Arbitrated Indirect Treatment Comparisons

TL;DR

The paper addresses the MAIC paradox in population-adjusted indirect comparisons by proposing arbitrated indirect treatment comparisons that target a common overlap population. It introduces overlap weights and extends them to two-trial settings, enabling estimands for the overlap population (ATO) and a clean decomposition of treatment contrasts via a common comparator. Two arbitrated MAIC implementations are presented: one where an arbitrator has IPD on covariates and one where IPD is not shared, including covariate simulation for the latter; a case study demonstrates that arbitration yields a consistent AB treatment effect in the overlap population, resolving the paradox. The work provides a principled framework for HTA submissions that ensures cross-sponsor consistency and paves the way for arbitrated extensions to related PAIC methods such as STC.

Abstract

Matching-adjusted indirect comparison (MAIC) has been increasingly employed in health technology assessments (HTA). By reweighting subjects from a trial with individual participant data (IPD) to match the covariate summary statistics of another trial with only aggregate data (AgD), MAIC facilitates the estimation of a treatment effect defined with respect to the AgD trial population. This manuscript introduces a new class of methods, termed arbitrated indirect treatment comparisons, designed to address the ``MAIC paradox'' -- a phenomenon highlighted by Jiang et al.~(2025). The MAIC paradox arises when different sponsors, analyzing the same data, reach conflicting conclusions regarding which treatment is more effective. The underlying issue is that each sponsor implicitly targets a different population. To resolve this inconsistency, the proposed methods focus on estimating treatment effects in a common target population, specifically chosen to be the overlap population.