Flexible regression approach to propensity score analysis and its relationship with matching and weighting

causalCmprsk: An R package for nonparametric and Cox-based estimation of average treatment effects in competing risks data

BACKGROUND AND OBJECTIVE

Competing risks data arise in both observational and experimental clinical studies with time-to-event outcomes, when each patient might follow one of the multiple mutually exclusive competing paths. Ignoring competing risks in the analysis can result in biased conclusions. In addition, possible confounding bias of the treatment-outcome relationship has to be addressed, when estimating treatment effects from observational data. In order to provide tools for estimation of average treatment effects on time-to-event outcomes in the presence of competing risks, we developed the R package causalCmprsk. We illustrate the package functionality in the estimation of effects of a right heart catheterization procedure on discharge and in-hospital death from observational data.

METHODS

The causalCmprsk package implements an inverse probability weighting estimation approach, aiming to emulate baseline randomization and alleviate possible treatment selection bias. The package allows for different types of weights, representing different target populations. causalCmprsk builds on existing methods from survival analysis and adapts them to the causal analysis in non-parametric and semi-parametric frameworks.

RESULTS

The causalCmprsk package has two main functions: fit.cox assumes a semiparametric structural Cox proportional hazards model for the counterfactual cause-specific hazards, while fit.nonpar does not impose any structural assumptions. In both frameworks, causalCmprsk implements estimators of (i) absolute risks for each treatment arm, e.g., cumulative hazards or cumulative incidence functions, and (ii) relative treatment effects, e.g., hazard ratios, or restricted mean time differences. The latter treatment effect measure translates the treatment effect from probability into more intuitive time domain and allows the user to quantify, for example, by how many days or months the treatment accelerates the recovery or postpones illness or death.

CONCLUSIONS

The causalCmprsk package provides a convenient and useful tool for causal analysis of competing risks data. It allows the user to distinguish between different causes of the end of follow-up and provides several time-varying measures of treatment effects. The package is accompanied by a vignette that contains more details, examples and code, making the package accessible even for non-expert users.

Preterm births prevalence during the COVID-19 pandemic in Brazil: results from the national database

The SARS-CoV-2 (COVID-19) pandemic impacted the health systems between and within countries, and in the course of the pandemic sexual and reproductive health services were the most disrupted. Findings from high-income settings have reported significant changes in preterm birth prevalence during the pandemic period. To understand the possible effects of the COVID-19 pandemic on preterm birth numbers at the Brazilian national level. We compare the number of preterm deliveries during the COVID-19 pandemic period (2020 and 2021) with previous years. We conducted a population-based cross-sectional study taking the period from January 2017 to December 2021 to account. We use individual-level live births data from the Brazilian Live Birth Information System (SINASC), and we estimate the odds ratio (OR) of preterm deliveries using propensity score weighting analysis in Brazil and its regions. During the study period (from 2017 to 2021), about 2.7 million live births were recorded per year, and the missing value for gestational age at delivery was less than 1.5%. The preterm birth prevalence slightly increased during the COVID-19 pandemic compared to the pre-pandemic period (11.32% in 2021 vs 11.09% in 2019, p-value < 0.0001). After adjusting for sociodemographic variables, the OR of preterm births in Brazil has significantly increased, 4% in 2020 (OR: 1.04 [1.03-1.05] 95% CI, p-value < 0.001), and 2% in 2021(OR: 1.02 [1.01-1.03] 95% CI, p-value < 0.001), compared to 2019. At the regional level, the preterm birth pattern in the South, Southeast and Northeast regions show a similar pattern. The highest odds ratio was observed in the South region (2020 vs 2019, OR: 1.07 [1.05-1.10] 95% CI; 2021 vs 2019, OR: 1.03 [1.01-1.06] 95% CI). However, we also observed a significant reduction in the ORs of preterm births in the northern region during the COVID-19 pandemic (2020 vs 2019, OR: 0.96 [0.94-0.98] 95% CI) and (2021 vs 2019, OR: 0.97 [0.95-0.99] 95% CI). Our analysis shows that the pandemic has increased regional variation in the number of preterm births in Brazil in 2020 and 2021 compared to the pre-pandemic years.

