Safety signal detection with control of latent factors

Authors

Xianming Tan, Department of Biostatistics at Gillings School of Global Public Health, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
William Wang, Merck and Co., Inc., North Wales, Pennsylvania, USA.
Donglin Zeng, Department of Biostatistics at Gillings School of Global Public Health, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
Guanghan F. Liu, Merck and Co., Inc., North Wales, Pennsylvania, USA.
Guoqing Diao, Department of Biostatistics and Bioinformatics, Milken Institute School of Public Health, George Washington University, Washington, DC, USA.
Niusha Jafari, Merck and Co., Inc., North Wales, Pennsylvania, USA.
Ethan M. Alt, Department of Biostatistics at Gillings School of Global Public Health, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
Joseph G. Ibrahim, Department of Biostatistics at Gillings School of Global Public Health, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.

Document Type

Journal Article

Publication Date

1-31-2024

Journal

Statistics in medicine

DOI

10.1002/sim.10015

Keywords

VAERS; generalized linear mixed models; multivariate logistic regression model; signal detection; variational inference (VI) method

Abstract

Postmarket drug safety database like vaccine adverse event reporting system (VAERS) collect thousands of spontaneous reports annually, with each report recording occurrences of any adverse events (AEs) and use of vaccines. We hope to identify signal vaccine-AE pairs, for which certain vaccines are statistically associated with certain adverse events (AE), using such data. Thus, the outcomes of interest are multiple AEs, which are binary outcomes and could be correlated because they might share certain latent factors; and the primary covariates are vaccines. Appropriately accounting for the complex correlation among AEs could improve the sensitivity and specificity of identifying signal vaccine-AE pairs. We propose a two-step approach in which we first estimate the shared latent factors among AEs using a working multivariate logistic regression model, and then use univariate logistic regression model to examine the vaccine-AE associations after controlling for the latent factors. Our simulation studies show that this approach outperforms current approaches in terms of sensitivity and specificity. We apply our approach in analyzing VAERS data and report our findings.

APA Citation

Tan, Xianming; Wang, William; Zeng, Donglin; Liu, Guanghan F.; Diao, Guoqing; Jafari, Niusha; Alt, Ethan M.; and Ibrahim, Joseph G., "Safety signal detection with control of latent factors" (2024). GW Authored Works. Paper 4100.
https://hsrc.himmelfarb.gwu.edu/gwhpubs/4100

Department

Biostatistics and Bioinformatics