Adjustment for duration of employment in occupational epidemiology

PURPOSE

In occupational epidemiology, the healthy worker survivor effect can manifest as a time-dependent confounder because healthier workers can accrue greater amounts of exposure over longer periods of employment. For example, in occupational studies of radiation exposure that focus on cumulative annualized radiation dose, workers can accrue greater amounts of cumulative radiation exposure over longer periods of employment, while workers with longer periods of employment can transition into jobs with a reduced potential for annualized radiation exposure. The extent to which confounding arising from the healthy worker survivor effect impacts radiation risk estimates is unknown.

METHODS

We assessed the impact of the healthy worker survivor effect on estimates of radiation risk among nuclear workers in a Million Person Study cohort. In simulation studies, we contrasted the ability of marginal structural Cox models with inverse probability weighting and Cox proportional hazards models to account for time-dependent confounding arising from the healthy worker survivor effect.

RESULTS

Marginal structural Cox models and Cox proportional hazards models with flexible functional forms for duration of employment provided reliable results.

CONCLUSIONS

It is crucial to flexibly adjust for duration of employment to account for confounding arising from the healthy worker survivor effect in occupational epidemiology.

Effect of statin use for the primary prevention of cardiovascular disease among older adults: a cautionary tale concerning target trials emulation

OBJECTIVES

Evidence concerning the effect of statins in primary prevention of cardiovascular disease (CVD) among older adults is lacking. Using Quebec population-wide administrative data, we emulated a hypothetical randomized trial including older adults >65 years on April 1, 2013, with no CVD history and no statin use in the previous year.

STUDY DESIGN AND SETTING

We included individuals who initiated statins and classified them as exposed if they were using statin at least 3 months after initiation and nonexposed otherwise. We followed them until March 31, 2018. The primary outcome was the composite endpoint of coronary events (myocardial infarction, coronary bypass, and percutaneous coronary intervention), stroke, and all-cause mortality. The intention-to-treat (ITT) effect was estimated with adjusted Cox models and per-protocol effect with inverse probability of censoring weighting.

RESULTS

A total of 65,096 individuals were included (mean age = 71.0 ± 5.5, female = 55.0%) and 93.7% were exposed. Whereas we observed a reduction in the composite outcome (ITT-hazard ratio (HR) = 0.75; 95% CI: 0.68-0.83) and mortality (ITT-HR = 0.69; 95% CI: 0.61-0.77) among exposed, coronary events increased (ITT-HR = 1.46; 95% CI: 1.09-1.94). All multibias E-values were low indicating that the results were not robust to unmeasured confounding, selection, and misclassification biases simultaneously.

CONCLUSION

We cannot conclude on the effectiveness of statins in primary prevention of CVD among older adults. We caution that an in-depth reflection on sources of biases and careful interpretation of results are always required in observational studies.

Benefit and risk of oral anticoagulant initiation strategies in patients with atrial fibrillation and cancer: a target trial emulation using the SEER-Medicare database

Oral anticoagulants (OACs) are recommended for patients with atrial fibrillation (AFib) having CHA2DS2-VASc score ≥ 2. However, the benefits of OAC initiation in patients with AFib and cancer at different levels of CHA2DS2-VASc is unknown. We included patients with new AFib diagnosis and a record of cancer (breast, prostate, or lung) from the 2012-2019 Surveillance, Epidemiology, and End Results (SEER)-Medicare database (n = 39,915). Risks of stroke and bleeding were compared between 5 treatment strategies: (1) initiated OAC when CHA2DS2-VASc ≥ 1 (n = 6008), (2) CHA2DS2-VASc ≥ 2 (n = 8694), (3) CHA2DS2-VASc ≥ 4 (n = 20,286), (4) CHA2DS2-VASc ≥ 6 (n = 30,944), and (5) never initiated OAC (reference group, n = 33,907). Confounders were adjusted using inverse probability weighting through cloning-censoring-weighting approach. Weighted pooled logistic regressions were used to estimate treatment effect [hazard ratios (HRs) and 95% confidence interval (95% CIs)]. We found that only patients who initiated OACs at CHA2DS2-VASc ≥ 6 had lower risk of stroke compared without OAC initiation (HR 0.64, 95% CI 0.54-0.75). All 4 active treatment strategies had reduced risk of bleeding compared to non-initiators, with OAC initiation at CHA2DS2-VASc ≥ 6 being the most beneficial strategy (HR = 0.49, 95% CI 0.44-0.55). In patients with lung cancer or regional/metastatic cancer, OAC initiation at any CHA2DS2-VASc level increased risk of stroke and did not reduce risk of bleeding (except for Regimen 4). In conclusion, among cancer patients with new AFib diagnosis, OAC initiation at higher risk of stroke (CHA2DS2-VASc score ≥ 6) is more beneficial in preventing ischemic stroke and bleeding. Patients with advanced cancer or low life-expectancy may initiate OACs when CHA2DS2-VASc score ≥ 6.

Estimating the Effect of PrEP in Black Men Who Have Sex with Men: A Framework to Utilize Data from Multiple Non-Randomized Studies to Estimate Causal Effects

Black men who have sex with men (MSM) are disproportionately burdened by the HIV epidemic in the US. The effectiveness of pre-exposure prophylaxis (PrEP) in preventing HIV infection has been demonstrated through randomized placebo-controlled clinical trials in several populations. Importantly, no such trial has been conducted exclusively among Black MSM in the US, and it would be unethical and infeasible to do so now. To estimate the causal effects of PrEP access, initiation, and adherence on HIV risk, we utilized causal inference methods to combine data from two non-randomized studies that exclusively enrolled Black MSM. The estimated relative risks of HIV were: (i) 0.52 (95% confidence interval: 0.21, 1.22) for individuals with versus without PrEP access, (ii) 0.48 (0.12, 0.89) for individuals who initiated PrEP but were not adherent versus those who did not initiate, and (iii) 0.23 (0.02, 0.80) for individuals who were adherent to PrEP versus those who did not initiate. Beyond addressing the knowledge gap around the effect of PrEP in Black MSM in the US, which may have ramifications for public health, we have provided a framework to combine data from multiple non-randomized studies to estimate causal effects, which has broad utility.

