz H et al. How can AI automate end-to-end data science? arXiv preprint arXiv:1910.14436. 2019.

45. Bate A, Michael Tregunno P. How is AI developing in pharmacovigilance? Ther Adv Drug Saf. 2026 Jan 30;17:20420986251412773. doi: 10.1177/20420986251412773

46. Fusaroli M, Salvo F, Begaud B, et al. The REporting of A Disproportionality Analysis for DrUg Safety Signal Detection Using Individual Case Safety Reports in PharmacoVigilance (READUS-PV): Explanation and Elaboration. Drug Saf. 2024 Jun;47(6):585-599. doi: 10.1007/s40264-024-01423-7.

47. Vvedenskaya E.V. Digital agents in medicine: new opportunities and challenges. Ethical Thought. 2024;1:115-128. (In Russ.)

48. Milne-Ives M, de Cock C, Lim E, et al. The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review. J Med Internet Res. 2020 Oct 22;22(10):e20346. doi: 10.2196/20346

49. Kiragga AN, Iddi S, Walekhwa AW, et al. Data science without borders: bridging the divide in data science capacity across African health institutions. Front Public Health. 2025 Dec 5;13:1695907. doi: 10.3389/fpubh.2025.1695907

50. Ball R, Dal Pan G. "Artificial Intelligence" for Pharmacovigilance: Ready for Prime Time? Drug Saf. 2022 May;45(5):429-438. doi: 10.1007/s40264-022-01157-4

51. Nagar A, Gobburu J, Chakravarty A. Artificial intelligence in pharmacovigilance: advancing drug safety monitoring and regulatory integration. Ther Adv Drug Saf. 2025 Jul 31;16:20420986251361435. doi: 10.1177/20420986251361435