Biostatistics and epidemiology
Systematic reviews and meta-analysis
How a systematic review is built, how a meta-analysis pools trials by inverse-variance weighting, reading a forest and funnel plot, heterogeneity (I²), publication bias and GRADE.
Tier 1Medical sciences concept
Written with AI assistance and fact-checked against the sources below. For exam study, not clinical decisions. How notes are made
At a glance
- A systematic review answers a focused question (PICO) with a prespecified protocol, a reproducible search of several databases, duplicate screening and data extraction, and formal risk-of-bias assessment. A narrative review does none of this.
- A meta-analysis is the optional statistical step: pooling the results of the included studies into one estimate with a confidence interval.
- Pooling adds precision, not validity. A meta-analysis of biased trials gives a precise, biased answer.
Loading the rest of the note…
Finished reading?
Sources
- Cochrane Handbook for Systematic Reviews of InterventionsCochrane (Higgins, Thomas et al.), 6.5 (2024)
- The PRISMA 2020 statement: an updated guideline for reporting systematic reviewsBMJ (Page et al., 2021;372:n71), 2020
- GRADE handbook for grading quality of evidence and strength of recommendationsGRADE Working Group (Schünemann et al.), 2013
- Bias in meta-analysis detected by a simple, graphical testBMJ (Egger et al., 1997;315:629-34)
- ISIS-4: a randomised factorial trial assessing early oral captopril, oral mononitrate, and intravenous magnesium sulphate in 58,050 patients with suspected acute myocardial infarctionLancet (ISIS-4 Collaborative Group, 1995;345:669-85)
- Last updated
- 14 November 2026
What changed
- 14 November 2026 Turnstile bot check on sign-in and signed-out feedback