EUVIMEDEUVIMED entdecken
Open Access

Illustrating the structures of bias from immortal time using directed acyclic graphs

Guoyi Yang iD, Stephen Burgess iD, Catherine Mary Schooling iD

International Journal of Epidemiology · 16.12.2024 · 54 (1)

DOI: 10.1093/ije/dyae176 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Epidemiology, online erschienen am 07.01.2025. Verfasst von Guoyi Yang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Public Health, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, China. Hauptthemen laut MEDLINE: Bias. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Wellcome Trust, Medical Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Immortal time is a period of follow-up during which death or the study outcome cannot occur by design. Bias from immortal time has been increasingly recognized in epidemiological studies. However, the fundamental causes and structures of bias from immortal time have not been explained systematically.

Methods

We use an example ‘Does winning a Nobel Prize prolong lifespan?’ for illustration. We illustrate how immortal time arises and present structures of bias from immortal time using directed acyclic graphs that specify time-varying variables. We further explore the structures of bias with the exclusion of immortal time and with the presence of competing risks. We discuss how these structures are shared by different study designs in pharmacoepidemiology and provide solutions, where possible, to address the bias.

Results

The fundamental cause of immortal time is misalignment of exposure allocation and eligibility. Specifically, immortal time arises from using post-eligibility information to define exposure or using post-exposure information to define eligibility. The structures of bias from immortal time are confounding by survival until exposure allocation or selection bias from selecting on survival until eligibility. Excluding immortal time from follow-up does not fully address this confounding or selection bias, and the presence of competing risks can worsen the bias. Bias from immortal time may be avoided by aligning baseline, exposure allocation and eligibility, and by excluding individuals with prior exposure.

Conclusions

Understanding bias from immortal time in terms of confounding or selection bias helps researchers identify and thereby avoid or ameliorate this bias.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BiasHumansTime FactorsSelection BiasPharmacoepidemiologyConfounding Factors, Epidemiologic

Stichwörter der Autor:innen

Biasdirected acyclic graphsepidemiologyimmortal time

Autor:innen und Institutionen

  • School of Public Health, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Hong Kong, China.
  • MRC Biostatistics Unit, University of Cambridge, Cambridge, UK.
  • British Heart Foundation Cardiovascular Epidemiology Unit, Department of Public Health and Primary Care, University of Cambridge, Cambridge, UK.
  • Graduate School of Public Health and Health Policy, City University of New York, New York, NY, USA.

ORCID-Profile: Guoyi Yang, Stephen Burgess, Catherine Mary Schooling

Förderung

  • Wellcome Trust
  • Medical Research Council

Zitieren

APA

Yang, G., Burgess, S., & Schooling, C. M. (2024). Illustrating the structures of bias from immortal time using directed acyclic graphs. International Journal of Epidemiology, 54(1). https://doi.org/10.1093/ije/dyae176

Vancouver

Yang G, Burgess S, Schooling CM. Illustrating the structures of bias from immortal time using directed acyclic graphs. International Journal of Epidemiology. 2024;54(1). doi:10.1093/ije/dyae176

BibTeX
@article{Yang2024,
  author = {Yang, Guoyi and Burgess, Stephen and Schooling, Catherine Mary},
  title = {Illustrating the structures of bias from immortal time using directed acyclic graphs},
  journal = {International Journal of Epidemiology},
  year = {2024},
  volume = {54},
  number = {1},
  doi = {10.1093/ije/dyae176}
}
Kostenlos starten →