A comprehensive review and shiny application on the matching-adjusted indirect comparison

Population-adjusted indirect comparison (PAIC) is an increasingly used technique for estimating the comparative effectiveness of different treatments for the health technology assessments when head-to-head trials are unavailable. Three commonly used PAIC methods include matching-adjusted indirect comparison (MAIC), simulated treatment comparison (STC), and multilevel network meta-regression (ML-NMR). MAIC enables researchers to achieve balanced covariate distribution across two independent trials when individual participant data are only available in one trial. In this article, we provide a comprehensive review of the MAIC methods, including their theoretical derivation, implicit assumptions, and connection to calibration estimation in survey sampling. We discuss the nuances between anchored and unanchored MAIC, as well as their required assumptions. Furthermore, we implement various MAIC methods in a user-friendly R Shiny application Shiny-MAIC. To our knowledge, it is the first Shiny application that implements various MAIC methods. The Shiny-MAIC application offers choice between anchored or unanchored MAIC, choice among different types of covariates and outcomes, and two variance estimators including bootstrap and robust standard errors. An example with simulated data is provided to demonstrate the utility of the Shiny-MAIC application, enabling a user-friendly approach conducting MAIC for healthcare decision-making. The Shiny-MAIC is freely available through the link: https://ziren.shinyapps.io/Shiny_MAIC/.

Statistical inference for time-to-event data in non-randomized cohorts with selective attrition

In multi-season clinical trials with a randomize-once strategy, patients enrolled from previous seasons who stay alive and remain in the study will be treated according to the initial randomization in subsequent seasons. To address the potentially selective attrition from earlier seasons for the non-randomized cohorts, we develop an inverse probability of treatment weighting method using season-specific propensity scores to produce unbiased estimates of survival functions or hazard ratios. Bootstrap variance estimators are used to account for the randomness in the estimated weights and the potential correlations in repeated events within each patient from season to season. Simulation studies show that the weighting procedure and bootstrap variance estimator provide unbiased estimates and valid inferences in Kaplan-Meier estimates and Cox proportional hazard models. Finally, data from the INVESTED trial are analyzed to illustrate the proposed method.

Mechanical Versus Bioprosthetic Aortic Valve Replacement in Patients Undergoing Bentall Procedure

BACKGROUND

The widely used Bentall procedure is the criterion standard treatment for aortic root pathology. Studies comparing the long-term outcomes of bioprosthetic and mechanical valves in patients undergoing the Bentall procedure are limited.

METHODS AND RESULTS

Patients who underwent the Bentall procedure with a bioprosthetic or mechanical valve between 2001 and 2018 were identified from Taiwan's National Health Insurance Research Database. The primary outcome of interest was all-cause mortality. Inverse probability of treatment weighting was performed to compare the 2 prosthetic types. In total, 1052 patients who underwent the Bentall procedure were identified. Among these patients, 351 (33.4%) and 701 (66.6%) chose bioprosthetic and mechanical valves, respectively. After inverse probability of treatment weighting, no significant differences in the in-hospital mortality (odds ratio, 0.96 [95% CI, 0.77-1.19]; P=0.716) and all-cause mortality (34.1% vs. 38.1%; hazard ratio, 0.90 [95% CI, 0.78-1.04]; P=0.154) were observed between the groups. The benefits of relative mortality associated with mechanical valves were apparent in younger patients and persisted until ≈50 years of age.

CONCLUSIONS

No differences in survival benefits were observed between the valves in patients who underwent the Bentall procedure. Additionally, bioprosthetic valves may be a reasonable choice for patients aged >50 years when receiving the Bentall procedure in this valve-in-valve era.

Impact of ACEIs and ARBs-related adverse drug reaction on patients' clinical outcomes: a cohort study in UK primary care

BACKGROUND

Adverse drug reaction (ADR) related to angiotensin-converting enzyme inhibitors (ACEIs) and angiotensin receptor blockers (ARBs) may negatively affect patients' treatment outcomes.

AIM

To investigate the impact of ACEIs/ARBs-related ADR consultation on cardiovascular disease (CVD) events and all-cause mortality.

DESIGN AND SETTING

Propensity score-matched cohort study of ACEIs/ARBs between 2004 and 2019 using UK IQVIA medical research data.

METHOD

ADR consultations were identified using standardised designated codes. Propensity scores were calculated based on comorbidities, concomitant medications, frailty, and polypharmacy. Cox's proportional hazard regression model was used to compare the outcomes between patients in ADR and non-ADR groups. In the secondary analysis, treatment- pattern changes following the ADR were examined and the subsequent outcomes were compared.

RESULTS

Among 1 471 906 eligible users of ACEIs/ARBs, 13 652 (0.93%) patients had ACEIs/ARBs- related ADR consultation in primary care. Patients with ACEIs/ARBs-related ADR consultation had an increased risk of subsequent CVD events and all- cause mortality in both primary prevention (CVD events: adjusted hazard ratio [aHR] 1.22, 95% confidence interval [CI] = 1.05 to 1.43; all-cause mortality: aHR 1.14, 95% CI = 1.01 to 1.27) and secondary prevention cohorts (CVD events: aHR 1.13, 95% CI = 1.05 to 1.21; all-cause mortality: aHR 1.15, 95% CI = 1.09 to 1.21). Half (50.19%) of patients with ADR continued to use ACEIs/ARBs, and these patients had a reduced risk of mortality (aHR 0.88, 95% CI = 0.82 to 0.95) compared with those who discontinued using ACEIs/ARBs.

CONCLUSION

This study provides information on the burden of ADR on patients and the health system. The findings call for additional monitoring and treatment strategies for patients affected by ADR to mitigate the risks of adverse clinical outcomes.

Antimicrobial exposure is associated with decreased survival in triple-negative breast cancer

Antimicrobial exposure during curative-intent treatment of triple-negative breast cancer (TNBC) may lead to gut microbiome dysbiosis, decreased circulating and tumor-infiltrating lymphocytes, and inferior outcomes. Here, we investigate the association of antimicrobial exposure and peripheral lymphocyte count during TNBC treatment with survival, using integrated electronic medical record and California Cancer Registry data in the Oncoshare database. Of 772 women with stage I-III TNBC treated with and without standard cytotoxic chemotherapy - prior to the immune checkpoint inhibitor era - most (654, 85%) used antimicrobials. Applying multivariate analyses, we show that each additional total or unique monthly antimicrobial prescription is associated with inferior overall and breast cancer-specific survival. This antimicrobial-mortality association is independent of changes in neutrophil count, is unrelated to disease severity, and is sustained through year three following diagnosis, suggesting antimicrobial exposure negatively impacts TNBC survival. These results may inform mechanistic studies and antimicrobial prescribing decisions in TNBC and other hormone receptor-independent cancers.

