Model-based standardization using multiple imputation.

BACKGROUND: When studying the association between treatment and a clinical outcome, a parametric multivariable model of the conditional outcome expectation is often used to adjust for covariates. The treatment coefficient of the outcome model targets a conditional treatment effect. Model-based standardization is typically applied to average the model predictions over the target covariate distribution, and generate a covariate-adjusted estimate of the marginal treatment effect. METHODS: The standard approach to model-based standardization involves maximum-likelihood estimation and use of the non-parametric bootstrap. We introduce a novel, general-purpose, model-based standardization method based on multiple imputation that is easily applicable when the outcome model is a generalized linear model. We term our proposed approach multiple imputation marginalization (MIM). MIM consists of two main stages: the generation of synthetic datasets and their analysis. MIM accommodates a Bayesian statistical framework, which naturally allows for the principled propagation of uncertainty, integrates the analysis into a probabilistic framework, and allows for the incorporation of prior evidence. RESULTS: We conduct a simulation study to benchmark the finite-sample performance of MIM in conjunction with a parametric outcome model. The simulations provide proof-of-principle in scenarios with binary outcomes, continuous-valued covariates, a logistic outcome model and the marginal log odds ratio as the target effect measure. When parametric modeling assumptions hold, MIM yields unbiased estimation in the target covariate distribution, valid coverage rates, and similar precision and efficiency than the standard approach to model-based standardization. CONCLUSION: We demonstrate that multiple imputation can be used to marginalize over a target covariate distribution, providing appropriate inference with a correctly specified parametric outcome model and offering statistical performance comparable to that of the standard approach to model-based standardization.

Methodological considerations for novel approaches to covariate-adjusted indirect treatment comparisons.

We examine four important considerations in the development of covariate adjustment methodologies for indirect treatment comparisons. First, we consider potential advantages of weighting versus outcome modeling, placing focus on bias-robustness. Second, we outline why model-based extrapolation may be required and useful, in the specific context of indirect treatment comparisons with limited overlap. Third, we describe challenges for covariate adjustment based on data-adaptive outcome modeling. Finally, we offer further perspectives on the promise of doubly robust covariate adjustment frameworks.

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.

Parametric G-computation for compatible indirect treatment comparisons with limited individual patient data.

Population adjustment methods such as matching-adjusted indirect comparison (MAIC) are increasingly used to compare marginal treatment effects when there are cross-trial differences in effect modifiers and limited patient-level data. MAIC is based on propensity score weighting, which is sensitive to poor covariate overlap and cannot extrapolate beyond the observed covariate space. Current outcome regression-based alternatives can extrapolate but target a conditional treatment effect that is incompatible in the indirect comparison. When adjusting for covariates, one must integrate or average the conditional estimate over the relevant population to recover a compatible marginal treatment effect. We propose a marginalization method based on parametric G-computation that can be easily applied where the outcome regression is a generalized linear model or a Cox model. The approach views the covariate adjustment regression as a nuisance model and separates its estimation from the evaluation of the marginal treatment effect of interest. The method can accommodate a Bayesian statistical framework, which naturally integrates the analysis into a probabilistic framework. A simulation study provides proof-of-principle and benchmarks the method's performance against MAIC and the conventional outcome regression. Parametric G-computation achieves more precise and more accurate estimates than MAIC, particularly when covariate overlap is poor, and yields unbiased marginal treatment effect estimates under no failures of assumptions. Furthermore, the marginalized regression-adjusted estimates provide greater precision and accuracy than the conditional estimates produced by the conventional outcome regression, which are systematically biased because the measure of effect is non-collapsible.

Comparison of Parametric Survival Extrapolation Approaches Incorporating General Population Mortality for Adequate Health Technology Assessment of New Oncology Drugs.

OBJECTIVES: Survival extrapolation of trial outcomes is required for health economic evaluation. Generally, all-cause mortality (ACM) is modeled using standard parametric distributions, often without distinguishing disease-specific/excess mortality and general population background mortality (GPM). Recent National Institute for Health and Care Excellence guidance (Technical Support Document 21) recommends adding GPM hazards to disease-specific/excess mortality hazards in the log-likelihood function ("internal additive hazards"). This article compares alternative extrapolation approaches with and without GPM adjustment. METHODS: Survival extrapolations using the internal additive hazards approach (1) are compared to no GPM adjustment (2), applying GPM hazards once ACM hazards drop below GPM hazards (3), adding GPM hazards to ACM hazards (4), and proportional hazards for ACM versus GPM hazards (5). The fit, face validity, mean predicted life-years, and corresponding uncertainty measures are assessed for the active versus control arms of immature and mature (30- and 75-month follow-up) multiple myeloma data and mature (64-month follow-up) breast cancer data. RESULTS: The 5 approaches yielded considerably different outcomes. Incremental mean predicted life-years vary most in the immature multiple myeloma data set. The lognormal distribution (best statistical fit for approaches 1-4) produces survival increments of 3.5 (95% credible interval: 1.4-5.3), 8.5 (3.1-13.0), 3.5 (1.3-5.4), 2.9 (1.1-4.5), and 1.6 (0.4-2.8) years for approaches 1 to 5, respectively. Approach 1 had the highest face validity for all data sets. Uncertainty over parametric distributions was comparable for GPM-adjusted approaches 1, 3, and 4, and much larger for approach 2. CONCLUSION: This study highlights the importance of GPM adjustment, and particularly of incorporating GPM hazards in the log-likelihood function of standard parametric distributions.

Methods for population adjustment with limited access to individual patient data: A review and simulation study.

Population-adjusted indirect comparisons estimate treatment effects when access to individual patient data is limited and there are cross-trial differences in effect modifiers. Popular methods include matching-adjusted indirect comparison (MAIC) and simulated treatment comparison (STC). There is limited formal evaluation of these methods and whether they can be used to accurately compare treatments. Thus, we undertake a comprehensive simulation study to compare standard unadjusted indirect comparisons, MAIC and STC across 162 scenarios. This simulation study assumes that the trials are investigating survival outcomes and measure continuous covariates, with the log hazard ratio as the measure of effect. MAIC yields unbiased treatment effect estimates under no failures of assumptions. The typical usage of STC produces bias because it targets a conditional treatment effect where the target estimand should be a marginal treatment effect. The incompatibility of estimates in the indirect comparison leads to bias as the measure of effect is non-collapsible. Standard indirect comparisons are systematically biased, particularly under stronger covariate imbalance and interaction effects. Standard errors and coverage rates are often valid in MAIC but the robust sandwich variance estimator underestimates variability where effective sample sizes are small. Interval estimates for the standard indirect comparison are too narrow and STC suffers from bias-induced undercoverage. MAIC provides the most accurate estimates and, with lower degrees of covariate overlap, its bias reduction outweighs the loss in precision under no failures of assumptions. An important future objective is the development of an alternative formulation to STC that targets a marginal treatment effect.

Conflating marginal and conditional treatment effects: Comments on "Assessing the performance of population adjustment methods for anchored indirect comparisons: A simulation study".

In this commentary, we highlight the importance of: (1) carefully considering and clarifying whether a marginal or conditional treatment effect is of interest in a population-adjusted indirect treatment comparison; and (2) developing distinct methodologies for estimating the different measures of effect. The appropriateness of each methodology depends on the preferred target of inference.