Cover Bills

Causal mediation analysis has gained increasing attention in recent years. This article guides empirical researchers through the concepts and challenges of causal mediation analysis. I first clarify the difference between traditional and causal mediation analysis and highlight the importance of adjusting for the treatment-by-mediator interaction and confounders of the treatment–mediator, treatment–outcome, and mediator–outcome relationships. I then introduce the definition of causal mediation effects under the potential outcomes framework and different methods for the identification and estimation of the effects. After that, I highlight the importance of conducting a sensitivity analysis to assess the sensitivity of analysis results to potential unmeasured confounding. I also list various statistical software that can conduct causal mediation analysis and sensitivity analysis and provide suggestions for writing a causal mediation analysis paper. Finally, I briefly introduce some extensions that I made with my colleagues, including power analysis, multisite causal mediation analysis, causal moderated mediation analysis, and relaxing the assumption of no post-treatment confounding.

BackgroundMediation analysis methodology underwent many advancements throughout the years, with the most recent and important advancement being the development of causal mediation analysis based on the counterfactual framework. However, a previous review showed that for experimental studies the uptake of causal mediation analysis remains low. The aim of this paper is to review the methodological characteristics of mediation analyses performed in observational epidemiologic studies published between 2015 and 2019 and to provide recommendations for the application of mediation analysis in future studies.MethodsWe searched the MEDLINE and EMBASE databases for observational epidemiologic studies published between 2015 and 2019 in which mediation analysis was applied as one of the primary analysis methods. Information was extracted on the characteristics of the mediation model and the applied mediation analysis method.ResultsWe included 174 studies, most of which applied traditional mediation analysis methods (n = 123, 70.7%). Causal mediation analysis was not often used to analyze more complicated mediation models, such as multiple mediator models. Most studies adjusted their analyses for measured confounders, but did not perform sensitivity analyses for unmeasured confounders and did not assess the presence of an exposure-mediator interaction.ConclusionsTo ensure a causal interpretation of the effect estimates in the mediation model, we recommend that researchers use causal mediation analysis and assess the plausibility of the causal assumptions. The uptake of causal mediation analysis can be enhanced through tutorial papers that demonstrate the application of causal mediation analysis, and through the development of software packages that facilitate the causal mediation analysis of relatively complicated mediation models.

Resistance training increases muscle size (i.e., causes hypertrophy) and muscle strength, particularly in untrained individuals. Hypertrophy is widely believed to be one of the mechanisms (i.e., a mediator) by which resistance training increases strength. However, some researchers have questioned whether training-induced hypertrophy causes increases in strength. One approach to resolving this issue has been to use correlations between training-induced changes in muscle size and strength to infer the effect of hypertrophy on strength. This is problematic because correlations between changes in muscle size and strength may be confounded (i.e., correlation is not causation). Another approach has involved randomizing participants to different volumes of exercise to create different levels of hypertrophy and then comparing the strength increases associated with different levels of hypertrophy. This approach is also problematic because the unit of randomization is exercise volume rather than hypertrophy, and the potential for confounding remains. Thus, a new approach is needed to determine the extent to which hypertrophy increases muscle strength. Here, we introduce resistance training researchers to causal mediation analysis and recommend that it be used to resolve the current debate. Causal mediation analysis potentially provides an unconfounded estimate of the effect of a mediating variable (hypertrophy) on an outcome (strength). This analysis is supplemented by causal maps that help conceptualize research questions and identify potential confounders. In addition to resolving the debate on hypertrophy, causal mediation analysis can be used to answer a host of other questions about mechanisms in the health sciences.

Causal mediation analysis provides an attractive framework for integrating diverse types of exposure, genomic, and phenotype data. Recently, this field has seen a surge of interest, largely driven by the increasing need for causal mediation analyses in health and social sciences. This article aims to provide a review of recent developments in mediation analysis, encompassing mediation analysis of a single mediator and a large number of mediators, as well as mediation analysis with multiple exposures and mediators. Our review focuses on the recent advancements in statistical inference for causal mediation analysis, especially in the context of high-dimensional mediation analysis. We delve into the complexities of testing mediation effects, especially addressing the challenge of testing a large number of composite null hypotheses. Through extensive simulation studies, we compare the existing methods across a range of scenarios. We also include an analysis of data from the Normative Aging Study, which examines DNA methylation CpG sites as potential mediators of the effect of smoking status on lung function. We discuss the pros and cons of these methods and future research directions.

Causal mediation analysis is the study of mechanisms—variables measured between a treatment and an outcome that partially explain their causal relationship. The past decade has seen an explosion of research in causal mediation analysis, resulting in both conceptual and methodological advancements. However, many of these methods have been out of reach for applied quantitative researchers, due to their complexity and the difficulty of implementing them in standard statistical software distributions. The mediation package in R provides a set of simple commands that execute some of the newer causal mediation methods. This article will summarize some of the recent advances in mediation analysis, critically review the mediation package, and demonstrate, by example, some of its capabilities.