Robust weights that optimally balance confounders for estimating marginal hazard ratios

Covariate balance is crucial in obtaining unbiased estimates of treatment effects in observational studies. Methods that target covariate balance have been successfully proposed and largely applied to estimate treatment effects on continuous outcomes. However, in many medical and epidemiological applications, the interest lies in estimating treatment effects on time-to-event outcomes. With this type of data, one of the most common estimands of interest is the marginal hazard ratio of the Cox proportional hazards model. In this article, we start by presenting robust orthogonality weights, a set of weights obtained by solving a quadratic constrained optimization problem that maximizes precision while constraining covariate balance defined as the correlation between confounders and treatment. By doing so, robust orthogonality weights optimally deal with both binary and continuous treatments. We then evaluate the performance of the proposed weights in estimating marginal hazard ratios of binary and continuous treatments with time-to-event outcomes in a simulation study. We finally apply robust orthogonality weights in the evaluation of the effect of hormone therapy on time to coronary heart disease and on the effect of red meat consumption on time to colon cancer among 24,069 postmenopausal women enrolled in the Women's Health Initiative observational study.

Estimation of marginal structural models under irregular visits and unmeasured confounder: calibrated inverse probability weights

Clinical information collected in electronic health records (EHRs) is becoming an essential source to emulate randomized experiments. Since patients do not interact with the healthcare system at random, the longitudinal information in large observational databases must account for irregular visits. Moreover, we need to also account for subject-specific unmeasured confounders which may act as a common cause for treatment assignment mechanism (e.g. glucose-lowering medications) while also influencing the outcome (e.g. Hemoglobin A1c). We used the calibration of longitudinal weights to improve the finite sample properties and to account for subject-specific unmeasured confounders. A Monte Carlo simulation study is conducted to evaluate the performance of calibrated inverse probability estimators using time-dependent treatment assignment and irregular visits with subject-specific unmeasured confounders. The simulation study showed that the longitudinal weights with calibrated restrictions improved the finite sample bias when compared to the stabilized weights. The application of the calibrated weights is demonstrated using the exposure of glucose lowering medications and the longitudinal outcome of Hemoglobin A1c. Our results support the effectiveness of glucose lowering medications in reducing Hemoglobin A1c among type II diabetes patients with elevated glycemic index ([Formula: see text]) using stabilized and calibrated weights.

Data-Adaptive Selection of the Propensity Score Truncation Level for Inverse-Probability-Weighted and Targeted Maximum Likelihood Estimators of Marginal Point Treatment Effects

Inverse probability weighting (IPW) and targeted maximum likelihood estimation (TMLE) are methodologies that can adjust for confounding and selection bias and are often used for causal inference. Both estimators rely on the positivity assumption that within strata of confounders there is a positive probability of receiving treatment at all levels under consideration. Practical applications of IPW require finite inverse probability (IP) weights. TMLE requires that propensity scores (PS) be bounded away from 0 and 1. Although truncation can improve variance and finite sample bias, this artificial distortion of the IP weights and PS distribution introduces asymptotic bias. As sample size grows, truncation-induced bias eventually swamps variance, rendering nominal confidence interval coverage and hypothesis tests invalid. We present a simple truncation strategy based on the sample size, n, that sets the upper bound on IP weights at $\sqrt{\textit{n}}$ ln n/5. For TMLE, the lower bound on the PS should be set to 5/($\sqrt{\textit{n}}$ ln n/5). Our strategy was designed to optimize the mean squared error of the parameter estimate. It naturally extends to data structures with missing outcomes. Simulation studies and a data analysis demonstrate our strategy's ability to minimize both bias and mean squared error in comparison with other common strategies, including the popular but flawed quantile-based heuristic.

Two-stage matching-adjusted indirect comparison

BACKGROUND

Anchored covariate-adjusted indirect comparisons inform reimbursement decisions where there are no head-to-head trials between the treatments of interest, there is a common comparator arm shared by the studies, and there are patient-level data limitations. Matching-adjusted indirect comparison (MAIC), based on propensity score weighting, is the most widely used covariate-adjusted indirect comparison method in health technology assessment. MAIC has poor precision and is inefficient when the effective sample size after weighting is small.

METHODS

A modular extension to MAIC, termed two-stage matching-adjusted indirect comparison (2SMAIC), is proposed. This uses two parametric models. One estimates the treatment assignment mechanism in the study with individual patient data (IPD), the other estimates the trial assignment mechanism. The first model produces inverse probability weights that are combined with the odds weights produced by the second model. The resulting weights seek to balance covariates between treatment arms and across studies. A simulation study provides proof-of-principle in an indirect comparison performed across two randomized trials. Nevertheless, 2SMAIC can be applied in situations where the IPD trial is observational, by including potential confounders in the treatment assignment model. The simulation study also explores the use of weight truncation in combination with MAIC for the first time.

RESULTS

Despite enforcing randomization and knowing the true treatment assignment mechanism in the IPD trial, 2SMAIC yields improved precision and efficiency with respect to MAIC in all scenarios, while maintaining similarly low levels of bias. The two-stage approach is effective when sample sizes in the IPD trial are low, as it controls for chance imbalances in prognostic baseline covariates between study arms. It is not as effective when overlap between the trials' target populations is poor and the extremity of the weights is high. In these scenarios, truncation leads to substantial precision and efficiency gains but induces considerable bias. The combination of a two-stage approach with truncation produces the highest precision and efficiency improvements.

CONCLUSIONS

Two-stage approaches to MAIC can increase precision and efficiency with respect to the standard approach by adjusting for empirical imbalances in prognostic covariates in the IPD trial. Further modules could be incorporated for additional variance reduction or to account for missingness and non-compliance in the IPD trial.

Marginal structural models using calibrated weights with SuperLearner: application to type II diabetes cohort

As different scientific disciplines begin to converge on machine learning for causal inference, we demonstrate the application of machine learning algorithms in the context of longitudinal causal estimation using electronic health records. Our aim is to formulate a marginal structural model for estimating diabetes care provisions in which we envisioned hypothetical (i.e. counterfactual) dynamic treatment regimes using a combination of drug therapies to manage diabetes: metformin, sulfonylurea and SGLT-2i. The binary outcome of diabetes care provisions was defined using a composite measure of chronic disease prevention and screening elements [27] including (i) primary care visit, (ii) blood pressure, (iii) weight, (iv) hemoglobin A1c, (v) lipid, (vi) ACR, (vii) eGFR and (viii) statin medication. We used several statistical learning algorithms to describe causal relationships between the prescription of three common classes of diabetes medications and quality of diabetes care using the electronic health records contained in National Diabetes Repository. In particular, we generated an ensemble of statistical learning algorithms using the SuperLearner framework based on the following base learners: (i) least absolute shrinkage and selection operator, (ii) ridge regression, (iii) elastic net, (iv) random forest, (v) gradient boosting machines, and (vi) neural network. Each statistical learning algorithm was fitted using the pseudo-population generated from the marginalization of the time-dependent confounding process. Covariate balance was assessed using the longitudinal (i.e. cumulative-time product) stabilized weights with calibrated restrictions. Our results indicated that the treatment drop-in cohorts (with respect to metformin, sulfonylurea and SGLT-2i) may have improved diabetes care provisions in relation to treatment naive (i.e. no treatment) cohort. As a clinical utility, we hope that this article will facilitate discussions around the prevention of adverse chronic outcomes associated with type II diabetes through the improvement of diabetes care provisions in primary care.

