Cox regression using a calendar time scale was unbiased in simulations of COVID-19 vaccine effectiveness & safety

Lars Christian Lund; Henrik Støvring; Anton Pottegård; Morten Andersen; Jesper Hallas

doi:10.1016/j.jclinepi.2023.02.012

Cox regression using a calendar time scale was unbiased in simulations of COVID-19 vaccine effectiveness & safety

J Clin Epidemiol. 2023 Apr:156:127-136. doi: 10.1016/j.jclinepi.2023.02.012. Epub 2023 Feb 16.

Authors

Lars Christian Lund¹, Henrik Støvring², Anton Pottegård², Morten Andersen³, Jesper Hallas²

Affiliations

¹ Clinical Pharmacology, Pharmacy and Environmental Medicine, University of Southern Denmark, Odense, Denmark. Electronic address: lclund@health.sdu.dk.
² Clinical Pharmacology, Pharmacy and Environmental Medicine, University of Southern Denmark, Odense, Denmark.
³ Pharmacovigilance Research Center, Department of Drug Design and Pharmacology, University of Copenhagen, Copenhagen, Denmark.

Abstract

Background: Observational studies on corona virus disease 2019 (COVID-19) vaccines compare event rates in vaccinated and unvaccinated person time using Poisson or Cox regression. In Cox regression, the chosen time scale needs to account for the time-varying incidence of severe acute respiratory syndrome corona virus 2 (SARS-CoV-2) infection and COVID-19 vaccination.We aimed to quantify bias in person-time based methods, with and without adjustment for calendar time, using simulations and empirical data analysis.

Methods: We simulated 500,000 individuals who were followed for 365 days, and a point exposure resembling COVID-19 vaccination (cumulative incidence 80%). We generated an effectiveness outcome, emulating the incidence of severe acute respiratory syndrome corona virus 2 infection in Denmark during 2021 (risk 10%), and a safety outcome with seasonal variation (myocarditis, risk 1/5,000). Incidence rate ratios (IRRs) were set to 0.1 for effectiveness and 5.0 for safety outcomes. IRRs and hazard ratios (HRs) were estimated using Poisson and Cox regression with a time under observation scale, and a calendar time scale. Bias was defined as estimated IRR or HR-true IRR. Further, we obtained estimates for both outcomes using data from the Danish health registries.

Results: Unadjusted IRRs (bias_effectivenes +0.16; bias_safety -2.09) and HRs estimated using a time-under-observation scale (+0.28;-2.15) were biased. Adjustment for calendar time reduced bias in Cox (+0.03; +0.33) and Poisson regression (0.00; -0.28). Cox regression using a calendar time scale was least biased (0.00, +0.12). When analyzing empirical data, adjusted Poisson and Cox regression using a calendar time scale yielded estimates in accordance with existing evidence.

Conclusion: Lack of adjustment for the time-varying incidence of COVID-19 related outcomes may severely bias estimates.

Keywords: COVID-19; Cohort studies; Cox regression; SARS-CoV-2; Simulation; Vaccine effectiveness; Vaccine safety.

MeSH terms

COVID-19 Vaccines* / adverse effects
COVID-19* / epidemiology
COVID-19* / prevention & control
Data Analysis
Humans
SARS-CoV-2
Vaccine Efficacy

Substances

COVID-19 Vaccines