{Maicplus}: An R Package to Support Analysis and Reporting of Matching Adjusted Indirect Treatment Comparisons (MAIC) for HTA Dossiers

OBJECTIVES: Sponsors are required to submit evidence of relative effectiveness of their treatment comparing to relevant comparators that may not be included in their clinical trial, for health technology assessment (HTA) in different countries. Matching-adjusted indirect treatment comparison (MAIC), by Signovrovitch et al. 2012, is a prevalent and well-accepted method to derive population-adjusted treatment effect in such case for two trials, one of which has Individual patient data (IPD) and the other has only aggregate data (AgD). However, there is a lack of open-source R packages following good software engineering practices for conducting and reporting MAIC analyses. This work introduces an R package {maicplus} developed jointly in a cross-industry workgroup (HTA-R workstream) to fill the gap.

METHODS: The implementation of MAIC needs to account for anchored or unanchored cases, different clinical endpoint types (time-to-event, binary, count, or continuous), and two common approaches to address estimation uncertainty (sandwich estimator and bootstrapping).

RESULTS: {maicplus} has functions to address all aforementioned analysis scenarios. A structured map of key functionalities is presented for easier package adoption. Then, essential documentation (e.g., user manual, example implementation, validation evidence) is highlighted via annotations on screenshots of the package website. Finally, key points of good software engineering practices are shared with other auxiliary information, such as future work plans, GitHub repository, how to provide user feedback or report bugs, etc.

CONCLUSIONS: It will benefits our HTA community (sponsors and payers) in the long run to have more open-source R tools that are developed and maintained following good software engineering practices. In addition to leveraging each other’s expertise and resource to create a standard tool for a common analysis for HTA submissions, open source collaboration brings in strong transparency of implementation details and real-world testing for high quality. {maicplus} was created as a result of such effort.