Introduction to computational causal inference using reproducible Stata, R, and Python code: A tutorial

The main purpose of many medical studies is to estimate the effects of a treatment or exposure on an outcome. However, it is not always possible to randomize the study participants to a particular treatment, therefore observational study designs may be used. There are major challenges with observational studies; one of which is confounding. Controlling for confounding is commonly performed by direct adjustment of measured confounders; although, sometimes this approach is suboptimal due to modeling assumptions and misspecification. Recent advances in the field of causal inference have dealt with confounding by building on classical standardization methods. However, these recent advances have progressed quickly with a relative paucity of computational-oriented applied tutorials contributing to some confusion in the use of these methods among applied researchers. In this tutorial, we show the computational implementation of different causal inference estimators from a historical perspective where new estimators were developed to overcome the limitations of the previous estimators (ie, nonparametric and parametric g-formula, inverse probability weighting, double-robust, and data-adaptive estimators). We illustrate the implementation of different methods using an empirical example from the Connors study based on intensive care medicine, and most importantly, we provide reproducible and commented code in Stata, R, and Python for researchers to adapt in their own observational study. The code can be accessed at https://github.com/migariane/Tutorial_Computational_Causal_Inference_Estimators.

Association of Membership at a Medical Fitness Facility With Adverse Health Outcomes

INTRODUCTION

Interventions that increase physical activity behavior can reduce morbidity and prolong life, but long-term effects in large populations are unproven. This study investigates the association of medical fitness facility membership and frequency of attendance with all-cause mortality and rate of hospitalization.

METHODS

A propensity weighted retrospective cohort study was conducted by linking individuals who attended medical fitness facilities in Winnipeg, Canada to provincial health administrative databases. Members aged ≥18 years who had ≥1 year of provincial health coverage from their index date between January 1, 2005 and December 31, 2015 were included. Controls were assigned a pseudo-index date at random on the basis of the frequency distribution of index dates in the intervention group. Members were stratified into low-frequency attenders (<1 weekly visit), moderate-frequency attenders (1-3 weekly visits), and high-frequency attenders (>3 weekly visits). The primary outcomes were time to all-cause mortality and rate of hospitalizations. Statistical analyses were performed between 2018 and 2020.

RESULTS

Among 19,300 adult members and 515,810 controls, members had a 60% lower risk of all-cause mortality during the first 651 days and 48% after 651 days. Membership was associated with a 13% lower risk of hospitalizations. A dose-response effect was apparent because higher weekly attendance was associated with a lower risk of hospitalizations (low frequency: 9%, moderate frequency: 20%, high frequency: 39%).

CONCLUSIONS

Membership at a medical fitness facility was associated with a reduced risk of all-cause mortality and hospitalizations. Healthcare systems should consider the medical fitness model as a preventative public health strategy to encourage physical activity participation.

An introduction to inverse probability of treatment weighting in observational research

In this article we introduce the concept of inverse probability of treatment weighting (IPTW) and describe how this method can be applied to adjust for measured confounding in observational research, illustrated by a clinical example from nephrology. IPTW involves two main steps. First, the probability—or propensity—of being exposed to the risk factor or intervention of interest is calculated, given an individual’s characteristics (i.e. propensity score). Second, weights are calculated as the inverse of the propensity score. The application of these weights to the study population creates a pseudopopulation in which confounders are equally distributed across exposed and unexposed groups. We also elaborate on how weighting can be applied in longitudinal studies to deal with informative censoring and time-dependent confounding in the setting of treatment-confounder feedback.

Adjuvant Hormonotherapy and Cardiovascular Risk in Post-Menopausal Women with Breast Cancer: A Large Population-Based Cohort Study

BACKGROUND

Whether aromatase inhibitors (AIs) increase the risk of cardiovascular (CV) events, compared to tamoxifen, in women with breast cancer is still debated. We evaluated the association between AI and CV outcomes in a large population-based cohort of breast cancer women.

METHODS

By using healthcare utilization databases of Lombardy (Italy), we identified women ≥50 years, with new diagnosis of breast cancer between 2009 and 2015, who started adjuvant therapy with either AI or tamoxifen. We estimated the association between exposure to AI and CV outcomes (including myocardial infarction, ischemic stroke, heart failure or any CV event) by a Cox proportional hazard model with inverse probability of treatment and censoring weighting.

RESULTS

The study cohort included 26,009 women starting treatment with AI and 7937 with tamoxifen. Over a median follow-up of 5.8 years, a positive association was found between AI and heart failure (Hazard Ratio = 1.20, 95% CI: 1.02 to 1.42) and any CV event (1.14, 1.00 to 1.29). The CV risk increased in women with previous CV risk factors, including hypertension, diabetes and dyslipidemia.

CONCLUSIONS

Adjuvant therapy with AI in breast cancer women aged more than 50 years is associated with increased risk of heart failure and combined CV events.

Association of Opioid Consumption Profiles After Hospitalization With Risk of Adverse Health Care Events

IMPORTANCE

Although better pain management has guided policies for opioid use over the past few decades, evidence is limited regarding how patterns of use are associated with the risk of potentially avoidable opioid-related adverse events.

OBJECTIVE

To estimate the risk of harms associated with opioid dose and duration of use, and to ascertain whether the risk is modified by treatment indication and age.

DESIGN, SETTING, AND PARTICIPANTS

This ad hoc cohort study followed up patients who were enrolled in a cluster randomized trial of medication reconciliation between October 1, 2014, and November 30, 2016, 12 months after they were discharged from the McGill University Health Centre in Montreal, Quebec, Canada. To be eligible for this study, patients needed to have filled at least 1 opioid prescription 3 months after discharge. Patients with a history of using methadone or buprenorphine were excluded. Data analyses were performed between February 1, 2019, and February 28, 2020.

