Inserm UMR 1153, Obstetrical, Perinatal and Pediatric Epidemiology Research Team, Research Center for Epidemiology and Biostatistics Sorbonne Paris Cité (CRESS), Paris Descartes University, Paris, France.
Adverse Events and incidents Department-Surveillance Division, Agence nationale de sécurité du médicament et des produits de santé (ANSM), Saint Denis, France.
Pharmacoepidemiol Drug Saf. 2019 Mar;28(3):370-376. doi: 10.1002/pds.4613. Epub 2018 Jul 10.
Change-point analysis (CPA) is a powerful method to analyse pharmacovigilance data but it has never been used on the disproportionality metric.
To optimize signal detection investigating the interest of time-series analysis in pharmacovigilance and the benefits of combining CPA with the proportional reporting ratio (PRR).
We investigated the couple benfluorex and aortic valve incompetence (AVI) using the French National Pharmacovigilance and EudraVigilance databases: CPA was applied on monthly counts of reports and the lower bound of monthly computed PRR (PRR-). We stated a CPA hypothesis that the substance-event combination is more likely to be a signal when the 2 following criteria are fulfilled: PRR- is greater than 1 with at least 5 cases, and CPA method detects at least 2 successive change points of PRR- which made consecutively increasing segments. We tested this hypothesis by 95 test cases identified from a drug safety reference set and 2 validated signals from EudraVigilance database: CPA was applied on PRR-.
For benfluorex and AVI, change points detected by CPA on PRR- were more meaningful compared with monthly counts of reports: More change points detected and detected earlier. In the reference set, 14 positive controls satisfied CPA hypothesis, 6 positive controls only met first requirements, 3 negative controls only met first requirement, and 2 validated signals satisfied CPA hypothesis.
The combination of CPA and PRR represents a significant advantage in detecting earlier signals and reducing false-positive signals. This approach should be confirmed in further studies.
变点分析（CPA）是一种强大的分析药物警戒数据的方法，但从未在不匀称性指标上使用过。
通过时间序列分析优化信号检测，研究药物警戒中组合使用 CPA 和比例报告比值（PRR）的益处。
我们使用法国国家药物警戒和 EudraVigilance 数据库调查了苯氟雷司和主动脉瓣功能不全（AVI）的案例：CPA 应用于报告的每月计数和计算得出的每月 PRR 的下限（PRR-）。我们提出了一个 CPA 假设，即当满足以下两个条件时，该物质-事件组合更有可能成为信号：PRR-大于 1 且至少有 5 例，以及 CPA 方法检测到至少 2 个连续的 PRR-变化点，这些变化点形成了连续增加的部分。我们通过从药物安全性参考集确定的 95 个测试案例和来自 EudraVigilance 数据库的 2 个验证信号来测试该假设：CPA 应用于 PRR-。
对于苯氟雷司和 AVI，CPA 在 PRR-上检测到的变点与报告的每月计数相比更有意义：检测到更多的变点，并且更早地检测到。在参考集中，有 14 个阳性对照符合 CPA 假设，6 个阳性对照仅满足第一个要求，3 个阴性对照仅满足第一个要求，并且 2 个验证信号符合 CPA 假设。
CPA 和 PRR 的组合在更早地检测信号和减少假阳性信号方面具有显著优势。这种方法应该在进一步的研究中得到证实。
