Artificial Intelligence dalam Digital Pharmacovigilance untuk Deteksi Reaksi Obat yang Tidak Diinginkan: Tinjauan Naratif
DOI:
https://doi.org/10.63004/hrji.v5i1.2033Keywords:
artificial intelligence, digital pharmacovigilance, keamanan obat, adverse drug reaction, keselamatan pasienAbstract
Perkembangan teknologi digital dalam bidang kesehatan telah mendorong perubahan sistem pemantauan keamanan obat dari pendekatan konvensional menuju digital pharmacovigilance. Sistem farmakovigilans memiliki peran penting dalam mengidentifikasi, mengevaluasi, dan mencegah risiko yang berkaitan dengan penggunaan obat, terutama kejadian adverse drug reaction (ADR). Namun, peningkatan jumlah obat, kompleksitas terapi, serta bertambahnya volume data kesehatan menyebabkan metode pemantauan tradisional menghadapi berbagai keterbatasan, seperti keterlambatan deteksi risiko dan rendahnya efisiensi analisis informasi keamanan obat. Artificial intelligence (AI) menjadi salah satu teknologi yang berpotensi mendukung transformasi sistem farmakovigilans melalui kemampuan dalam mengolah data kesehatan, mengenali pola, serta menyediakan informasi pendukung untuk evaluasi keamanan obat. Artikel ini bertujuan untuk membahas peran, manfaat, tantangan, dan perspektif masa depan penerapan AI dalam digital pharmacovigilance dari sudut pandang kefarmasian. Metode yang digunakan dalam kajian ini adalah narrative review dengan melakukan penelusuran literatur melalui basis data PubMed, ScienceDirect, SpringerLink, dan Google Scholar. Literatur yang dianalisis mencakup publikasi ilmiah mengenai farmakovigilans, keamanan obat, serta pemanfaatan AI dalam mendukung sistem pemantauan obat. Hasil kajian menunjukkan bahwa AI memiliki potensi dalam meningkatkan efektivitas farmakovigilans melalui dukungan terhadap proses pengumpulan informasi keamanan obat, deteksi risiko, evaluasi ADR, pemantauan literatur, serta pengambilan keputusan klinis. Dalam praktik kefarmasian, penerapan AI dapat membantu meningkatkan efisiensi kerja apoteker, memperkuat monitoring terapi, dan mendukung peningkatan keselamatan pasien. Meskipun demikian, implementasi AI masih menghadapi tantangan terkait kualitas data, perlindungan privasi pasien, validasi hasil analisis, regulasi, serta kesiapan tenaga kesehatan dalam memanfaatkan teknologi tersebut. Oleh karena itu, AI perlu diposisikan sebagai alat pendukung keputusan yang melengkapi peran tenaga kesehatan, bukan menggantikannya. Integrasi AI yang dilakukan secara bertanggung jawab berpotensi membangun sistem farmakovigilans yang lebih proaktif, efektif, dan berorientasi pada keselamatan pasien.
Downloads
References
Organization WH. The safety of medicines in public health programmes: pharmacovigilance an essential tool. France: WHO Press; 2006.
Palleria C, Leporini C, Chimirri S, Marrazzo G, Sacchetta S, Lista RM, Staltari O, Scuteri A, Scicchitano F, Russo E. Limitations and obstacles of the spontaneous adverse drugs reactions reporting : Two “ challenging ” case reports. Pharmacology and Pharmacotherapeutics. 2013;4(1). doi:10.4103/0976-500X.120955
Hazell L, Shakir SAW. Under-reporting of adverse drug reactions : a systematic review. Pubmed. 2006;29(5):385–96. doi:0.2165/00002018-200629050-00003 Full text linksCite PubMed PMID: 16689555.
Harpaz R, Callahan A, Tamang S, Low Y, Odgers D, Finlayso S, Jung K, LePendu P. Text mining for adverse drug events: the promise, challenges, and state of the art. Pubmed. 2014;37(10). doi:10.1007/s40264-014-0218-z PubMed PMID: 25151493.
DW B, D L, A S, M K, KJT C, A R, GP J, K R. The potential of artificial intelligence to improve patient safety: a scoping review. Europe PMC. 2021;4(1). doi:10.1038/s41746-021-00423-6 PubMed PMID: 33742085.
Li Y, Tao W, Li Z, Sun Z, Li F, Fenton S, Xu H, Tao C. Artificial intelligence-powered pharmacovigilance : A review of machine and deep learning in clinical text-based adverse drug event detection for benchmark datasets. Journal of Biomedical Informatics. 2024;152(3):104621. doi:10.1016/j.jbi.2024.104621
Bouvy JC, Bruin ML De, Koopmanschap MA. Epidemiology of adverse drug reactions in Europe: a review of recent observational studies. PUBMED. 2015;38(5):437–53. doi:10.1007/s40264-015-0281-0 PubMed PMID: 25822400.