EXPOSURES

Time-varying measures of opioid use included current use, daily morphine milligram equivalent (MME) dose, cumulative and continuous use duration, and type of ingredients in prescription opioids used. Hospitalization records, dispensed prescriptions records, and postdischarge interviews were used to evaluate adherence to the opioid prescriptions after discharge.

MAIN OUTCOMES AND MEASURES

Opioid-related emergency department visits, hospital readmissions, or all-cause death. Outcomes were ascertained using provincial medical services claims and hospitalization databases.

RESULTS

Of 3486 participants in the cluster randomized trial (mean [SD] age of 69.6 [14.9] years; 2010 men [57.7%]), 1511 patients were included in this ad hoc cohort study. Among those with at least 1 opioid dispensation, 241 patients (15.9%) experienced an opioid-related emergency department visit, hospital readmission, or death. Results from marginal structural Cox proportional hazards regression models showed more than a 2-fold increase in the risk of opioid-related adverse events associated with a cumulative use duration of more than 90 days (adjusted hazard ratio, 2.56; 95% CI, 1.25-5.27) compared with 1 to 30 days. A 3-fold risk increase was found with a mean daily dose higher than 90 MME (adjusted hazard ratio, 3.51; 95% CI, 1.58-7.82) compared with 90 MME or lower.

CONCLUSIONS AND RELEVANCE

This study found an association between risk of adverse health care events and higher opioid doses and longer treatment duration. This finding can inform policies for limiting opioid duration and dose to attenuate the risk of avoidable morbidity.

Formulating causal questions and principled statistical answers

Although review papers on causal inference methods are now available, there is a lack of introductory overviews on what they can render and on the guiding criteria for choosing one particular method. This tutorial gives an overview in situations where an exposure of interest is set at a chosen baseline ("point exposure") and the target outcome arises at a later time point. We first phrase relevant causal questions and make a case for being specific about the possible exposure levels involved and the populations for which the question is relevant. Using the potential outcomes framework, we describe principled definitions of causal effects and of estimation approaches classified according to whether they invoke the no unmeasured confounding assumption (including outcome regression and propensity score-based methods) or an instrumental variable with added assumptions. We mainly focus on continuous outcomes and causal average treatment effects. We discuss interpretation, challenges, and potential pitfalls and illustrate application using a "simulation learner," that mimics the effect of various breastfeeding interventions on a child's later development. This involves a typical simulation component with generated exposure, covariate, and outcome data inspired by a randomized intervention study. The simulation learner further generates various (linked) exposure types with a set of possible values per observation unit, from which observed as well as potential outcome data are generated. It thus provides true values of several causal effects. R code for data generation and analysis is available on www.ofcaus.org, where SAS and Stata code for analysis is also provided.

Long-term comparative safety analysis of the risks associated with adding or switching to a sulfonylurea as second-line Type 2 diabetes mellitus treatment in a US veteran population

AIM

To examine the risks of all-cause mortality and cardiovascular events associated with adding vs switching to second-line therapies in a comparative safety study of people with Type 2 diabetes mellitus.

METHODS

We conducted a retrospective cohort study using an as-treated analysis of people served by the Veterans Health Administration who were on metformin and subsequently augmented this treatment or switched to other oral glucose-lowering treatments between 1998 and 2012. This study included 145 250 people with long follow-up. Confounding was addressed through several strategies, involving weighted propensity score models with rich confounder adjustment and strict inclusion criteria, coupled with an incident-user design.

RESULTS

Second-line use of sulfonylureas was related to higher mortality (hazard ratio 1.39, 95% CI 1.14, 1.70) and cardiovascular risks (hazard ratio 1.19, 95% CI 1.09, 1.30) compared with thiazolidinedione therapy. Differential hazards were associated with discontinuing or not discontinuing metformin; switching to sulfonylurea therapy was associated with a higher risk of all-cause mortality and cardiovascular events compared with all other therapies. Furthermore, add-on sulfonylurea therapy was associated with an elevated risk for both outcomes when compared with thiazolidinedione add-on therapy.

CONCLUSIONS

The results of the present study may inform decisions on whether to augment or discontinue metformin; when considering the long-term risks, switching to a sulfonylurea appears unfavourable compared with other therapies. Instead, adding a thiazolidinedione to existing metformin therapy appears to be superior to adding or switching to a sulfonylurea.

Recent Trends and Effectiveness of Antiretroviral Regimens Among Men Who Have Sex With Men Living With HIV in the United States: The Multicenter AIDS Cohort Study (MACS) 2008-2017

OBJECTIVE

We evaluated trends and population effectiveness (tolerability, HIV suppression) of current combination antiretroviral therapy (cART) regimens mindful of treatment guidelines.

METHOD

Trend analyses included 18 017 person-visits (1457 men) on cART during 2008-2017 in the Multicenter AIDS Cohort Study. Effectiveness analyses of current regimens used 3598 person-visit-pairs (745 men) on cART in 2014-2017. Inverse-probability-of-treatment-and-censoring weighted Poisson regression with robust variances was used to evaluate the association between regimens and switching, adherence and HIV RNA <20 copies/mL.

RESULTS

Integrase strand transfer inhibitor (INSTI)-based regimen usage has increased since 2008. Almost 90% of cART initiators started with INSTI-cART in 2016-2017; cART adherence was stable around 90% and 83%-85% suppressed virus (<20 cp/mL). Commonly used regimens in 2014-2017 contained disoproxil fumarate/emtricitabine (TDF/FTC) backbone with efavirenz (EFV, n = 1161 person-visits), elvitegravir/cobicistat (EVG/c, n = 551), rilpivirine (RPV, n = 492), darunavir/ritonavir (DRV/r, n = 351), or atazanavir (ATV)/r (n = 333). Others were dolutegravir/abacavir/lamivudine (DTG/ABC/3TC, n = 401) and EVG/c/tenofovir alafenamide/FTC (EVG/c/TAF/FTC, n = 309). Compared to EFV/TDF/FTC users, ATV/r+TDF/FTC users switched more (rate ratio [RR] = 1.80, 95% confidence interval (CI), 1.17-2.76), while those on DTG/ABC/3TC (RR [95% CI] = 0.16 [0.08-0.31]) or EVG/c/TAF/FTC (RR [95% CI] = 0.12 [0.06-0.27]) switched less. The rate of suppressed HIV RNA was 15% (95% CI, 2%-26%) lower among younger EVG/c/TDF/FTC users and 18% (95% CI, 3%-34%) higher in older DRV/r+TDF/FTC users; adherence did not differ by regimen.

