911±¬ÁÏÍø

This module builds on the principles of systematic review and meta-analysis covered in earlier MSc modules to provide you with the statistical knowledge and tools to perform meta-analyses based on data from clinical trials. We will cover the statistical principles of meta-analysis, including fixed-effect and random-effects models, and you will utilise these models to meta-analyse continuous, binary, and time-to-event data. You will learn how to assess and investigate heterogeneity as well as exploring the impact that bias can have in a meta-analysis. In addition, we will cover three advanced topics that are subjects of ongoing research: individual participant data (IPD) meta-analysis, networks of multiple treatments, and treatment effect modification by patient-level covariates.   Ìý

At the end of the module, you will be able to:Ìý

1. Understand the assumptions behind three popular meta-analysis models for summary data (common-effect, random-effects, fixed-effects), and perform and interpret results from eachÌý

2. Understand the interpretation of popular heterogeneity statistics, assess the degree of heterogeneity in summary data, and know how to explore possible reasons for observed heterogeneityÌý

3. Understand how bias and missing data can impact a meta-analysis, and know how to assess and account for these in practiceÌý

4. Understand the difference between individual participant data (IPD) and aggregate (summary) data, and know how to plan, conduct, and perform meta-analysis using IPDÌý

5. Understand the concepts of direct and indirect evidence on treatment comparisons, and how a network meta-analysis is built. Know how to interpret results from a network analysis.Ìý

6. Understand how baseline characteristics may modify the overall treatment effect at the trial level and at the patient level, and know how to appropriately analyse and interpret treatment-covariate interactionsÌý

7. Fit a variety of meta-analysis models using statistical software, producing forest plots and other graphical summariesÌý

This module is compulsory for students on the Statistics for Clinical Trials route of the MSc Clinical Trials.Ìý

Schmid CH, Stijnen T, White IR. Handbook of Meta Analysis. Boca Raton, FL: Chapman and Hall/CRC Press; 2020 (available UCL library)Ìý

Higgins JPT, Thompson SG, Spiegelhalter DJ. ‘A re-evaluation of random-effects meta-analysis’. Journal of the RSS Series A. 2009; 172(1): 137–159. doi: 10.1111/j.1467-985X.2008.00552.xÌý

Rice K, Higgins JPT, Lumley T. ‘A re-evaluation of fixed effect(s) meta-analysis’. Journal of the RSS Series A. 2018; 181 Part 1, 205-227. doi: 10.1111/rssa.12275Ìý

Salanti G, Higgins JPT, Ades AE, Ioannidis JPA. ‘Evaluation of networks of randomized trials’. Statistical Methods in Medical Research 2008; 17: 279-301.Ìý

Riley RD, Debray TP, Fisher D, et al. ‘Individual participant data meta analysis to examine interactions between treatment effect and participant level covariates: Statistical recommendations for conduct and planning’. Statistics in Medicine. 2020; 39: 2115– 2137Ìý

Fisher DJ, Carpenter JR, Morris TP, Freeman SC, Tierney JF. ‘Meta-analytical methods to identify who benefits most from treatments: daft, deluded, or deft approach?’ BMJ 2017; 356 :j573 doi:10.1136/bmj.j573Ìý

Burke DL, Ensor J, Riley RD. ‘Meta-analysis using individual participant data: one-stage and two-stage approaches, and why they may differ’. Stat Med. 2017 Feb 28;36(5):855-875. doi: 10.1002/sim.7141.Ìý

Morris TP, Fisher DJ, Kenward MG, Carpenter JR. ‘Meta analysis of Gaussian individual patient data: Two stage or not two stage?’ Statistics in Medicine. 2018; 37: 1419– 1438. Ìý

Godolphin PJ, White IR, Tierney JF, Fisher DF. ‘Estimating interactions and subgroup-specific treatment effects in meta-analysis without aggregation bias: A within-trial framework’. Research Synthesis Methods. 2022; 14(1): 68-78. doi: 10.1002/jrsm.1590Ìý