Background: People with psychosis have a reduced life expectancy by 15 years, mainly due to preventable physical illnesses for which obesity is a precursor. Obesity is three times more common in psychosis and antipsychotics are an important cause. Prediction could individualise obesity treatment but current models are not fully actionable for individuals.Aims: We test whether antipsychotic-induced weight increase at 1 year is causally mediated by weight change in the first 12 weeks of treatment, rather than the following 40 weeks. We then develop and internally validate a causal actionable prediction pathway to prevent antipsychotic-induced obesity.Methods: We use parallel causal mediation analysis to determine the natural direct and indirect, and total effects of antipsychotic choice on weight in a trial of olanzapine versus haloperidol in 97 participants. We develop a baseline causal actionable prediction model to predict weight gain at 12 weeks in 172 participants, and a 12-week model to predict obesity at 1 year in 97 of the participants, and then demonstrate counterfactual prediction.Results: Antipsychotic-induced weight gain at 1 year appears to be causally mediated by weight change during the first 12 weeks treatment – indirect effect 5.70 (95% CI 2.83 to 8.66). At internal validation, the discrimination c-statistic for the baseline causal actionable prediction model was 0.732 and the calibration slope was 0.768. For the 12-week model, the c-statistic was 0.914 and the calibration slope was 0.601. We use the models to predict the counterfactual outcomes of antipsychotic choice and 12-week weight change.Conclusions: Our study shows it may be early, rather than later weight change, which causally mediates antipsychotic-induced weight gain at 1 year. We also demonstrate the potential for causal prediction of counterfactuals targeting obesity for true precision medicine. Further research in larger samples is necessary before causal prediction models could be applied clinically.

Traditional mediation analysis, which relies on linear regression models, has faced criticism due to its limited suitability for cases involving different types of variables and complex covariates, such as interactions. This can result in unclear definitions of direct and indirect effects. As an alternative, causal mediation analysis using the counterfactual framework has been introduced to provide clearer definitions of direct and indirect effects while allowing for more flexible modeling methods. However, the conceptual understanding of this approach based on the counterfactual framework remains challenging for applied researchers. To address this issue, the present article was written to highlight and illustrate the definitions of causal estimands, including controlled direct effect, natural direct effect, and natural indirect effect, based on the key concept of nested counterfactuals. Furthermore, we recommend using 2 R packages, ‘medflex’ and ‘mediation’, to perform causal mediation analysis and provide public health examples. The article also offers caveats and guidelines for accurate interpretation of the results.

Background:Surgical interventions allow for tailoring of treatment to individual patients and implementation may vary with surgeon and healthcare provider. In addition, in clinical trials assessing two competing surgical interventions, the treatments may be accompanied by co-interventions.Aims:This study explores the use of causal mediation analysis to (1) delineate the treatment effect that results directly from the surgical intervention under study and the indirect effect acting through a co-intervention and (2) to evaluate the benefit of the surgical intervention if either everybody in the trial population received the co-intervention or nobody received it.Methods:Within a counterfactual framework, relevant direct and indirect effects of a surgical intervention are estimated and adjusted for confounding via parametric regression models, for the situation where both mediator and outcome are binary, with baseline stratification factors included as fixed effects and surgeons as random intercepts. The causal difference in probability of a successful outcome (estimand of interest) is calculated using Monte Carlo simulation with bootstrapping for confidence intervals. Packages for estimation within standard statistical software are reviewed briefly. A step by step application of methods is illustrated using the Amaze randomised trial of ablation as an adjunct to cardiac surgery in patients with irregular heart rhythm, with a co-intervention (removal of the left atrial appendage) administered to a subset of participants at the surgeon’s discretion. The primary outcome was return to normal heart rhythm at one year post surgery.Results:In Amaze, 17% (95% confidence interval: 6%, 28%) more patients in the active arm had a successful outcome, but there was a large difference between active and control arms in the proportion of patients who received the co-intervention (55% and 30%, respectively). Causal mediation analysis suggested that around 1% of the treatment effect was attributable to the co-intervention (16% natural direct effect). The controlled direct effect ranged from 18% (6%, 30%) if the co-intervention were mandated, to 14% (2%, 25%) if it were prohibited. Including age as a moderator of the mediation effects showed that the natural direct effect of ablation appeared to decrease with age.Conclusions:Causal mediation analysis is a useful quantitative tool to explore mediating effects of co-interventions in surgical trials. In Amaze, investigators could be reassured that the effect of the active treatment, not explainable by differential use of the co-intervention, was significant across analyses.

Frailty as a mediator of postoperative delirium in older adults undergoing orthopedic surgery: A causal mediation analysis

BackgroundCausal mediation, a quantitative analysis method, has the potential to be a valuable addition to any primary care provider, researcher, or student’s toolbox.ObjectiveThis manuscript describes the theory behind causal mediation, provides a running example to help understand the application of this method in research, and explains how the results may be applied practically to help design appropriate interventions.Methods and applicationCausal mediation allows an exploration of the mechanism of action of a primary care intervention on an outcome that may pass through a third variable that is on the causal pathway, a mediator. Causal mediation analysis allows the decomposition of the total effect of an intervention on an outcome into both direct and indirect effects. Careful interpretation of generated results can guide decision-makers when devising or refining interventions or policies that affect patient health outcomes in primary care.ConclusionCausal mediation has been used in many disciplines and is well-positioned to answer varied research questions. However, the full extent of its potential has yet to be realized.

