INTEGRATED ANALYSIS OF PHARMACOVIGILANCE EVENT CHARACTERISTICS AND CLINICAL SAFETY INDICATORS
Abstract
Adverse drug event detection from biomedical text using computer-based algorithms is becoming more common in pharmacovigilance. Nonetheless, the uneven distribution of events could be an impediment to the detection process of some clinically significant adverse drug events. The present study aimed to analyze pharmacovigilance event characteristics and evaluate machine learning performance for distinguishing adverse events from potential therapeutic events in biomedical text. A quantitative secondary data analysis was conducted using 5,019 annotated biomedical text
records. Event distribution, text length, and word count were summarized descriptively. Logistic Regression, Support Vector Machine, and Random Forest classifiers were trained using TF-IDF feature representations. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrices. Feature coefficient analysis was additionally performed to identify terms associated with each event class. Adverse events represented the majority of records (n = 4,485), whereas potential therapeutic events accounted for 534 records. Therapeutic-event records showed higher mean text length and word count than adverse-event records. Random Forest achieved the highest accuracy (0.882) but demonstrated very low recall (0.033). Logistic Regression produced the strongest balanced performance, with an accuracy of 0.877, a recall of 0.512, and an F1-score of 0.500. Feature interpretation identified clinically meaningful terms associated with therapeutic improvement and adverse drug reactions. Interpretability of machine learning helped in the classification of pharmacovigilance events, but the imbalance had a large effect on the model’s behavior. It is
important to have balanced performance and interpretability for the analysis of biomedical safety texts.
Downloads
References
Sun, Z., Li, J., Pergola, G., Wallace, B. C., John, B., Greene, N., & He, Y. (2022). PHEE: A Dataset for
Pharmacovigilance Event Extraction from Text [Data set]. Empirical Methods in Natural Language Processing
(EMNLP), Abu Dhabi, UAE. Zenodo. https://doi.org/10.5281/zenodo.7689970
Al-Worafi, Y. M. (2020). Pharmacovigilance. In Drug safety in developing countries (pp. 29-38). Academic Press.
Lucas, S., Ailani, J., Smith, T. R., Abdrabboh, A., Xue, F., & Navetta, M. S. (2022). Pharmacovigilance: reporting
requirements throughout a product’s lifecycle. Therapeutic advances in drug safety, 13, 20420986221125006.
Desai, M. K. (2024). Artificial intelligence in pharmacovigilance–Opportunities and challenges. Perspectives in
Clinical Research, 15(3), 116-121.
Sartori, D., Aronson, J. K., Norén, G. N., & Onakpoya, I. J. (2023). Signals of adverse drug reactions communicated
by pharmacovigilance stakeholders: a scoping review of the global literature. Drug safety, 46(2), 109-120.
Yang, J., & Li, F. (2025). The Impact of Technological Progress on Pharmacovigilance. Pharmacovigilance-Facts,
Challenges, Limitations and Opportunities: Facts, Challenges, Limitations and Opportunities, 43.
Vestergaard Kvist, A., Faruque, J., Vallejo-Yagüe, E., Weiler, S., Winter, E. M., & Burden, A. M. (2021).
Cardiovascular safety profile of romosozumab: a pharmacovigilance analysis of the US Food and Drug Administration
Adverse Event Reporting System (FAERS). Journal of clinical medicine, 10(8), 1660.
Young, I. J. B., Luz, S., & Lone, N. (2019). A systematic review of natural language processing for classification tasks
in the field of incident reporting and adverse event analysis. International journal of medical informatics, 132,
Negi, K., Pavuri, A., Patel, L., & Jain, C. (2019). A novel method for drug-adverse event extraction using machine
learning. Informatics in Medicine Unlocked, 17, 100190.
Al-Worafi, Y. M. (2023). Technology for drug safety: Current status and future developments. Springer Nature.
Liu, F., Jagannatha, A., & Yu, H. (2019). Towards drug safety surveillance and pharmacovigilance: current progress
in detecting medication and adverse drug events from electronic health records. Drug safety, 42(1), 95.
