EUVIMEDEUVIMED entdecken
Crossref

The population-attributable fraction for time-to-event data

Maja von Cube, Martin Schumacher, Jean Francois Timsit, Johan Decruyenaere, Johan Steen iD

International Journal of Epidemiology · 06.06.2023 · 52 (3) · 837-845

DOI: 10.1093/ije/dyac217 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Epidemiology, online erschienen am 22.11.2022. Verfasst von Maja von Cube und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Medical Biometry and Statistics, Faculty of Medicine and Medical Center, University of Freiburg, Freiburg, Germany. Hauptthemen laut MEDLINE: Bias. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: Education and Qualification for Postdocs, Medical Scientists Program, Medical Centre.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Even though the population-attributable fraction (PAF) is a well-established metric, it is often incorrectly estimated or interpreted not only in clinical application, but also in statistical research articles. The risk of bias is especially high in more complex time-to-event data settings.

Methods

We explain how the PAF can be defined, identified and estimated in time-to-event settings with competing risks and time-dependent exposures. By using multi-state methodology and inverse probability weighting, we demonstrate how to reduce or completely avoid severe types of biases including competing risks bias, immortal time bias and confounding due to both baseline and time-varying patient characteristics.

Results

The method is exemplarily applied to a real data set. Moreover, we estimate the number of deaths that were attributable to ventilator-associated pneumonia in France in the year 2016. The example demonstrates how, under certain simplifying assumptions, PAF estimates can be extrapolated to a target population of interest.

Conclusions

Defining and estimating the PAF in advanced time-to-event settings within a framework that unifies causal and multi-state modelling enables to tackle common sources of bias and allows straightforward implementation with standard software packages.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BiasHumansProbabilityTimeFrance

Stichwörter der Autor:innen

Attributable fractioncompeting risks biasimmortal time biasmulti-state modellingsoftware implementation

Autor:innen und Institutionen

  • Institute of Medical Biometry and Statistics, Faculty of Medicine and Medical Center, University of Freiburg, Freiburg, Germany.
  • University of Paris, IAME, INSERM, Paris, France.
  • AP-HP, Bichat Hospital, Medical and Infectious Diseases ICU (MI2), Paris, France.
  • Faculty of Medicine and Health Sciences, Department of Internal Medicine and Pediatrics, Ghent University Hospital, Ghent, Belgium.
  • Department of Intensive Care Medicine, Ghent University Hospital, Ghent, Belgium.
  • Renal Division, Ghent University Hospital, Ghent, Belgium.

ORCID-Profile: Johan Steen

Förderung

  • Education and Qualification for Postdocs
  • Medical Scientists Program
  • Medical Centre

Zitieren

APA

von Cube, M., Schumacher, M., Timsit, J. F., Decruyenaere, J., & Steen, J. (2023). The population-attributable fraction for time-to-event data. International Journal of Epidemiology, 52(3), 837-845. https://doi.org/10.1093/ije/dyac217

Vancouver

von Cube M, Schumacher M, Timsit JF, Decruyenaere J, Steen J. The population-attributable fraction for time-to-event data. International Journal of Epidemiology. 2023;52(3):837-845. doi:10.1093/ije/dyac217

BibTeX
@article{vonCube2023,
  author = {von Cube, Maja and Schumacher, Martin and Timsit, Jean Francois and Decruyenaere, Johan and Steen, Johan},
  title = {The population-attributable fraction for time-to-event data},
  journal = {International Journal of Epidemiology},
  year = {2023},
  volume = {52},
  number = {3},
  pages = {837--845},
  doi = {10.1093/ije/dyac217}
}
Kostenlos starten →