Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Population-Adjusted Indirect Treatment Comparison with the outstandR Package in R

Nathan Green, Antonio Remiro-Azocar

TL;DR

The paper introduces outstandR, an R package that provides a unified framework for population-adjusted indirect comparisons (PAIC) when IPD are available for one study and only aggregate data for another. It covers multiple PAIC methods, including MAIC, STC, parametric G-computation (MLE and Bayesian), and Multiple Imputation Marginalization, with explicit treatment of prognostic factors and effect modifiers. The framework emphasizes covariate simulation, model standardisation, and robust contrast estimation, supported by flexible variance estimation (bootstrap, sandwich, and Rubin's rules) and a modular S3 design that separates strategy specification from computation. Practical demonstrations show how to apply MAIC, STC, G-computation, and MIM across binary, continuous, and count outcomes, with options for user-defined covariate distributions and custom outcome scales. The approach advances evidence synthesis in HTA by enabling robust, transparent cross-trial comparisons under complex covariate structures, while acknowledging limitations and outlining future work on unanchored comparisons and time-to-event data.

Abstract

Indirect treatment comparisons (ITCs) are essential in Health Technology Assessment (HTA) when head-to-head clinical trials are absent. A common challenge arises when attempting to compare a treatment with available individual patient data (IPD) against a competitor with only reported aggregate-level data (ALD), particularly when trial populations differ in effect modifiers. While methods such as Matching-Adjusted Indirect Comparison (MAIC) and Simulated Treatment Comparison (STC) exist to adjust for these cross-trial differences, software implementations have often been fragmented or limited in scope. This article introduces outstandR, an R package designed to provide a comprehensive and unified framework for population-adjusted indirect comparison (PAIC). Beyond standard weighting and regression approaches, outstandR implements advanced G-computation methods within both maximum likelihood and Bayesian frameworks, and Multiple Imputation Marginalization (MIM) to address non-collapsibility and missing data. By streamlining the workflow of covariate simulation, model standardization, and contrast estimation, outstandR enables robust and compatible evidence synthesis in complex decision-making scenarios.

Population-Adjusted Indirect Treatment Comparison with the outstandR Package in R

TL;DR

The paper introduces outstandR, an R package that provides a unified framework for population-adjusted indirect comparisons (PAIC) when IPD are available for one study and only aggregate data for another. It covers multiple PAIC methods, including MAIC, STC, parametric G-computation (MLE and Bayesian), and Multiple Imputation Marginalization, with explicit treatment of prognostic factors and effect modifiers. The framework emphasizes covariate simulation, model standardisation, and robust contrast estimation, supported by flexible variance estimation (bootstrap, sandwich, and Rubin's rules) and a modular S3 design that separates strategy specification from computation. Practical demonstrations show how to apply MAIC, STC, G-computation, and MIM across binary, continuous, and count outcomes, with options for user-defined covariate distributions and custom outcome scales. The approach advances evidence synthesis in HTA by enabling robust, transparent cross-trial comparisons under complex covariate structures, while acknowledging limitations and outlining future work on unanchored comparisons and time-to-event data.

Abstract

Indirect treatment comparisons (ITCs) are essential in Health Technology Assessment (HTA) when head-to-head clinical trials are absent. A common challenge arises when attempting to compare a treatment with available individual patient data (IPD) against a competitor with only reported aggregate-level data (ALD), particularly when trial populations differ in effect modifiers. While methods such as Matching-Adjusted Indirect Comparison (MAIC) and Simulated Treatment Comparison (STC) exist to adjust for these cross-trial differences, software implementations have often been fragmented or limited in scope. This article introduces outstandR, an R package designed to provide a comprehensive and unified framework for population-adjusted indirect comparison (PAIC). Beyond standard weighting and regression approaches, outstandR implements advanced G-computation methods within both maximum likelihood and Bayesian frameworks, and Multiple Imputation Marginalization (MIM) to address non-collapsibility and missing data. By streamlining the workflow of covariate simulation, model standardization, and contrast estimation, outstandR enables robust and compatible evidence synthesis in complex decision-making scenarios.
Paper Structure (52 sections, 23 equations, 3 figures, 4 tables)

This paper contains 52 sections, 23 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Population-Adjusted Indirect Comparison (PAIC)
  3. General problem formulation
  4. Population adjustment methods
  5. Matching-Adjusted Indirect Comparison (MAIC)
  6. Simulated Treatment Comparison (STC)
  7. Model Fitting (Optimization Step)
  8. Prediction (Simulation Step)
  9. Limitations and modifications
  10. Parametric G-computation with Maximum Likelihood
  11. Maximum Likelihood Implementation Steps
  12. Simulation/Prediction Step
  13. Synthetic cohort generation
  14. Parametric G-computation with Bayesian Inference
  15. Step 1: Specify and Fit Models with Bayesian Inference
  16. ...and 37 more sections

Figures (3)

  • Figure 1: Forest plots of aboslute estimates and relative contrasts for all adjustment strategies.
  • Figure 2: Histogram of MAIC analysis distribution of weights.
  • Figure 3: Bayesian G-computation MCMC trace plots.