Mediational g-formula for time-varying treatment and repeated-measured multiple mediators: Application to atorvastatin’s effect on cardiovascular disease via cholesterol lowering and anti-inflammatory actions in elderly type 2 diabetics

Abstract

Modern causal mediation theory has formalized several types of indirect and direct effects of treatment on outcomes regarding specific mediator variables. We reviewed and unified distinct approaches to estimate the “interventional” direct and indirect effects for multiple mediators and time-varying variables. This study was motivated by a clinical trial of elderly type-2 diabetic patients in which atorvastatin was widely prescribed to control patients’ cholesterol levels to reduce diabetic complications, including cardiovascular disease. Among atorvastatin’s preventive side-effects (pleiotropic effects), we focus on its anti-inflammatory action as measured by white blood cell counts. Hence, we estimate atorvastatin’s interventional indirect effects through cholesterol lowering and through anti-inflammatory action, and interventional direct effect bypassing these two actions. In our analysis, total effect (six-year cardiovascular disease risk difference) estimated by standard plug-in g-formula of −3.65% (95% confidence interval: −10.29%, 4.38%) is decomposed into indirect effect via low-density lipoprotein cholesterol (−0.90% [−1.91%, −0.07%]), via white blood cell counts (−0.03% [−0.22%, 0.11%]), and direct effect (−2.84% [−9.71%, 5.41%]) by the proposed parametric mediational g-formula. The SAS program and its evaluation via simulated datasets are provided in the Supplemental materials.

Keywords

g-formula longitudinal data mediation analysis time-to-event analysis time-varying confounding

Get full access to this article

View all access options for this article.

References

Robins

JM.

The control of confounding by intermediate variables.

Stat Med 1989; 8: 679–701.

Robins

Greenland

Identifiability and exchangeability for direct and indirect effects.

Epidemiology 1992; 3: 143–155.

Pearl

Direct and indirect effects. In: Proceedings of the seventeenth conference on uncertainty in artificial intelligence. San Francisco, CA: Morgan Kaufmann, 2001, pp.411–420.

Robins

JM.

Semantics of causal DAG models and the identification of direct and indirect effects. In: Hjort

Green

Richardson

(eds) Highly structured stochastic systems. Oxford: Oxford University Press, 2003, pp.70–81.

Didelez

Dawid

Geneletti

Direct and indirect effects of sequential treatments. In: Shrout

(ed.) Proceedings of the 22nd annual conference on uncertainty in artificial intelligence, 2006, pp.138–146.

VanderWeele

Vansteelandt

Robins

JM.

Effect decomposition in the presence of an exposure-induced mediator-outcome confounder.

Epidemiology 2014; 25: 300–306.

Naimi

Moodie

Auger

, et al. Stochastic mediation contrasts in epidemiologic research: interpregnancy interval and the educational disparity in preterm delivery. Am J Epidemiol 2014; 180: 436–445.

Rudolph

Goin

Paksarian

, et al. Causal mediation analysis with observational data: considerations and illustration examining mechanisms linking neighborhood poverty to adolescent substance use. Am J Epidemiol 2019; 188: 598–608.

VanderWeele

TJ.

Explanation in causal inference: methods for mediation and interaction. Oxford: Oxford University Press, 2015.

10.

Robins

Richardson

TS.

Alternative graphical causal models and the identification of direct effects. In: Shrout

Keyes

Ornstein

(eds) Causality and psychopathology: finding the determinants of disorders and their cures. New York, NY: Oxford University Press, 2010, pp.103–158.

11.

American Diabetes Association. Standards of medical care for patients with diabetes—2018. Diabetes Care 2018; 41: S1–S155.

12.

Robinson

Smith

Maheshwari

, et al. Pleiotropic effects of statins: benefit beyond cholesterol reduction? A meta-regression analysis. J Am Coll Cardiol 2005; 46: 1855–1862.

13.

Cholesterol Treatment Trialists’ (CTT) Collaborators. The effects of lowering LDL cholesterol with statin therapy in people at low risk of vascular disease: meta-analysis of individual data from 27 randomised trials. Lancet 2012; 380: 581–590.

14.

Shinozaki

Matsuyama

Iimuro

, et al. Effective prevention of cardiovascular disease and diabetes-related events with atorvastatin in Japanese elderly patients with type 2 diabetes mellitus: adjusting for treatment changes using a marginal structural proportional hazards model and a rank-preserving structural failure time model. Geriatr Gerontol Int 2012; 12: 88–102.

15.

Talbot

Delaney

JAC

Sandfort

, et al. Importance of the lipid-related pathways in the association between statins, mortality, and cardiovascular disease risk: the Multi-Ethnic Study of Atherosclerosis. Pharmacoepidemiol Drug Safe 2018; 27: 365–372.

16.

Nissen

Tuzcu

Schoenhagen

, et al. Statin therapy, LDL cholesterol, C-reactive protein, and coronary artery disease. N Engl J Med 2005; 352: 29–38.

