Model‐Based Network Meta‐Analysis: A Framework for Evidence Synthesis of Clinical Trial Data

Abstract

Model‐based meta‐analysis (MBMA) is increasingly used in drug development to inform decision‐making and future trial designs, through the use of complex dose and/or time course models. Network meta‐analysis (NMA) is increasingly being used by reimbursement agencies to estimate a set of coherent relative treatment effects for multiple treatments that respect the randomization within the trials. However, NMAs typically either consider different doses completely independently or lump them together, with few examples of models for dose. We propose a framework, model‐based network meta‐analysis (MBNMA), that combines both approaches, that respects randomization, and allows estimation and prediction for multiple agents and a range of doses, using plausible physiological dose‐response models. We illustrate our approach with an example comparing the efficacies of triptans for migraine relief. This uses a binary endpoint, although we note that the model can be easily modified for other outcome types.

Model‐Based Meta‐Analysis for Multiple Myeloma: A Quantitative Drug‐Independent Framework for Efficient Decisions in Oncology Drug Development

“…MBMA is acknowledged as a valuable tool in the drug development process that is widely used for integrating data to enable informed and efficient development decisions, for example in dose–response analyses . The approach has been successfully used in other cancer types and in other therapeutic areas to assist in the development of new agents and, in combination with network meta‐analysis, to model the findings of head‐to‐head trials .…”

Model‐Informed Drug Discovery and Development: Current Industry Good Practice and Regulatory Expectations and Future Perspectives

“…The exceptions seemed to be regarding the EMA respondents perhaps having less familiarity with model‐based meta‐analysis (MBMA) approaches and their utility in providing indirect comparative efficacy and safety information, which can be used to underpin dose selection, therapeutic benefit, and facilitate trial design (see for more discussion). This highlights the need for further interaction and education in this area, including greater engagement with statistical colleagues on the merits of using pharmacology principles to maximize the value of MBMA . The mixed viewpoint with respect to quantitative systems pharmacology modeling indicates that, despite application in a regulatory context, there is also the need for more engagement in this space to fully explore the potential and the additional complexity of these approaches.…”

Model‐Based Meta‐Analysis in Ankylosing Spondylitis: A Quantitative Comparison of Biologics and Small Targeted Molecules

“…For those drugs with limited dose ranges or without noticeable dose‐response, the dose ranges were either “lumped” (assumed to have the same efficacy) or “split” (to separately estimate each dose or regimen). However, the former could result into increasing heterogeneity and the latter may lead to inadequate use of information . Therefore, this analysis integrated the two methods—we lumped all the dose/regimen together and then individually estimated the E max of the doses or regimens that have different efficacy, if a better model fit was achieved.…”

“…However, the former could result into increasing heterogeneity and the latter may lead to inadequate use of information. 30 Therefore, this analysis integrated the two methods-we lumped all the dose/regimen together and then individually estimated the E max of the doses or regimens that have different efficacy, if a better model fit was achieved.…”