Explore the vast range of titles available.

Background Mediation 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. Methods We 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. Results We 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. Conclusions To 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.

Background Logistic regression is often used for mediation analysis with a dichotomous outcome. However, previous studies showed that the indirect effect and proportion mediated are often affected by a change of scales in logistic regression models. To circumvent this, standardization has been proposed. The aim of this study was to show the relative performance of the unstandardized and standardized estimates of the indirect effect and proportion mediated based on multiple regression, structural equation modeling, and the potential outcomes framework for mediation models with a dichotomous outcome. Methods We compared the performance of the effect estimates yielded by the three methods using a simulation study and two real-life data examples from an observational cohort study ( n  = 360). Results Lowest bias and highest efficiency were observed for the estimates from the potential outcomes framework and for the crude indirect effect ab and the proportion mediated ab /( ab  +  c’ ) based on multiple regression and SEM. Conclusions We advise the use of either the potential outcomes framework estimates or the ab estimate of the indirect effect and the ab /( ab  +  c’ ) estimate of the proportion mediated based on multiple regression and SEM when mediation analysis is based on logistic regression. Standardization of the coefficients prior to estimating the indirect effect and the proportion mediated may not increase the performance of these estimates.

Background Confounding bias is a common concern in epidemiological research. Its presence is often determined by comparing exposure effects between univariable- and multivariable regression models, using an arbitrary threshold of a 10% difference to indicate confounding bias. However, many clinical researchers are not aware that the use of this change-in-estimate criterion may lead to wrong conclusions when applied to logistic regression coefficients. This is due to a statistical phenomenon called noncollapsibility, which manifests itself in logistic regression models. This paper aims to clarify the role of noncollapsibility in logistic regression and to provide guidance in determining the presence of confounding bias. Methods A Monte Carlo simulation study was designed to uncover patterns of confounding bias and noncollapsibility effects in logistic regression. An empirical data example was used to illustrate the inability of the change-in-estimate criterion to distinguish confounding bias from noncollapsibility effects. Results The simulation study showed that, depending on the sign and magnitude of the confounding bias and the noncollapsibility effect, the difference between the effect estimates from univariable- and multivariable regression models may underestimate or overestimate the magnitude of the confounding bias. Because of the noncollapsibility effect, multivariable regression analysis and inverse probability weighting provided different but valid estimates of the confounder-adjusted exposure effect. In our data example, confounding bias was underestimated by the change in estimate due to the presence of a noncollapsibility effect. Conclusion In logistic regression, the difference between the univariable- and multivariable effect estimate might not only reflect confounding bias but also a noncollapsibility effect. Ideally, the set of confounders is determined at the study design phase and based on subject matter knowledge. To quantify confounding bias, one could compare the unadjusted exposure effect estimate and the estimate from an inverse probability weighted model.

Background Evidence has not been conclusive on whether adolescent overweight is associated with mental health, possibly caused by indirect, yet untested associations. Therefore, the purpose of this study was to examine the association between overweight or obesity and mental health problems among adolescents, and to determine whether victimization plays a mediating role in these associations. Methods Self-reported data on mental health and victimization and objectively measured Body Mass Index data were used, using three cohorts (2010–2011 until 2012–2013) and an interval between the measurement waves of two years later. We performed a multi-level mediation analysis with a two-level structure to incorporate the clustering of the measurements within individuals. The study population consisted of 13,740 secondary school students, 13–14 years old at the first measurement moment, in Amsterdam, the Netherlands. Results Compared to their normal-weight peers, adolescents with overweight or obesity reported psychosocial problems and suicidal thoughts more often. Victimization was a significant mediator in the relationship between having overweight, and psychosocial problems (indirect effect OR: 2.3; 95% CI 1.5, 3.7 and direct effect OR: 1.4; 95% CI 1.2, 1.7) or suicidal thoughts (indirect effect OR: 2.1; 95% CI 1.4, 3.2 and direct effect OR: 1.3; 95% CI 1.1, 1.5). The associations between obesity, and psychosocial problems (indirect OR: 6.2; 95% CI 2.8, 14.7 and direct effect OR: 1.4; 95% CI 1.0, 2.0), or suicidal thoughts (indirect OR: 4.5; 95% CI 2.3, 9.1 and direct effect OR: 1.5; 95% CI 1.1, 2.0) were even stronger. Conclusions Overweight and obesity were significantly associated with mental health problems in adolescents, and victimization played a mediating role in this association. Victimization and mental health should be integrated into prevention programs that address healthy weight development. Moreover, overweight should be given more attention in programs to prevent victimization and promote adolescent mental health.

