The Fragility Index of meta-analyses

The conclusion of a meta-analysis of a binary outcome could be changed if the outcomes of a few patients were modified within the randomized controlled trials included in it.

The Fragility Index for meta-analyses of randomized controlled trials is an intuitive measure for the confidence we have in the conclusions of a meta-analysis.

It is defined as the minimum number of patients from one or more trials included in the meta-analysis for which a modification on the event status (ie, changing events to non-events, or non-events to events) would change the statistical significance of the pooled treatment effect.

After specific event-status modifications, a statistically significant pooled treatment effect could be turned non-significant, and a statistically non-significant treatment effect could be turned significant.

Evaluate the Fragility Index for your own meta-analysis

Evaluate the fragility of the conclusions of your own meta-analysis!

How does it work

The method used to evaluate the Fragility Index of meta-analyses is based on an iterative re-evaluation of the statistical significance of the pooled treatment effect of modified meta-analyses, iteratively derived from the original meta-analysis by performing single event-status modifications in each arm of each trial in turn.

A schematic represention is available here . You can also check our code on Github.

Contact: ignacioatal--at--gmail--dot--com

Example of a statistically significant meta-analysis with Fragility Index = 2