Performance of pharmacovigilance signal-detection algorithms for the FDA adverse event reporting system

Abstract

Signal-detection algorithms (SDAs) are recognized as vital tools in pharmacovigilance. However, their performance characteristics are generally unknown. By leveraging a unique gold standard recently made public by the Observational Medical Outcomes Partnership (OMOP) and by conducting a unique systematic evaluation, we provide new insights into the diagnostic potential and characteristics of SDAs that are routinely applied to the US Food and Drug Administration (FDA) Adverse Event Reporting System (AERS). We find that SDAs can attain reasonable predictive accuracy in signaling adverse events. Two performance classes emerge, indicating that the class of approaches that address confounding and masking effects benefits safety surveillance. Our study shows that not all events are equally detectable, suggesting that specific events might be monitored more effectively using other data sources. We provide performance guidelines for several operating scenarios to inform the trade-off between sensitivity and specificity for specific use cases. We also propose an approach and demonstrate its application in identifying optimal signaling thresholds, given specific misclassification tolerances.

Figure 1

Signal detection algorithm performance based on the Area Under the Receiver Operating Characteristic curves (AUC) metric. LR, Logistic regression; ELR, Extended Logistic Regression; MGPS, Multi-item Gamma Poisson Shrinker; PRR, Proportional Reporting Ratio; ROR, Reporting Odds Ratio. Signal score labels suffixed by ‘05’ (lower bound signal scores) represent the lower 5% of their corresponding point estimate distributions. Error bars reflect AUC 95% confidence intervals.

Figure 2

Receiver Operating Characteristic (ROC) curves for the EB05, PRR05, ROR05, LR05, and ELR05 signal scores. The pattern of containment between logistic regression and disproportionality based methods imply that the class of logistic regression based approaches provides greater specificity across all levels of sensitivity.

Figure 3

Signal detection algorithm performance (AUC) classified by event. Error bars reflect AUC 95% confidence intervals. AUC, Area Under the Receiver Operating Characteristic curve.