CONCLUSIONS

Consistent with guidelines, recent cART initiators started with INSTI-cART, which was associated with less switching early after initiation. Factors beyond those studied here, such as need for salvage therapy, unique personal characteristics, drug interactions, and cost may influence treatment decisions.

A test for the correct specification of marginal structural models

Marginal structural models (MSMs) allow estimating the causal effect of a time-varying exposure on an outcome in the presence of time-dependent confounding. The parameters of MSMs can be estimated utilizing an inverse probability of treatment weight estimator under certain assumptions. One of these assumptions is that the proposed causal model relating the outcome to exposure history is correctly specified. However, in practice, the true model is unknown. We propose a test that employs the observed data to attempt validating the assumption that the model is correctly specified. The performance of the proposed test is investigated with a simulation study. We illustrate our approach by estimating the effect of repeated exposure to psychosocial stressors at work on ambulatory blood pressure in a large cohort of white-collar workers in Québec City, Canada. Code examples in SAS and R are provided to facilitate the implementation of the test.

Optimal probability weights for estimating causal effects of time-varying treatments with marginal structural Cox models

Marginal structural Cox models have been used to estimate the causal effect of a time-varying treatment on a survival outcome in the presence of time-dependent confounders. These methods rely on the positivity assumption, which states that the propensity scores are bounded away from zero and one. Practical violations of this assumption are common in longitudinal studies, resulting in extreme weights that may yield erroneous inferences. Truncation, which consists of replacing outlying weights with less extreme ones, is the most common approach to control for extreme weights to date. While truncation reduces the variability in the weights and the consequent sampling variability of the estimator, it can also introduce bias. Instead of truncated weights, we propose using optimal probability weights, defined as those that have a specified variance and the smallest Euclidean distance from the original, untruncated weights. The set of optimal weights is obtained by solving a constrained quadratic optimization problem. The proposed weights are evaluated in a simulation study and applied to the assessment of the effect of treatment on time to death among people in Sweden who live with human immunodeficiency virus and inject drugs.

Immigrant Legal Status and Health: Legal Status Disparities in Chronic Conditions and Musculoskeletal Pain Among Mexican-Born Farm Workers in the United States

Immigrant legal status determines access to the rights and privileges of U.S. society. Legal status may be conceived of as a fundamental cause of health, producing a health disparity whereby unauthorized immigrants are disadvantaged relative to authorized immigrants, a perspective that is supported by research on legal status disparities in self-rated health and mental health. We conducted a systematic review of the literature on legal status disparities in physical health and examined whether a legal status disparity exists in chronic conditions and musculoskeletal pain among 17,462 Mexican-born immigrants employed as farm workers in the United States and surveyed in the National Agricultural Workers Survey between 2000 and 2015. We found that unauthorized, Mexican-born farm workers have a lower incidence of chronic conditions and lower prevalence of pain compared with authorized farm workers. Furthermore, we found a legal status gradient in health whereby naturalized U.S. citizens report the worst health, followed by legal permanent residents and unauthorized immigrants. Although inconsistent with fundamental cause theory, our results were robust to alternative specifications and consistent with a small body of existing research on legal status disparities in physical health. Although it is well known that Mexican immigrants have better-than-expected health outcomes given their social disadvantage, we suggest that an epidemiologic paradox may also apply to within-immigrant disparities by legal status. We offer several explanations for the counterintuitive result.

On adaptive propensity score truncation in causal inference

The positivity assumption, or the experimental treatment assignment (ETA) assumption, is important for identifiability in causal inference. Even if the positivity assumption holds, practical violations of this assumption may jeopardize the finite sample performance of the causal estimator. One of the consequences of practical violations of the positivity assumption is extreme values in the estimated propensity score (PS). A common practice to address this issue is truncating the PS estimate when constructing PS-based estimators. In this study, we propose a novel adaptive truncation method, Positivity-C-TMLE, based on the collaborative targeted maximum likelihood estimation (C-TMLE) methodology. We demonstrate the outstanding performance of our novel approach in a variety of simulations by comparing it with other commonly studied estimators. Results show that by adaptively truncating the estimated PS with a more targeted objective function, the Positivity-C-TMLE estimator achieves the best performance for both point estimation and confidence interval coverage among all estimators considered.

Effect of Transfusion on Mortality and Other Adverse Events Among Critically Ill Septic Patients: An Observational Study Using a Marginal Structural Cox Model

OBJECTIVES

RBC transfusion is often required in patients with sepsis. However, adverse events have been associated with RBC transfusion, raising safety concerns. A randomized controlled trial validated the 7 g/dL threshold, but previously transfused patients were excluded. Cohort studies led to conflicting results and did not handle time-dependent covariates and history of treatment. Additional data are thus warranted to guide patient's management.

DESIGN

To estimate the effect of one or more RBC within 1 day on three major outcomes (mortality, ICU-acquired infections, and severe hypoxemia) at day 30, we used marginal structural models. A trajectory modeling, based on hematocrit evolution pattern, allowed identification of subgroups. Secondary analyses were performed into each of them.

SETTING

A prospective French multicenter database.

PATIENTS

Patients with sepsis at admission. Patients with hemorrhagic shock at admission were excluded.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Overall, in our cohort of 6,016 patients, RBC transfusion was not associated with death (hazard ratio, 1.07; 95% CI, 0.88-1.30; p = 0.52). However, RBC transfusion was associated with increased occurrence of ICU-acquired infections (hazard ratio, 2.77; 95% CI, 2.33-3.28; p < 0.01) and of severe hypoxemia (hazard ratio, 1.29; 95% CI, 1.14-1.47; p < 0.01). A protective effect from death by the transfusion was found in the subgroup with the lowest hematocrit level (26 [interquartile range, 24-28]) (hazard ratio, 0.72; 95% CI, 0.55-0.95; p = 0.02).

CONCLUSIONS

RBC transfusion did not affect overall mortality in critically ill patients with sepsis. Increased occurrence rate of ICU-acquired infection and severe hypoxemia are expected outcomes from RBC transfusion that need to be weighted with its benefits in selected patients.

