Quantitative bias analysis in practice: review of software for regression with unmeasured confounding

BMC Medical Research Methodology

Research

RolfH. H. Groenwold¹  Kate Tilling²  Emily Kawabata²  Rachael A. Hughes² 

[1] Department of Clinical Epidemiology, Leiden University Medical Center, Leiden, The Netherlands;Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, The Netherlands;MRC Integrative Epidemiology Unit, University of Bristol, Bristol, UK;Population Health Sciences, Bristol Medical School, University of Bristol, Bristol, UK;

关键词: Causal inference;    Quantitative bias analysis;    Sensitivity analysis;    Software review;    Unmeasured confounding;   

DOI  :  10.1186/s12874-023-01906-8

 received in 2022-11-28, accepted in 2023-03-30,  发布年份 2023

来源: Springer

【 摘 要 】

BackgroundFailure to appropriately account for unmeasured confounding may lead to erroneous conclusions. Quantitative bias analysis (QBA) can be used to quantify the potential impact of unmeasured confounding or how much unmeasured confounding would be needed to change a study’s conclusions. Currently, QBA methods are not routinely implemented, partly due to a lack of knowledge about accessible software. Also, comparisons of QBA methods have focused on analyses with a binary outcome.MethodsWe conducted a systematic review of the latest developments in QBA software published between 2011 and 2021. Our inclusion criteria were software that did not require adaption (i.e., code changes) before application, was still available in 2022, and accompanied by documentation. Key properties of each software tool were identified. We provide a detailed description of programs applicable for a linear regression analysis, illustrate their application using two data examples and provide code to assist researchers in future use of these programs.ResultsOur review identified 21 programs with 62%\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$62\%$$\end{document} created post 2016. All are implementations of a deterministic QBA with 81%\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$81\%$$\end{document} available in the free software R. There are programs applicable when the analysis of interest is a regression of binary, continuous or survival outcomes, and for matched and mediation analyses. We identified five programs implementing differing QBAs for a continuous outcome: treatSens, causalsens, sensemakr, EValue, and konfound. When applied to one of our illustrative examples, causalsens incorrectly indicated sensitivity to unmeasured confounding whereas the other four programs indicated robustness. sensemakr performs the most detailed QBA and includes a benchmarking feature for multiple unmeasured confounders.ConclusionsSoftware is now available to implement a QBA for a range of different analyses. However, the diversity of methods, even for the same analysis of interest, presents challenges to their widespread uptake. Provision of detailed QBA guidelines would be highly beneficial.