Confounding adjustment in the analysis of augmented randomized controlled trial with hybrid control arm

The augmented randomized controlled trial (RCT) with hybrid control arm includes a randomized treatment group (RT), a smaller randomized control group (RC), and a large synthetic control (SC) group from real-world data. This kind of trial is useful when there is logistics and ethics hurdle to conduct a fully powered RCT with equal allocation, or when it is necessary to increase the power of the RCT by incorporating real-world data. A difficulty in the analysis of augmented RCT is that the SC and RC may be systematically different in the distribution of observed and unmeasured confounding factors, causing bias when the two control groups are analyzed together as hybrid controls. We propose to use propensity score (PS) analysis to balance the observed confounders between SC and RC. The possible bias caused by unmeasured confounders can be estimated and tested by analyzing propensity score adjusted outcomes from SC and RC. We also propose a partial bias correction (PBC) procedure to reduce bias from unmeasured confounding. Extensive simulation studies show that the proposed PS + PBC procedures can improve the efficiency and statistical power by effectively incorporating the SC into the RCT data analysis, while still control the estimation bias and Type I error inflation that might arise from unmeasured confounding. We illustrate the proposed statistical procedures with data from an augmented RCT in oncology.

Variance estimation for the average treatment effects on the treated and on the controls

Common causal estimands include the average treatment effect, the average treatment effect of the treated, and the average treatment effect on the controls. Using augmented inverse probability weighting methods, parametric models are judiciously leveraged to yield doubly robust estimators, that is, estimators that are consistent when at least one the parametric models is correctly specified. Three sources of uncertainty are associated when we evaluate these estimators and their variances, that is, when we estimate the treatment and outcome regression models as well as the desired treatment effect. In this article, we propose methods to calculate the variance of the normalized, doubly robust average treatment effect of the treated and average treatment effect on the controls estimators and investigate their finite sample properties. We consider both the asymptotic sandwich variance estimation, the standard bootstrap as well as two wild bootstrap methods. For the asymptotic approximations, we incorporate the aforementioned uncertainties via estimating equations. Moreover, unlike the standard bootstrap procedures, the proposed wild bootstrap methods use perturbations of the influence functions of the estimators through independently distributed random variables. We conduct an extensive simulation study where we vary the heterogeneity of the treatment effect as well as the proportion of participants assigned to the active treatment group. We illustrate the methods using an observational study of critical ill patients on the use of right heart catherization.

Does Internet Use Impact the Health Status of Middle-Aged and Older Populations? Evidence from China Health and Retirement Longitudinal Study (CHARLS)

In the context of both rapid technological development and increasing aging, the relationship between technological development and the health of the middle-aged and older population is gradually receiving academic attention. This study empirically examined the health consequences of the Internet for the middle-aged and older population in China using data from the 2018 China Health and Retirement Longitudinal Study. The results indicated that Internet use was effective in improving the self-assessed health and chronic disease status of the middle-aged and older population. However, the effect of Internet use on the improvement of chronic disease conditions in this population was more pronounced than self-assessed health. In the heterogeneity analysis, the effect of Internet use on the health of female and middle-aged adults was more significant than that of male and older adults aged >60 years. This paper also used a propensity score matching model to eliminate the endogeneity problem caused by sample selectivity bias. The results revealed that the propensity score matching model analysis was more robust. Moreover, if sample selectivity bias was not eliminated, the effect of Internet use on the improvement of self-assessed health in the middle-aged and older population would be underestimated, whereas the effect of Internet use on the chronic disease status of the middle-aged and older adults would be overestimated.

Causal inference methods for small non-randomized studies: Methods and an application in COVID-19

The usual development cycles are too slow for the development of vaccines, diagnostics and treatments in pandemics such as the ongoing SARS-CoV-2 pandemic. Given the pressure in such a situation, there is a risk that findings of early clinical trials are overinterpreted despite their limitations in terms of size and design. Motivated by a non-randomized open-label study investigating the efficacy of hydroxychloroquine in patients with COVID-19, we describe in a unified fashion various alternative approaches to the analysis of non-randomized studies. A widely used tool to reduce the impact of treatment-selection bias are so-called propensity score (PS) methods. Conditioning on the propensity score allows one to replicate the design of a randomized controlled trial, conditional on observed covariates. Extensions include the g-computation approach, which is less frequently applied, in particular in clinical studies. Moreover, doubly robust estimators provide additional advantages. Here, we investigate the properties of propensity score based methods including three variations of doubly robust estimators in small sample settings, typical for early trials, in a simulation study. R code for the simulations is provided.