Abstract
This paper introduces a machine learning classifier designed to automate causality assessment in Individual Case Safety Reports (ICSRs), utilizing the principle of event similarity. The classifier’s effectiveness was evaluated using adverse events from six marketed products. Furthermore, we incorporated an augmentation tool to efficiently manage the classification of ‘unassessable’ adverse events. To enhance medical review oversight, we developed a web-based application serving as a reliable decision-support tool for medical reviewers. The outcomes obtained from our model were highly encouraging, emphasizing the potential advantages of utilizing such a model in ICSR causality assessment.
Data availability
The data is sensitive, proprietary, post-marketing adverse event data and is not available for sharing. However, inquiries regarding the data or the study can be directed to the corresponding author Jun Ren at jun.ren@biogen.com
References
Zitu, M. M., Zhang, S., Owen, D. H. & Chiang, C. Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records. Front. Pharmacol. https://doi.org/10.3389/fphar.2023.1218679 (2023).
Cherkas, Y., Ide, J. & van Stekelenborg, J. Leveraging machine learning to facilitate individual case causality assessment of adverse drug reactions. Drug Saf. 45, 571–82 (2022).
Zhao, Y. et al. Machine learning in causal inference: Application in pharmacovigilance. Drug Saf. 45(5), 459–476. https://doi.org/10.1007/s40264-022-01155-6 (2022).
Kıcıman, E., Ness, R., Sharma, A., & Tan, C. Causal reasoning and large language models: opening a new frontier for causality. https://arxiv.org/abs/2305.00050.
Yan, C. et al. DNDDI: an integrated drug similarity network method for predicting drug-drug interactions. In Bioinformatics Research and Applications. ISBRA 2019. Lecture Notes in Computer Science (eds Cai, Z. et al.) vol 11490 (Springer, 2019). https://doi.org/10.1007/978-3-030-20242-2_8.
Saaty, T. L. Decision making with the analytic hierarchy process. Int. J. Serv. Sci. 1(1), 83–98 (2008).
Meyboom, R. H. B. & Royer, R. J. Causality classification in pharmacovigilance centres in the European community. Pharmacoepidemiol. Drug Saf. 1, 87–97 (1992).
Cover, T. & Hart, P. Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13(1), 21–27 (1967).
Ren, J. et al. Application of a kNN-based similarity method to biopharmaceutical manufacturing. Biotechnol. Prog. 36(2), e2945. https://doi.org/10.1002/btpr.2945 (2019).
Cassisi, C., Montalto, P., Aliotta, M., Cannata, A. & Pulvirenti, A. Similarity measures and dimensionality reduction techniques for time series data mining. Adv. Data Min. Knowl. Discov. Appl. https://doi.org/10.5772/49941 (2012).
Indyk, P. & Motwani, R. Approximate nearest neighbors: towards removing the curse of dimensionality. Proceedings of the thirtieth annual ACM symposium on Theory of computing (STOC ’98) 604–613 (ACM, 1998).
Dupuch, M. & Grabar, N. Semantic distance-based creation of clusters of pharmacovigilance terms and their evaluation. J. Biomed. Inform. 53, 287–296. https://doi.org/10.1016/j.jbi.2014.11.012 (2015).
Funding
This research was funded by Biogen.
Author information
Authors and Affiliations
Contributions
Jun Ren and Hua Carroll led the model development effort and model augmentation activities. All authors contributed to the manuscript in accordance with the guidance. All authors read and approved the final version.
Corresponding author
Ethics declarations
Competing interests
All authors are employees of Biogen. The authors declare no competing interests.
Ethics aproval
The research only utilized post-marketing AE data.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Ren, J., Carroll, H., McCarthy, K. et al. A kNN based machine learning approach to automating causality assessment of adverse events. Sci Rep (2026). https://doi.org/10.1038/s41598-026-40267-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-40267-2
