EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Causal inference using multivariate generalized linear mixed-effects models

Yizhen Xu iD, Ji Soo Kim, Laura K Hummers, Ami A Shah, Scott L Zeger

Biometrics · 2024

DOI: 10.1093/biomtc/ujae100 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biometrics, 2024. Verfasst von Yizhen Xu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Division of Biostatistics, Department of Population Health Sciences, University of Utah, Salt Lake City, UT 84108, United States. Hauptthemen laut MEDLINE: Bayes Theorem, Computer Simulation, Algorithms. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIAMS NIH HHS, NIH HHS, NIH/NIAMS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dynamic prediction of causal effects under different treatment regimens is an essential problem in precision medicine. It is challenging because the actual mechanisms of treatment assignment and effects are unknown in observational studies. We propose a multivariate generalized linear mixed-effects model and a Bayesian g-computation algorithm to calculate the posterior distribution of subgroup-specific intervention benefits of dynamic treatment regimes. Unmeasured time-invariant factors are included as subject-specific random effects in the assumed joint distribution of outcomes, time-varying confounders, and treatment assignments. We identify a sequential ignorability assumption conditional on treatment assignment heterogeneity, that is, analogous to balancing the latent treatment preference due to unmeasured time-invariant factors. We present a simulation study to assess the proposed method’s performance. The method is applied to observational clinical data to investigate the efficacy of continuously using mycophenolate in different subgroups of scleroderma patients.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bayes TheoremComputer SimulationAlgorithmsHumansLinear ModelsCausalityMycophenolic AcidMultivariate AnalysisPrecision MedicineObservational Studies as TopicBiometry

Stichwörter der Autor:innen

g-computation algorithmlatent variable modelinglongitudinal causal inferencemixed-effects models

Substanzen

Mycophenolic Acid

Autor:innen und Institutionen

  • Division of Biostatistics, Department of Population Health Sciences, University of Utah, Salt Lake City, UT 84108, United States.
  • Division of Rheumatology, School of Medicine, Johns Hopkins University, Baltimore, MD 21224, United States.
  • Department of Biostatistics, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD 21205, United States.

ORCID-Profile: Yizhen Xu

Förderung

  • NIAMS NIH HHS
  • NIH HHS
  • NIH/NIAMS
  • NIH

Zitieren

APA

Xu, Y., Kim, J. S., Hummers, L. K., Shah, A. A., & Zeger, S. L. (2024). Causal inference using multivariate generalized linear mixed-effects models. Biometrics. https://doi.org/10.1093/biomtc/ujae100

Vancouver

Xu Y, Kim JS, Hummers LK, Shah AA, Zeger SL. Causal inference using multivariate generalized linear mixed-effects models. Biometrics. 2024. doi:10.1093/biomtc/ujae100

BibTeX
@article{Xu2024,
  author = {Xu, Yizhen and Kim, Ji Soo and Hummers, Laura K and Shah, Ami A and Zeger, Scott L},
  title = {Causal inference using multivariate generalized linear mixed-effects models},
  journal = {Biometrics},
  year = {2024},
  doi = {10.1093/biomtc/ujae100}
}
Kostenlos starten →