Hripcsak G, Duke JD, Shah NH, Reich CG, Huser V, Schuemie MJ, Suchard MA, Park RW, Wong ICK, Rijnbeek PR, Lei J van der, Pratt N, Norén GN, Li YC, Stang PE, Madigan D, Patrick B RyanGeorge Hripcsak 1, Jon D Duke 2, Nigam H Shah 3, Christian G Reich 4, Vojtech Huser 5, Martijn J Schuemie 6, Marc A Suchard 7, Rae Woong Park 8, Ian Chi Kei Wong 6, Peter R Rijnbeek 9, Johan van der Lei 9, Nicole Pratt 10, G Niklas Norén 11, PBR. Observational Health Data Sciences and Informatics (OHDSI): Opportunities for Observational Researchers. Pubmed. 2015;216:574–8. PubMed PMID: 26262116.
Obermeyer Z, J E, Emanuel MD. Predicting the Future — Big Data, Machine Learning, and Clinical Medicine. The New England Journal Of Medicine. 2016;375(13). doi:10.1056/NEJMp1606181
Huang L, Shea AL, Qian H, Masurkar A, Deng H, Liu D. Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records. pubmed. 2019. doi:10.1016/j.jbi.2019.103291 PubMed PMID: 31560949.
Hakim JB, Painter JL, Ramcharran D, Kara V, Powell G, Sobczak P, Sato C, Bate A, Beam A. The need for guardrails with large language models in pharmacovigilance and other medical safety critical settings. Scientific Reports. 2025;1–14. doi:s41598-025-09138-0 1
Singhal K, Azizi S, Tu T, Mahdavi SS, Wei J, Chung HW, Scales N, Tanwani A, Cole-lewis H, Pfohl S, Payne P, Seneviratne M, Gamble P, Kelly C, Babiker A, Schärli N, Chowdhery A, Mansfield P, Demner-fushman D, Agüera B, Webster D, Corrado GS, Matias Y, Chou K, Gottweis J, Tomasev N, Liu Y, Rajkomar A, Barral J. Large language models encode clinical knowledge. Nature. 2023;620(3):172–9. doi:10.1038/s41586-023-06291-2
Kalyanaraman V, Mahalakshmi AS. ARTIFICIAL INTELLIGENCE IN HEALTHCARE: A REVIEW ON APPLICATIONS AND FUTURE DIRECTIONS. Journal Of Technology. 2024;15(11):184–96.
Organization WH. ETHICS AND GOVERNANCE OF ARTIFICIAL INTELLIGENCE FOR HEALTH. Switzerland: WHO Press; 2021.
Bate A, Evans SJW. Quantitative signal detection using spontaneous ADR reporting. Pubmed. 2009;18(6):427–36. doi:10.1002/pds.1742 Full text links PubMed PMID: 19358225.
Pinheiro LC, Arlett P, Roes K, Tshinanu FM, Westman G, Frias Z, Hamann H, Jornet JB, Khan I, Larsen J, Broich K, Cooke E. Artificial Intelligence in European Medicines Regulation : From Vision to Action . Harnessing the Capabilities of Artificial Intelligence for the Benefit of Public and Animal Health. CLINICAL PHARMACOLOGY & THERAPEUTICS. 2025;117(2):335–7. doi:10.1002/cpt.3494
Yu E, Chu X, Zhang W, Meng X, Yang Y, Ji X. Large Language Models in Medicine : Applications , Challenges , and Future Directions. International Journal of Medical Sciences. 2025;22(11):2792–801. doi:10.7150/ijms.111780
Koletsas P, Gavazova E, Staynova R, Kafalova D. Application of artificial intelligence in pharmacovigilance: a systematic review. Pubmed. 2025;39(3):400–6. doi:10.1007/s40290-025-00561-2
Sylvia S, Oliva J. Artificial Intelligence in Health Care : Opportunities , Challenges , and the Road Ahead. Pubmed. 2024;85(4):238–9. doi:10.18043/001c.120561
Sarker A, Gonzalez G. Portable automatic text classification for adverse drug reaction detection via multi-corpus training. Journal of Biomedical Informatics. 2015;53:196–207. doi:10.1016/j.jbi.2014.11.002
Schuemie MJ, Ryan PB, DuMouchel W, Suchard MA, Madigan D. Interpreting observational studies: why empirical calibration is needed to correct p-values. PUBMED. 2014;33(2):209–18. doi:10.1002/sim.5925 PubMed PMID: 23900808.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Yerry Dayana, Rangga Febriyana

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


