A discovery and verification approach to pharmacovigilance using electronic healthcare data

Abstract

Introduction: Pharmacovigilance is vital for drug safety. The process typically involves two key steps: initial signal generation from spontaneous reporting systems (SRSs) and subsequent expert review to assess the signals' (potential) causality and decide on the appropriate action.

Methods: We propose a novel discovery and verification approach to pharmacovigilance based on electronic healthcare data. We enhance the signal detection phase by introducing an ensemble of methods which generated signals are combined using Borda count ranking; a method designed to emphasize consensus. Ensemble methods tend to perform better when data is noisy and leverage the strengths of individual classifiers, while trying to mitigate some of their limitations. Additionally, we offer the committee of medical experts with the option to perform an in-depth investigation of selected signals through tailored pharmacoepidemiological studies to evaluate their plausibility or spuriousness. To illustrate our approach, we utilize data from the German Pharmacoepidemiological Research Database, focusing on drug reactions to the direct oral anticoagulant rivaroxaban.

Results: In this example, the ensemble method is built upon the Bayesian confidence propagation neural network, longitudinal Gamma Poisson shrinker, penalized regression and random forests. We also conduct a pharmacoepidemiological verification study in the form of a nested active comparator case-control study, involving patients diagnosed with atrial fibrillation who initiated anticoagulant treatment between 2011 and 2017.

Discussion: The case study reveals our ability to detect known adverse drug reactions and discover new signals. Importantly, the ensemble method is computationally efficient. Hasty false conclusions can be avoided by a verification study, which is, however, time-consuming to carry out. We provide an online tool for easy application: https://borda.bips.eu.

Keywords: Borda count; DOAC; GEPARD; drug safety; machine learning; medical records.

FIGURE 1

(A) The conventional pharmacovigilance approach involves applying a single detection method to SRS data to generate a single ranking of ADRs pairs. This ranking is subsequently submitted to a committee of medical experts. (B) The approach proposed in this paper entails the application of $Q$ distinct signal detection methods to EHC data, resulting in $Q$ rankings. These rankings are then amalgamated into a unified ranking using the Borda count method. The consolidated ranking is then presented to the committee. Furthermore, the option to conduct a verification study is provided to the committee as well. The $*$ indicates that, preferably, the EHC data are split into two sets: one for detection and one for the verification phase.

FIGURE 2

Kendall’s $\tau$ correlations between the rankings of the BCPNN, LGPS, RF and LASSO. The correlation values fall within the range of $[-\mathrm{1,1}]$ . However, for clarity, the legend only depicts the positive range [0,1].

FIGURE 3

The relative ranks represent the positions of seven adverse outcomes, with five consisting of multiple individual ADRs. Each dot represents an individual ICD-code. A relative rank of 1 signifies the highest rank, indicating no signal, while a relative rank of 0 indicates the top rank, suggesting a very strong signal.