Adjustment for time-dependent unmeasured confounders in marginal structural Cox models using validation sample data

Large databases used in observational studies of drug safety often lack information on important confounders. The resulting unmeasured confounding bias may be avoided by using additional confounder information, frequently available in smaller clinical “validation samples”. Yet, no existing method that uses such validation samples is able to deal with unmeasured time-varying variables acting as both confounders and possible mediators of the treatment effect. We propose and compare alternative methods which control for confounders measured only in a validation sample within marginal structural Cox models. Each method corrects the time-varying inverse probability of treatment weights for all subject-by-time observations using either regression calibration of the propensity score, or multiple imputation of unmeasured confounders. Two proposed methods rely on martingale residuals from a Cox model that includes only confounders fully measured in the large database, to correct inverse probability of treatment weight for imputed values of unmeasured confounders. Simulation demonstrates that martingale residual-based methods systematically reduce confounding bias over naïve methods, with multiple imputation including the martingale residual yielding, on average, the best overall accuracy. We apply martingale residual-based imputation to re-assess the potential risk of drug-induced hypoglycemia in diabetic patients, where an important laboratory test is repeatedly measured only in a small sub-cohort.

Contours of a causal feedback mechanism between adaptive personality and psychosocial function in patients with personality disorders: a secondary analysis from a randomized clinical trial

BACKGROUND

Patients with personality disorders commonly exhibit impairment in psychosocial function that persists over time even with diagnostic remission. Further causal knowledge may help to identify and assess factors with a potential to alleviate this impairment. Psychosocial function is associated with personality functioning which describes personality disorder severity in DSM-5 (section III) and which can reportedly be improved by therapy.

METHODS

The reciprocal association between personality functioning and psychosocial function was assessed, in 113 patients with different personality disorders, in a secondary longitudinal analysis of data from a randomized clinical trial, over six years. Personality functioning was represented by three domains of the Severity Indices of Personality Problems: Relational Capacity, Identity Integration, and Self-control. Psychosocial function was measured by Global Assessment of Functioning. The marginal structural model was used for estimation of causal effects of the three personality functioning domains on psychosocial function, and vice versa. The attractiveness of this model lies in the ability to assess an effect of a time - varying exposure on an outcome, while adjusting for time - varying confounding.

RESULTS

Strong causal effects were found. A hypothetical intervention to increase Relational Capacity by one standard deviation, both at one and two time-points prior to assessment of psychosocial function, would increase psychosocial function by 3.5 standard deviations (95% CI: 2.0, 4.96). Significant effects of Identity Integration and Self-control on psychosocial function, and from psychosocial function on all three domains of personality functioning, although weaker, were also found.

CONCLUSION

This study indicates that persistent impairment in psychosocial function can be addressed through a causal pathway of personality functioning, with interventions of at least 18 months duration.

Estimating inverse probability weights using super learner when weight-model specification is unknown in a marginal structural Cox model context

Correct specification of the inverse probability weighting (IPW) model is necessary for consistent inference from a marginal structural Cox model (MSCM). In practical applications, researchers are typically unaware of the true specification of the weight model. Nonetheless, IPWs are commonly estimated using parametric models, such as the main-effects logistic regression model. In practice, assumptions underlying such models may not hold and data-adaptive statistical learning methods may provide an alternative. Many candidate statistical learning approaches are available in the literature. However, the optimal approach for a given dataset is impossible to predict. Super learner (SL) has been proposed as a tool for selecting an optimal learner from a set of candidates using cross-validation. In this study, we evaluate the usefulness of a SL in estimating IPW in four different MSCM simulation scenarios, in which we varied the specification of the true weight model specification (linear and/or additive). Our simulations show that, in the presence of weight model misspecification, with a rich and diverse set of candidate algorithms, SL can generally offer a better alternative to the commonly used statistical learning approaches in terms of MSE as well as the coverage probabilities of the estimated effect in an MSCM. The findings from the simulation studies guided the application of the MSCM in a multiple sclerosis cohort from British Columbia, Canada (1995-2008), to estimate the impact of beta-interferon treatment in delaying disability progression. Copyright © 2017 John Wiley & Sons, Ltd.

Effect Estimation in Point-Exposure Studies with Binary Outcomes and High-Dimensional Covariate Data - A Comparison of Targeted Maximum Likelihood Estimation and Inverse Probability of Treatment Weighting

Inverse probability of treatment weighting (IPW) and targeted maximum likelihood estimation (TMLE) are relatively new methods proposed for estimating marginal causal effects. TMLE is doubly robust, yielding consistent estimators even under misspecification of either the treatment or the outcome model. While IPW methods are known to be sensitive to near violations of the practical positivity assumption (e. g., in the case of data sparsity), the consequences of this violation in the TMLE framework for binary outcomes have been less widely investigated. As near practical positivity violations are particularly likely in high-dimensional covariate settings, a better understanding of the performance of TMLE is of particular interest for pharmcoepidemiological studies using large databases. Using plasmode and Monte-Carlo simulation studies, we evaluated the performance of TMLE compared to that of IPW estimators based on a point-exposure cohort study of the marginal causal effect of post-myocardial infarction statin use on the 1-year risk of all-cause mortality from the Clinical Practice Research Datalink. A variety of treatment model specifications were considered, inducing different degrees of near practical non-positivity. Our simulation study showed that the performance of the TMLE and IPW estimators were comparable when the dimension of the fitted treatment model was small to moderate; however, they differed when a large number of covariates was considered. When a rich outcome model was included in the TMLE, estimators were unbiased. In some cases, we found irregular bias and large standard errors with both methods even with a correctly specified high-dimensional treatment model. The IPW estimator showed a slightly better root MSE with high-dimensional treatment model specifications in our simulation setting. In conclusion, for estimation of the marginal expectation of the outcome under a fixed treatment, TMLE and IPW estimators employing the same treatment model specification may perform differently due to differential sensitivity to practical positivity violations; however, TMLE, being doubly robust, shows improved performance with richer specifications of the outcome model. Although TMLE is appealing for its double robustness property, such violations in a high-dimensional covariate setting are problematic for both methods.

Comparison of statistical approaches dealing with time-dependent confounding in drug effectiveness studies

In longitudinal studies, if the time-dependent covariates are affected by the past treatment, time-dependent confounding may be present. For a time-to-event response, marginal structural Cox models are frequently used to deal with such confounding. To avoid some of the problems of fitting marginal structural Cox model, the sequential Cox approach has been suggested as an alternative. Although the estimation mechanisms are different, both approaches claim to estimate the causal effect of treatment by appropriately adjusting for time-dependent confounding. We carry out simulation studies to assess the suitability of the sequential Cox approach for analyzing time-to-event data in the presence of a time-dependent covariate that may or may not be a time-dependent confounder. Results from these simulations revealed that the sequential Cox approach is not as effective as marginal structural Cox model in addressing the time-dependent confounding. The sequential Cox approach was also found to be inadequate in the presence of a time-dependent covariate. We propose a modified version of the sequential Cox approach that correctly estimates the treatment effect in both of the above scenarios. All approaches are applied to investigate the impact of beta-interferon treatment in delaying disability progression in the British Columbia Multiple Sclerosis cohort (1995-2008).