Background Confounding is a common issue in epidemiological research. Commonly used confounder-adjustment methods include multivariable regression analysis and propensity score methods. Although it is common practice to assess the linearity assumption for the exposure-outcome effect, most researchers do not assess linearity of the relationship between the confounder and the exposure and between the confounder and the outcome before adjusting for the confounder in the analysis. Failing to take the true non-linear functional form of the confounder-exposure and confounder-outcome associations into account may result in an under- or overestimation of the true exposure effect. Therefore, this paper aims to demonstrate the importance of assessing the linearity assumption for confounder-exposure and confounder-outcome associations and the importance of correctly specifying these associations when the linearity assumption is violated. Methods A Monte Carlo simulation study was used to assess and compare the performance of confounder-adjustment methods when the functional form of the confounder-exposure and confounder-outcome associations were misspecified (i.e., linearity was wrongly assumed) and correctly specified (i.e., linearity was rightly assumed) under multiple sample sizes. An empirical data example was used to illustrate that the misspecification of confounder-exposure and confounder-outcome associations leads to bias. Results The simulation study illustrated that the exposure effect estimate will be biased when for propensity score (PS) methods the confounder-exposure association is misspecified. For methods in which the outcome is regressed on the confounder or the PS, the exposure effect estimate will be biased if the confounder-outcome association is misspecified. In the empirical data example, correct specification of the confounder-exposure and confounder-outcome associations resulted in smaller exposure effect estimates. Conclusion When attempting to remove bias by adjusting for confounding, misspecification of the confounder-exposure and confounder-outcome associations might actually introduce bias. It is therefore important that researchers not only assess the linearity of the exposure-outcome effect, but also of the confounder-exposure or confounder-outcome associations depending on the confounder-adjustment method used.

Purpose This study investigated the effects of psychosocial working conditions on mental health-related long-term sickness absence and whether distress, work satisfaction, burnout, engagement, and work ability mediated the associations between psychosocial working conditions and mental health-related long-term sickness absence. Methods This cohort study included 53,833 non-sick listed workers who participated in occupational health surveys between 2010 and 2013. The effects of the individual psychosocial working conditions on mental long-term sickness absence were analyzed using univariable and multivariable logistic regression analyses. Mediation analyses were performed to examine the mediating role of distress, burnout, work satisfaction, engagement, and work ability between psychosocial working conditions and mental long-term sickness absence. The mediation analyses were performed using structural equation modeling. Results Role clarity, cognitive demands, emotional demands, work variety, learning opportunities, and co-worker support were related to mental health-related long-term sickness absence after adjustment for other working conditions. The relationship between emotional demands and mental health-related long-term sickness absence was the strongest, OR 1.304 (p < 0.001, 95% CI 1.135 to 1.498). The relation between psychosocial working conditions and mental health-related long-term sickness absence was mediated by distress, burnout, work satisfaction, engagement, and work ability. Distress was the most important mediator between psychosocial working conditions and mental health-related long-term sickness absence. Conclusions Psychosocial working conditions are related to mental health-related long-term sickness absence. After correction for other working conditions, the association between emotional demands and mental health-related long-term sickness absence was the strongest. Psychosocial working conditions are indirectly related to mental health-related long-term sickness absence through mediation by distress, work satisfaction, and work ability.

There is an increasing awareness that replication should become common practice in empirical studies. However, study results might fail to replicate for various reasons. The robustness of published study results can be assessed using the relatively new multiverse-analysis methodology, in which the robustness of the effect estimates against data analytical decisions is assessed. However, the uptake of multiverse analysis in empirical studies remains low, which might be due to the scarcity of guidance available on performing multiverse analysis. Researchers might experience difficulties in identifying data analytical decisions and in summarizing the large number of effect estimates yielded by a multiverse analysis. These difficulties are amplified when applying multiverse analysis to assess the robustness of the effect estimates from a mediation analysis, as a mediation analysis involves more data analytical decisions than a bivariate analysis. The aim of this paper is to provide an overview and worked example of the use of multiverse analysis to assess the robustness of the effect estimates from a mediation analysis. We showed that the number of data analytical decisions in a mediation analysis is larger than in a bivariate analysis. By using a real-life data example from the Longitudinal Aging Study Amsterdam, we demonstrated the application of multiverse analysis to a mediation analysis. This included the use of specification curves to determine the impact of data analytical decisions on the magnitude and statistical significance of the direct, indirect, and total effect estimates. Although the multiverse analysis methodology is still relatively new and future research is needed to further advance this methodology, this paper shows that multiverse analysis is a useful method for the assessment of the robustness of the direct, indirect, and total effect estimates in a mediation analysis and thereby to inform replication studies.