Causal Mediation Analysis

Posttraumatic stress disorder (PTSD) is associated with neuroendocrine alterations and metabolic abnormalities; however, how metabolism is affected by neuroendocrine disturbances is unclear. The data from combat-exposed veterans with PTSD show increased glycolysis to lactate flux, reduced TCA cycle flux, impaired amino acid and lipid metabolism, insulin resistance, inflammation, and hypersensitive hypothalamic-pituitary-adrenal (HPA) axis. To analyze whether the co-occurrence of multiple metabolic abnormalities is independent or arises from an underlying regulatory defect, we employed a systems biological approach using an integrated mathematical model and multiomic analysis. The models for hepatic metabolism, HPA axis, inflammation, and regulatory signaling were integrated to perform metabolic control analysis (MCA) with respect to the observations from our clinical data. We combined the metabolomics, neuroendocrine, clinical laboratory, and cytokine data from combat-exposed veterans with and without PTSD to characterize the differences in regulatory effects. MCA revealed mechanistic association of the HPA axis and inflammation with metabolic dysfunction consistent with PTSD. This was supported by the data using correlational and causal analysis that revealed significant associations between cortisol suppression, high-sensitivity C-reactive protein, homeostatic model assessment of insulin resistance, γ-glutamyltransferase, hypoxanthine, and several metabolites. Causal mediation analysis indicates that the effects of enhanced glucocorticoid receptor sensitivity (GRS) on glycolytic pathway, gluconeogenic and branched-chain amino acids, triglycerides, and hepatic function are jointly mediated by inflammation, insulin resistance, oxidative stress, and energy deficit. Our analysis suggests that the interventions to normalize GRS and inflammation may help to manage features of metabolic dysfunction in PTSD.

Background/Introduction Educational interventions have been developed and tested in an attempt to improve health-related quality of life (HRQOL) for patients with heart failure (HF). While some have shown satisfactory results, the mechanism of the intervention effect on HRQOL remains unclear. Purpose To explore whether HF knowledge, self-care behaviours, self-care maintenance, self-care confidence, or social support mediates the effect of intervention on HRQOL of patients with HF Methods We analysed data from a randomized controlled trial testing the effect of an educational intervention for patients with HF. The intervention group (n=60) received 1-hour single session education followed by 8-week telephone follow-ups, and the control group (n=62) received care as usual. Study variables were measured at baseline and at 3 and 6 months. Using causal mediation analysis described by Valeri & VanderWeele (2013), we explored the causal pathway between intervention allocation and HRQOL at 6 months with HF knowledge, self-care behaviours, self-care maintenance, self-care confidence, and social support measured at 3 months as potential mediators (Figure 1). Results Intervention allocation was significantly associated with HF knowledge, self-care behaviours, self-care maintenance, and self-care confidence at 3 months (all p<0.05), but not with social support at 3 months (p=0.57). In unadjusted models, none of the potential mediators had a significant indirect effect between intervention and HRQOL. When adjusting for age and gender, the indirect effect of self-care behaviours on 6-month HRQOL became significant (indirect effect −6.24, 95% CI: −12.88 to −1.18). When baseline values of the mediator and HRQOL were adjusted in addition to age and gender, the indirect effect of self-care behaviours remained significant (indirect effect −7.18, 95% CI: −13.48 to −2.35) and the indirect effect of self-care maintenance became significant (indirect effect −3.02, 95% CI: −7.94 to −0.07). Conclusion Our findings support the mediating role of self-care behaviours on the relationship between the educational intervention and HRQOL of patients with HF. In order to successfully improve HRQOL of patients with HF, educational interventions should aim to promote self-care behaviours, especially by encouraging treatment adherence and self-monitoring. Funding Acknowledgement Type of funding sources: Public Institution(s). Main funding source(s): Seoul National University, College of Medicine Figure 1. Mediation model

Online retailers worldwide invest beyond their core business of retailing to offer their own delivery services (ODS) to deliver products to customers’ homes through their own logistics network. How does this shift to ODS affect customers’ behaviors and sales performance? When and why do retailers venture beyond their core competence to offer ODS? To explore these questions, the authors analyze 250,055 customer transactions over 10 years across 416 cities and 49 product categories from JD, a major online retailer in China. Using difference-in-differences models, causal mediation analysis, and the synthetic control method, they find that ODS increases customers’ monthly spending by 7.8% and grows city-level sales by 11.9%. This study is the first to quantify the sales impact of ODS and shed light on when and why it works. The findings reveal that ODS has greater value for markets with lower trust levels, infrequent customers, high-risk product categories, and consumers who prefer the focal retailer (versus that of third-party sellers). Causal mediation analysis further reveals that ODS not only improves delivery quality but also builds customer trust, which together increase customers’ monthly spending, purchase frequency, and the number of items ordered.

Obstructive sleep apnea, chronic obstructive pulmonary disease and NAFLD: an individual participant data meta-analysis