Attelind Sofia, Eriksson Niclas, Sundström Anders, Wadelius Mia, Hallberg Pär
Department of Medical Sciences, Clinical Pharmacogenomics, Uppsala University, Uppsala, Sweden.
Department of Drug Safety, Swedish Medical Products Agency, Uppsala, Sweden.
Pharmacoepidemiol Drug Saf. 2023 Dec;32(12):1431-1438. doi: 10.1002/pds.5679. Epub 2023 Aug 14.
In addition to identifying new safety signals, pharmacovigilance databases could be used to identify potential risk factors for adverse drug reactions (ADRs).
To evaluate whether data mining in a pharmacovigilance database can be used to identify known and possible novel risk factors for ADRs, for use in pharmacovigilance practice.
Exploratory data mining was performed within the Swedish national database of spontaneously reported ADRs. Bleeding associated with direct oral anticoagulants (DOACs)-rivaroxaban, apixaban, edoxaban, and dabigatran-was used as a test model. We compared demographics, drug treatment, and clinical features between cases with bleeding (N = 965) and controls who had experienced other serious ADRs to DOACs (N = 511). Statistical analysis was performed by unadjusted and age adjusted logistic regression models, and the random forest based machine-learning method Boruta.
In the logistic regression, 13 factors were significantly more common among cases of bleeding compared with controls. Eleven were labelled or previously proposed risk factors. Cardiac arrhythmia (e.g., atrial fibrillation), hypertension, mental impairment disorders (e.g., dementia), renal and urinary tract procedures, gastrointestinal ulceration and perforation, and interacting drugs remained significant after adjustment for age. In the Boruta analysis, high age, arrhythmia, hypertension, cardiac failure, thromboembolism, and pharmacodynamically interacting drugs had a larger than random association with the outcome. High age, cardiac arrhythmia, hypertension, cardiac failure, and pharmacodynamically interacting drugs had odds ratios for bleeding above one, while thromboembolism had an odds ratio below one.
We demonstrated that data mining within a pharmacovigilance database identifies known risk factors for DOAC bleeding, and potential risk factors such as dementia and atrial fibrillation. We propose that the method could be used in pharmacovigilance for identification of potential ADR risk factors that merit further evaluation.
除了识别新的安全信号外，药物警戒数据库还可用于识别药物不良反应（ADR）的潜在风险因素。
评估药物警戒数据库中的数据挖掘是否可用于识别ADR已知和可能的新风险因素，以用于药物警戒实践。
在瑞典国家自发报告ADR数据库中进行探索性数据挖掘。将与直接口服抗凝剂（DOACs）——利伐沙班、阿哌沙班、依度沙班和达比加群相关的出血作为测试模型。我们比较了出血病例（N = 965）和经历过DOACs其他严重ADR的对照（N = 511）之间的人口统计学、药物治疗和临床特征。通过未调整和年龄调整的逻辑回归模型以及基于随机森林的机器学习方法Boruta进行统计分析。
在逻辑回归中，与对照组相比，13个因素在出血病例中显著更常见。其中11个是已标记或先前提出的风险因素。心律失常（如心房颤动）、高血压、精神障碍（如痴呆）、肾脏和尿路手术、胃肠道溃疡和穿孔以及相互作用药物在年龄调整后仍具有显著性。在Boruta分析中，高龄、心律失常、高血压、心力衰竭、血栓栓塞和药效学相互作用药物与结果的关联大于随机关联。高龄、心律失常、高血压、心力衰竭和药效学相互作用药物的出血比值比高于1，而血栓栓塞的比值比低于1。
我们证明了药物警戒数据库中的数据挖掘可识别DOAC出血的已知风险因素以及痴呆和心房颤动等潜在风险因素。我们建议该方法可用于药物警戒中识别值得进一步评估的潜在ADR风险因素。