Basile, A. O., Yahi, A., & Tatonetti, N. P. (2019). Artificial intelligence for drug toxicity and safety. Trends in
pharmacological sciences, 40(9), 624-635.
Panda, P., & Mohapatra, R. (2024). Revolutionizing Patient Safety: Machine Learning and AI for the Early Detection
of Adverse Drug Reactions and Drug-Induced Toxicity. Current Artificial Intelligence.
Alomar, M., Tawfiq, A. M., Hassan, N., & Palaian, S. (2020). Post marketing surveillance of suspected adverse drug
reactions through spontaneous reporting: current status, challenges and the future. Therapeutic advances in drug
safety, 11, 2042098620938595.
Mehta, R. (2025). Postmarket drug safety monitoring. In Translational Gastroenterology (pp. 395-397). Academic
Press.
Li, D., Gou, J., Zhu, J., Zhang, T., Liu, F., Zhang, D., ... & Liu, S. (2023). Severe cutaneous adverse reactions to drugs:
A real-world pharmacovigilance study using the FDA Adverse Event Reporting System database. Frontiers in
Pharmacology, 14, 1117391.
Lé
tinier, L., Ferreira, A., Marceron, A., Babin, M., Micallef, J., Miremont-Salamé
, G., ... & French Network of
Pharmacovigilance Centres. (2021). Spontaneous reports of serious adverse drug reactions resulting from drug–drug
interactions: an analysis from the French Pharmacovigilance Database. Frontiers in Pharmacology, 11, 624562.
Khemani, B., Malave, S., Shinde, S., Shukla, M., Shikalgar, R., & Talwar, H. (2025). AI-driven pharmacovigilance:
Enhancing adverse drug reaction detection with deep learning and NLP. MethodsX, 15, 103460.
De Abreu Ferreira, R., Zhong, S., Moureaud, C., Le, M. T., Rothstein, A., Li, X., ... & Patwardhan, M. (2024). A pilot,
predictive surveillance model in pharmacovigilance using machine learning approaches. Advances in Therapy, 41(6),
-2445.
Majekodunmi, E. A. (2025). Strengthening Drug Safety and Public Health Surveillance in the United States: The Role
of Artificial Intelligence in Pharmacovigilance. Available at SSRN 5181179.
Martin, G. L., Jouganous, J., Savidan, R., Bellec, A., Goehrs, C., Benkebil, M., ... & French Network of
Pharmacovigilance Centres. (2022). Validation of artificial intelligence to support the automatic coding of patient
adverse drug reaction reports, using nationwide pharmacovigilance data. Drug Safety, 45(5), 535-548.
Sharma, M., Baghel, R., Thakur, S., & Adwal, S. (2021). Surveillance of adverse drug reactions at an adverse drug
reaction monitoring centre in Central India: a 7-year surveillance study. BMJ open, 11(10), e052737.
Kim, S., Kang, T., Chung, T. K., Choi, Y., Hong, Y., Jung, K., & Lee, H. (2023). Automatic extraction of
comprehensive drug safety information from adverse drug event narratives in the Korea adverse event reporting
system using natural language processing techniques. Drug Safety, 46(8), 781-795.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 International Journal For Research In Biology & Pharmacy
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
In consideration of the journal, Green Publication taking action in reviewing and editing our manuscript, the authors undersigned hereby transfer, assign, or otherwise convey all copyright ownership to the Editorial Office of the Green Publication in the event that such work is published in the journal. Such conveyance covers any product that may derive from the published journal, whether print or electronic. Green Publication shall have the right to register copyright to the Article in its name as claimant, whether separately
or as part of the journal issue or other medium in which the Article is included.
By signing this Agreement, the author(s), and in the case of a Work Made For Hire, the employer, jointly and severally represent and warrant that the Article is original with the author(s) and does not infringe any copyright or violate any other right of any third parties, and that the Article has not been published elsewhere, and is not being considered for publication elsewhere in any form, except as provided herein. Each author’s signature should appear below. The signing author(s) (and, in
