Three AKT style questions about meta analysis

Описание: In this video we are going to look at three distinct questions around the AKT and what they could ask.

1) Levels of evidence
With this the key is to go in order:
Systematic reviews & Meta analysis
Randomised Control Trials
Cohort studies
Case-control studies
Case series and case studies
Expert opinion, editorials

2) Forrest plot
With this we look at how to interpret a forrest plot. With the following steps. Initially orientate with the 'no effect line'. The black diamond gives the 'overall effect' of all of the studies and the sides representing the confidence interval.

Finally each study can be looked at with the size of the block representing the weight and the two ends of the line representing the confidence intervals.

3) Funnel plot
This is all to do with publication bias. If the diagram looks like a symetrical triangle, then there is little to no bias. If it is one sided, then there is bias.

Questions two and three are based off this paper:
Effectiveness of physical activity promotion based in primary care: systematic review and meta-analysis of randomised controlled trials
Gillian Orrow, academic clinical fellow in general practice, Ann-Louise Kinmonth, foundation professor of general practice, Simon Sanderson, senior clinical research associate, Stephen Sutton, professor of behavioural science
https://www.bmj.com/content/344/bmj.e...

I hope that it helps with your AKT revision, don’t forget to check out these two videos that may help:

Confidence intervals:    • How to be confident with confidence interv...  
Mean, Median, Mode:    • AKT Data Analysis Unveiled: Mean, Median, ...