17.

Ridker

Danielson

Fonseca

, et al. Reduction in C-reactive protein and LDL cholesterol and cardiovascular event rates after initiation of rosuvastatin: a prospective study of the JUPITER trial. Lancet 2009; 373: 1175–1182.

18.

Everett

Glynn

MacFadyen

, et al. Rosuvastatin in the prevention of stroke among men and women with elevated levels of C-reactive protein: justification for the use of statins in prevention: an Intervention Trial Evaluating Rosuvastatin (JUPITER). Circulation 2010; 121: 143–150.

19.

Taguri

Featherstone

Cheng

Causal mediation analysis with multiple causally non-ordered mediators.

Stat Meth Med Res 2018; 27: 3–19.

20.

Bellavia

Valeri

Decomposition of the total effect in the presence of multiple mediators and interactions. Am J Epidemiol 2018; 187: 1311–1318.

21.

VanderWeele

Vansteelandt

Mediation analysis with multiple mediators. Epidemiol Meth 2014; 2: 95–115.

22.

Daniel

De Stavola

Cousens

, et al. Causal mediation analysis with multiple mediators. Biometrics 2015; 71: 1–14.

23.

Vansteelandt

Daniel

RM.

Interventional effects for mediation analysis with multiple mediators. Epidemiology 2017; 28: 258–265.

24.

Shinozaki

Matsuyama

Ohashi

Estimation of controlled direct effects in time-varying treatments using structural nested mean models: application to a primary prevention trial for coronary events with pravastatin.

Stat Med 2014; 33: 3214–3228.

25.

VanderWeele

Tchetgen Tchetgen

EJ.

Mediation analysis with time varying exposures and mediators.

J Roy Stat Soc Ser B 2017; 79: 917–938.

26.

Lin

Young

Logan

, et al. Parametric mediational g-formula approach to mediation analysis with time-varying exposures, mediators, and confounders. Epidemiology 2017; 28: 266–274.

27.

Lin

Young

Logan

, et al. Mediation analysis for a survival outcome with time-varying exposures, mediators, and confounders. Stat Med 2017; 36: 4153–4166.

28.

Robins

JM.

Association, causation, and marginal structural models. Synthese 1999; 121: 151–179.

29.

VanderWeele

TJ.

Marginal structural models for the estimation of direct and indirect effects.

Epidemiology 2009; 20: 18–26.

30.

Robins

JM.

Testing and estimation of direct effects by reparameterizing directed acyclic graphs with structural nested models. In: Glymour

Cooper

(eds) Computation, causation, and discovery. AAAI Press/The MIT Press: Menlo Park, CA, 1999, pp.349–405.

31.

Araki

Iimuro

Sakurai

, et al. Long-term multiple risk factor interventions in Japanese elderly diabetic patients: the Japanese Elderly Diabetes Intervention Trial–study design, baseline characteristics and effects of intervention. Geriatr Gerontol Int 2012; 12: S7–S17.

32.

Taubman

Robins

Mittleman

, et al. Intervening on risk factors for coronary heart disease: an application of the parametric g-formula. Int J Epidemiol 2009; 38: 1599–1611.

33.

Miles

Kanki

Meloni

, et al . On partial identification of the natural indirect effect. J Causal Inference 2017; 5: 20160004.

34.

Young

Cain

Robins

, et al. Comparative effectiveness of dynamic treatment regimes: an application of the parametric g-formula. Stat Biosci 2011; 3: 119–143.

35.

Strohmaier

Roysland

Hoff

, et al. Dynamic path analysis: a useful tool to investigate mediation processes in clinical survival trials. Stat Med 2015; 34: 3866–3887.

36.

Vansteelandt

Linder

Vandenberghe

, et al. Mediation analysis of time-to-event endpoints accounting for repeatedly measured mediators subject to time-varying confounding. Stat Med 2019; 38: 4828–4840.

37.

Lin

VanderWeele

Interventional approach for path-specific effects. J Causal Inference 2017; 5: 20150027.

38.

Robins

Wasserman

Estimation of effects of sequential treatments by reparameterizing directed acyclic graphs. In: Proceedings of the thirteenth conference on uncertainty in artificial intelligence, 1997, pp.409–420. https://dl.acm.org/doi/proceedings/10.5555/2074226

39.

Petersen

Porter

, S Gruber, et al.

Diagnosing and responding to violations in the positivity assumption.

Stat Meth Med Res 2012; 21: 31–54.

40.

Aalen

Røysland

Gran

, et al. Can we believe the DAGs? A comment on the relationship between causal DAGs and mechanisms. Stat Meth Med Res 2016; 25: 2294–2314.

41.

Aalen

Gran

Røysland

, et al. Feedback and mediation in causal inference illustrated by stochastic process models. Scand Stat Theory Appl 2018; 45: 62–86.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.11 MB

0.00 MB

0.39 MB