Doubly robust augmented weighting estimators for the analysis of externally controlled single-arm trials and unanchored indirect treatment comparisons

TL;DR

This paper tackles the challenge of estimating treatment effects when only an externally controlled SAT and/or unanchored ITCs are available. It introduces a unified causal framework and a doubly robust augmented MAIC estimator that combines entropy-balancing weights with an outcome-model-based correction, extending to settings with unavailable external IPD. Through extensive simulations and an applied example, the authors demonstrate that the DR augmented MAIC estimator offers improved protection against model misspecification and competitive precision compared with traditional weighting and G-computation, approaching the efficiency of G-computation when the outcome model is correct. The work highlights the practical value of balancing-based approaches augmented with outcome modeling in health technology assessment and external-control analyses, while acknowledging limitations due to potential unmeasured confounding and positivity violations.

Abstract

Externally controlled single-arm trials are critical to assess treatment efficacy across therapeutic indications for which randomized controlled trials are not feasible. A closely-related research design, the unanchored indirect treatment comparison, is often required for disconnected treatment networks in health technology assessment. We present a unified causal inference framework for both research designs. We develop a novel estimator that augments a popular weighting approach based on entropy balancing -- matching-adjusted indirect comparison (MAIC) -- by fitting a model for the conditional outcome expectation. The predictions of the outcome model are combined with the entropy balancing MAIC weights. While the standard MAIC estimator is singly robust where the outcome model is non-linear, our augmented MAIC approach is doubly robust, providing increased robustness against model misspecification. This is demonstrated in a simulation study with binary outcomes and a logistic outcome model, where the augmented estimator demonstrates its doubly robust property, while exhibiting higher precision than all non-augmented weighting estimators and near-identical precision to G-computation. We describe the extension of our estimator to the setting with unavailable individual participant data for the external control, illustrating it through an applied example. Our findings reinforce the understanding that entropy balancing-based approaches have desirable properties compared to standard ``modeling'' approaches to weighting, but should be augmented to improve protection against bias and guarantee double robustness.

Figures (4)

• Figure 1: Histogram of the normalized IOW weights (left) and MAIC (entropy balancing) weights (right).
• Figure 2: Point estimates with 95% CIs of the ATC (marginal log-odds ratio of objective response) for the different estimators in the applied example. DR denotes doubly robust and EB denotes entropy balancing.
• Figure 3: Density plots showing the overlap of covariates $X_{1}$,$X_{2}$,$X_{3}$, and $X_{4}$ for Scenarios KS1 and KS2 in the simulation study.
• Figure 4: Density plots showing the overlap of covariates $X_{1}$,$X_{2}$,$X_{3}$, and $X_{4}$ for Scenarios KS3 and KS4 in the simulation study.