Martingale residual-based method to control for confounders measured only in a validation sample in time-to-event analysis

Unmeasured confounding remains an important problem in observational studies, including pharmacoepidemiological studies of large administrative databases. Several recently developed methods utilize smaller validation samples, with information on additional confounders, to control for confounders unmeasured in the main, larger database. However, up-to-date applications of these methods to survival analyses seem to be limited to propensity score calibration, which relies on a strong surrogacy assumption. We propose a new method, specifically designed for time-to-event analyses, which uses martingale residuals, in addition to measured covariates, to enhance imputation of the unmeasured confounders in the main database. The method is applicable for analyses with both time-invariant data and time-varying exposure/confounders. In simulations, our method consistently eliminated bias because of unmeasured confounding, regardless of surrogacy violation and other relevant design parameters, and almost always yielded lower mean squared errors than other methods applicable for survival analyses, outperforming propensity score calibration in several scenarios. We apply the method to a real-life pharmacoepidemiological database study of the association between glucocorticoid therapy and risk of type II diabetes mellitus in patients with rheumatoid arthritis, with additional potential confounders available in an external validation sample. Compared with conventional analyses, which adjust only for confounders measured in the main database, our estimates suggest a considerably weaker association. Copyright © 2016 John Wiley & Sons, Ltd.

Estimating optimal shared-parameter dynamic regimens with application to a multistage depression clinical trial

A dynamic treatment regimen consists of decision rules that recommend how to individualize treatment to patients based on available treatment and covariate history. In many scientific domains, these decision rules are shared across stages of intervention. As an illustrative example, we discuss STAR*D, a multistage randomized clinical trial for treating major depression. Estimating these shared decision rules often amounts to estimating parameters indexing the decision rules that are shared across stages. In this article, we propose a novel simultaneous estimation procedure for the shared parameters based on Q-learning. We provide an extensive simulation study to illustrate the merit of the proposed method over simple competitors, in terms of the treatment allocation matching of the procedure with the "oracle" procedure, defined as the one that makes treatment recommendations based on the true parameter values as opposed to their estimates. We also look at bias and mean squared error of the individual parameter-estimates as secondary metrics. Finally, we analyze the STAR*D data using the proposed method.

The missing cause approach to unmeasured confounding in pharmacoepidemiology

Unmeasured confounding is a major threat to the validity of pharmacoepidemiological studies of medication safety and effectiveness. We propose a new method for detecting and reducing the impact of unobserved confounding in large observational database studies. The method uses assumptions similar to the prescribing preference-based instrumental variable (IV) approach. Our method relies on the new 'missing cause' principle, according to which the impact of unmeasured confounding by (contra-)indication may be detected by assessing discrepancies between the following: (i) treatment actually received by individual patients and (ii) treatment that they would be expected to receive based on the observed data. Specifically, we use the treatment-by-discrepancy interaction to test for the presence of unmeasured confounding and correct the treatment effect estimate for the resulting bias. Under standard IV assumptions, we first proved that unmeasured confounding induces a spurious treatment-by-discrepancy interaction in risk difference models for binary outcomes and then simulated large pharmacoepidemiological studies with unmeasured confounding. In simulations, our estimates had four to six times smaller bias than conventional treatment effect estimates, adjusted only for measured confounders, and much smaller variance inflation than unbiased but very unstable IV estimates, resulting in uniformly lowest root mean square errors. The much lower variance of our estimates, relative to IV estimates, was also observed in an application comparing gastrointestinal safety of two classes of anti-inflammatory drugs. In conclusion, our missing cause-based method may complement other methods and enhance accuracy of analyses of large pharmacoepidemiological studies.

Adaptive truncated weighting for improving marginal structural model estimation of treatment effects informally censored by subsequent therapy

Randomized clinical trials are designed to estimate the direct effect of a treatment by randomly assigning patients to receive either treatment or control. However, in some trials, patients who discontinued their initial randomized treatment are allowed to switch to another treatment. Therefore, the direct treatment effect of interest may be confounded by subsequent treatment. Moreover, the decision on whether to initiate a second-line treatment is typically made based on time-dependent factors that may be affected by prior treatment history. Due to these time-dependent confounders, traditional time-dependent Cox models may produce biased estimators of the direct treatment effect. Marginal structural models (MSMs) have been applied to estimate causal treatment effects even in the presence of time-dependent confounders. However, the occurrence of extremely large weights can inflate the variance of the MSM estimators. In this article, we proposed a new method for estimating weights in MSMs by adaptively truncating the longitudinal inverse probabilities. This method provides balance in the bias variance trade-off when large weights are inevitable, without the ad hoc removal of selected observations. We conducted simulation studies to explore the performance of different methods by comparing bias, standard deviation, confidence interval coverage rates, and mean square error under various scenarios. We also applied these methods to a randomized, open-label, phase III study of patients with nonsquamous non-small cell lung cancer.

Marginal structural Cox models for estimating the association between β-interferon exposure and disease progression in a multiple sclerosis cohort

Longitudinal observational data are required to assess the association between exposure to β-interferon medications and disease progression among relapsing-remitting multiple sclerosis (MS) patients in the "real-world" clinical practice setting. Marginal structural Cox models (MSCMs) can provide distinct advantages over traditional approaches by allowing adjustment for time-varying confounders such as MS relapses, as well as baseline characteristics, through the use of inverse probability weighting. We assessed the suitability of MSCMs to analyze data from a large cohort of 1,697 relapsing-remitting MS patients in British Columbia, Canada (1995-2008). In the context of this observational study, which spanned more than a decade and involved patients with a chronic yet fluctuating disease, the recently proposed "normalized stabilized" weights were found to be the most appropriate choice of weights. Using this model, no association between β-interferon exposure and the hazard of disability progression was found (hazard ratio = 1.36, 95% confidence interval: 0.95, 1.94). For sensitivity analyses, truncated normalized unstabilized weights were used in additional MSCMs and to construct inverse probability weight-adjusted survival curves; the findings did not change. Additionally, qualitatively similar conclusions from approximation approaches to the weighted Cox model (i.e., MSCM) extend confidence in the findings.