What it is
One question, all the evidence, one statistical answer.
A systematic review finds every study that has asked your question. A meta-analysis then combines their results statistically, so instead of ten small, conflicting trials you have a single pooled estimate, with a confidence interval, a measure of how much the studies disagree, and an honest read on how much to trust it.
Two types we run here
Pairwise, compares two options (A vs B) by pooling head-to-head studies.
Network, compares many treatments at once, even those never tested directly against each other, and ranks them.
Individual-patient-data (IPD), pools the raw patient-level data (or reconstructs it from published survival curves) for the most powerful, flexible analysis.
Comparing many treatments, or pooling a diagnostic test? See network meta-analyses and diagnostic accuracy meta-analyses.