Mediation analysis is an important statistical method in prevention research, as it can be used to determine effective intervention components. Traditional mediation analysis defines direct and indirect effects in terms of linear regression coefficients. It is unclear how these traditional effects are estimated in settings with binary variables. An important recent methodological advancement in the mediation analysis literature is the development of the causal mediation analysis framework. Causal mediation analysis defines causal effects as the difference between two potential outcomes. These definitions can be applied to any mediation model to estimate natural direct and indirect effects, including models with binary variables and an exposure–mediator interaction. This paper aims to clarify the similarities and differences between the causal and traditional effect estimates for mediation models with a binary mediator and a binary outcome. Causal and traditional mediation analyses were applied to an empirical example to demonstrate these similarities and differences. Causal and traditional mediation analysis provided similar controlled direct effect estimates, but different estimates of the natural direct effects, natural indirect effects, and total effect. Traditional mediation analysis methods do not generalize well to mediation models with binary variables, while the natural effect definitions can be applied to any mediation model. Causal mediation analysis is therefore the preferred method for the analysis of mediation models with binary variables.

Background Quality of life (QoL) is an important outcome from the perspective of patients and their caregivers, in both dementia and pre-dementia stages. Yet, little is known about the long-term changes in QoL over time. We aimed to compare the trajectories of QoL between amyloid-positive and amyloid-negative SCD or MCI patients and to evaluate QoL trajectories along the Alzheimer’s disease (AD) continuum of cognitively normal to dementia. Methods We included longitudinal data of 447 subjective cognitive decline (SCD), 276 mild cognitive impairment (MCI), and 417 AD dementia patients from the Amsterdam Dementia Cohort. We compared QoL trajectories (EQ-5D and visual analog scale (VAS)) between (1) amyloid-positive and amyloid-negative SCD or MCI patients and (2) amyloid-positive SCD, MCI, and dementia patients with linear mixed-effect models. The models were adjusted for age, sex, Charlson Comorbidity Index (CCI), education, and EQ-5D scale (3 or 5 level). Results In SCD, amyloid-positive participants had a higher VAS at baseline but showed a steeper decline over time in EQ-5D and VAS than amyloid-negative participants. Also, in MCI, amyloid-positive patients had higher QoL at baseline but subsequently showed a steeper decline in QoL over time compared to amyloid-negative patients. When we compared amyloid-positive patients along the Alzheimer continuum, we found no difference between SCD, MCI, or dementia in baseline QoL, but QoL decreased at a faster rate in the dementia stage compared with the of SCD and MCI stages. Conclusions QoL decreased at a faster rate over time in amyloid-positive SCD or MCI patients than amyloid-negative patients. QoL decreases over time along the entire AD continuum of SCD, MCI and dementia, with the strongest decrease in dementia patients. Knowledge of QoL trajectories is essential for the future evaluation of treatments in AD.

Background Patients and caregivers express a desire for accurate prognostic information about time to institutionalization and mortality. Previous studies predicting institutionalization and mortality focused on the dementia stage. However, Alzheimer’s disease (AD) is characterized by a long pre-dementia stage. Therefore, we developed prediction models to predict institutionalization and mortality along the AD continuum of cognitively normal to dementia. Methods This study included SCD/MCI patients (subjective cognitive decline (SCD) or mild cognitive impairment (MCI)) and patients with AD dementia from the Amsterdam Dementia Cohort. We developed internally and externally validated prediction models with biomarkers and without biomarkers, stratified by dementia status. Determinants were selected using backward selection ( p <0.10). All models included age and sex. Discriminative performance of the models was assessed with Harrell’s C statistics. Results We included n=1418 SCD/MCI patients ( n =123 died, n =74 were institutionalized) and n =1179 patients with AD dementia ( n =413 died, n =453 were institutionalized). For both SCD/MCI and dementia stages, the models for institutionalization and mortality included after backward selection clinical characteristics, imaging, and cerebrospinal fluid (CSF) biomarkers. In SCD/MCI, the Harrell’s C-statistics of the models were 0.81 (model without biomarkers: 0.76) for institutionalization and 0.79 (model without biomarker: 0.76) for mortality. In AD-dementia, the Harrell’s C-statistics of the models were 0.68 (model without biomarkers: 0.67) for institutionalization and 0.65 (model without biomarker: 0.65) for mortality. Models based on data from amyloid-positive patients only had similar discrimination. Conclusions We constructed prediction models to predict institutionalization and mortality with good accuracy for SCD/MCI patients and moderate accuracy for patients with AD dementia. The developed prediction models can be used to provide patients and their caregivers with prognostic information on time to institutionalization and mortality along the cognitive continuum of AD.