【 授权许可】

CC BY   
© The Author(s) 2023

【 图 表 】

41116_2023_36_Article_IEq284.gif

41116_2023_36_Article_IEq283.gif

41116_2023_36_Article_IEq276.gif

Fig. 1

41116_2023_36_Article_IEq274.gif

41116_2023_36_Article_IEq273.gif

41116_2023_36_Article_IEq272.gif

41116_2023_36_Article_IEq270.gif

Fig. 8

41116_2023_36_Article_IEq269.gif

41116_2023_36_Article_IEq268.gif

41116_2023_36_Article_IEq267.gif

41116_2023_36_Article_IEq266.gif

41116_2023_36_Article_IEq265.gif

Fig. 1

Fig. 1

41116_2023_36_Article_IEq260.gif

41116_2023_36_Article_IEq259.gif

41116_2023_36_Article_IEq258.gif

41116_2023_36_Article_IEq257.gif

Fig. 1

41116_2023_36_Article_IEq255.gif

41116_2023_36_Article_IEq254.gif

41116_2023_36_Article_IEq253.gif

Fig. 4

Fig. 2

Fig. 1

Fig. 1

41116_2023_36_Article_IEq247.gif

41116_2023_36_Article_IEq246.gif

41116_2023_36_Article_IEq245.gif

Fig. 3

41116_2023_36_Article_IEq242.gif

41116_2023_36_Article_IEq241.gif

41116_2023_36_Article_IEq240.gif

41116_2023_36_Article_IEq239.gif

41116_2023_36_Article_IEq238.gif

41116_2023_36_Article_IEq237.gif

Fig. 2

41116_2023_36_Article_IEq235.gif

41116_2023_36_Article_IEq234.gif

41116_2023_36_Article_IEq232.gif

41116_2023_36_Article_IEq230.gif

Fig. 7

41116_2023_36_Article_IEq229.gif

41116_2023_36_Article_IEq228.gif

41116_2023_36_Article_IEq227.gif

41116_2023_36_Article_IEq226.gif

41116_2023_36_Article_IEq225.gif

41116_2023_36_Article_IEq224.gif

41116_2023_36_Article_IEq223.gif

41116_2023_36_Article_IEq222.gif

41116_2023_36_Article_IEq220.gif

41116_2023_36_Article_IEq219.gif

Fig. 3

41116_2023_36_Article_IEq217.gif

41116_2023_36_Article_IEq216.gif

41116_2023_36_Article_IEq215.gif

41116_2023_36_Article_IEq214.gif

41116_2023_36_Article_IEq213.gif

41116_2023_36_Article_IEq212.gif

41116_2023_36_Article_IEq210.gif

41116_2023_36_Article_IEq209.gif

Fig. 1

Fig. 1

41116_2023_36_Article_IEq205.gif

Fig. 2

Fig. 1

41116_2023_36_Article_IEq202.gif

41116_2023_36_Article_IEq201.gif

Fig. 1

Fig. 1

41116_2023_36_Article_IEq198.gif

41116_2023_36_Article_IEq196.gif

41116_2023_36_Article_IEq195.gif

41116_2023_36_Article_IEq194.gif

41116_2023_36_Article_IEq193.gif

41116_2023_36_Article_IEq192.gif

41116_2023_36_Article_IEq191.gif

41116_2023_36_Article_IEq190.gif

41116_2023_36_Article_IEq189.gif

41116_2023_36_Article_IEq187.gif

Fig. 2

41116_2023_36_Article_IEq185.gif

41116_2023_36_Article_IEq184.gif

41116_2023_36_Article_IEq182.gif

41116_2023_36_Article_IEq181.gif

41116_2023_36_Article_IEq180.gif

41116_2023_36_Article_IEq179.gif

Fig. 2

41116_2023_36_Article_IEq176.gif

41116_2023_36_Article_IEq175.gif

41116_2023_36_Article_IEq174.gif

41116_2023_36_Article_IEq173.gif

41116_2023_36_Article_IEq172.gif

41116_2023_36_Article_IEq171.gif

41116_2023_36_Article_IEq170.gif

40517_2023_256_Article_IEq96.gif

41116_2023_36_Article_IEq169.gif

41116_2023_36_Article_IEq168.gif

41116_2023_36_Article_IEq167.gif

41116_2023_36_Article_IEq166.gif

41116_2023_36_Article_IEq165.gif

41116_2023_36_Article_IEq164.gif

41116_2023_36_Article_IEq163.gif

41116_2023_36_Article_IEq162.gif

41116_2023_36_Article_IEq161.gif

41116_2023_36_Article_IEq160.gif

41116_2023_36_Article_IEq159.gif

41116_2023_36_Article_IEq158.gif

41116_2023_36_Article_IEq157.gif

41116_2023_36_Article_IEq156.gif

41116_2023_36_Article_IEq155.gif

41116_2023_36_Article_IEq154.gif

40517_2023_256_Article_IEq75.gif

41116_2023_36_Article_IEq153.gif

41116_2023_36_Article_IEq152.gif

41116_2023_36_Article_IEq151.gif

Fig. 13

41116_2023_36_Article_IEq150.gif

41116_2023_36_Article_IEq149.gif

41116_2023_36_Article_IEq148.gif

41116_2023_36_Article_IEq146.gif

Fig. 1

41116_2023_36_Article_IEq145.gif

Fig. 1

41116_2023_36_Article_IEq143.gif

41116_2023_36_Article_IEq142.gif

Fig. 8

Fig. 7

Fig. 2

40517_2023_256_Article_IEq71.gif

40517_2023_256_Article_IEq68.gif

Fig. 5

41116_2023_36_Article_IEq140.gif

41116_2023_36_Article_IEq139.gif

41116_2023_36_Article_IEq138.gif

41116_2023_36_Article_IEq137.gif

41116_2023_36_Article_IEq135.gif

41116_2023_36_Article_IEq134.gif

40517_2023_256_Article_IEq58.gif

41116_2023_36_Article_IEq133.gif

41116_2023_36_Article_IEq132.gif

41116_2023_36_Article_IEq131.gif

41116_2023_36_Article_IEq130.gif

41116_2023_36_Article_IEq129.gif

41116_2023_36_Article_IEq128.gif

41116_2023_36_Article_IEq127.gif

41116_2023_36_Article_IEq126.gif

41116_2023_36_Article_IEq125.gif

41116_2023_36_Article_IEq124.gif

41116_2023_36_Article_IEq123.gif

41116_2023_36_Article_IEq122.gif

41116_2023_36_Article_IEq121.gif

41116_2023_36_Article_IEq120.gif

41116_2023_36_Article_IEq119.gif

41116_2023_36_Article_IEq118.gif

41116_2023_36_Article_IEq114.gif

41116_2023_36_Article_IEq112.gif

41116_2023_36_Article_IEq110.gif

41116_2023_36_Article_IEq109.gif

40517_2023_256_Article_IEq37.gif

41116_2023_36_Article_IEq106.gif

41116_2023_36_Article_IEq105.gif

41116_2023_36_Article_IEq104.gif

41116_2023_36_Article_IEq103.gif

41116_2023_36_Article_IEq102.gif

41116_2023_36_Article_IEq100.gif

41116_2023_36_Article_IEq99.gif

41116_2023_36_Article_IEq98.gif

40517_2023_256_Article_IEq1.gif

Fig. 2

40517_2023_256_Article_IEq204.gif

Fig. 7