Informative Censoring-A Cause of Bias in Estimating COVID-19 Mortality Using Hospital Data

Hung-Mo Lin; Sean T H Liu; Matthew A Levin; John Williamson; Nicole M Bouvier; Judith A Aberg; David Reich; Natalia Egorova

doi:10.3390/life13010210

Informative Censoring-A Cause of Bias in Estimating COVID-19 Mortality Using Hospital Data

Life (Basel). 2023 Jan 11;13(1):210. doi: 10.3390/life13010210.

Authors

Hung-Mo Lin¹, Sean T H Liu², Matthew A Levin³, John Williamson⁴, Nicole M Bouvier², Judith A Aberg², David Reich³, Natalia Egorova¹

Affiliations

¹ Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
² Division of Infectious Diseases, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
³ Department of Anesthesiology, Perioperative and Pain Medicine, Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
⁴ Division of Parasitic Diseases and Malaria, Centers for Disease Control and Prevention, Atlanta, GA 30333, USA.

Abstract

(1) Background: Several retrospective observational analyzed treatment outcomes for COVID-19; (2) Methods: Inverse probability of censoring weighting (IPCW) was applied to correct for bias due to informative censoring in database of hospitalized patients who did and did not receive convalescent plasma; (3) Results: When compared with an IPCW analysis, overall mortality was overestimated using an unadjusted Kaplan-Meier curve, and hazard ratios for the older age group compared to the youngest were underestimated using the Cox proportional hazard models and 30-day mortality; (4) Conclusions: An IPCW analysis provided stabilizing weights by hospital admission.

Keywords: COVID-19; censoring; convalescent plasma.

Grants and funding

This research received no external funding.