• Many packages fit the second stage of a two-stage IPD network meta-analysis, such as network in Stata, and netmeta in R. A nice overview of various packages is given here.

• Bayesian one-stage and two-stage approaches to network meta-analysis are provided here, and could be adapted for IPD situations.

​

• For combining IPD and aggregate data, multilevel network meta-regression (ML-NMR) can be seen as a natural extension of IPD network meta-regression for incorporating aggregate data.

• In brief, the approach simultaneously fits a participant-level model (to the IPD trials) and an aggregate-level model (to the aggregate data trials). The approach recognises that aggregate data arise from averaging over a population of individuals (trial participants), and so the included aggregate-level model arises from averaging (i.e. integrating) the included participant-level model over the population in each aggregate data trial.

• Notably, ML-NMR reduces to a one-stage network IPD meta-regression when every trial has IPD, and reduces to a network meta-analysis of aggregate data when no adjustment is to be performed (i.e. the second stage of the two-stage approach).

• ML-NMR models can be fitted using the R package multinma.