Systematic review & meta analysis
Download as PPTX, PDF1 like224 views
This document provides an overview of different types of systematic reviews and meta-analyses, including how to conduct them. It discusses formulating an appropriate research question using PICO (Population, Intervention, Comparison, Outcome), searching for relevant articles, assessing quality, conducting meta-analyses to quantitatively summarize results, and interpreting forest plots. Some advantages of meta-analyses are improving precision and power to detect effects by combining multiple studies. However, pitfalls include bias from only publishing statistically significant results and agenda-driven biases in selectively including studies.
Systematic review & meta analysis
- 1. Systematic Review & Meta- analysis Ahmad Abed Ahmadi BSPH, MSc
- 5. Types of Review • Narrative review • Systematic review • Scoping review • Rapid review • Cochrane systematic review • Meta analysis • Network meta analysis • Individual patient data (IPD) meta analysis
- 6. Types of Review • Systematic review (Qualitative summary) • Meta-analysis (Quantitative summary)
- 7. How to conduct a review
- 8. Why bother • Good questions • Timely topics • Topics with multiple studies • Topics with conflicting results
- 9. Formulating the question • Specific and spliced • Don’t take a random question • The question doesn’t need to be complex • You don’t need to always be first • You should select a topic of your interest • Use the PICO
- 10. Research Question How does a social history of smoking in patients diagnosed with COVID-19 affect disease severity? P- COVID-19 patients who are smokers I- Active smoking in COVID-19 patients C- COVID-19 patients who are non-smokers O- Disease progression, intensive care unit admission, need for mechanical ventilation, and mortality
- 11. Draft your research strategy • Question • How does a social history of smoking in patients diagnosed with COVID-19 affect disease severity? • Keywords • smoking status • COVID‐19 • Inclusion • Randomized, and observational studies reporting the smoking status of hospitalized patients presenting with different severities of disease and/or at least one clinical endpoint of interest.
- 12. Draft your research strategy • Exclusion • Studies on other coronaviruses or if there was insufficient information to distinguish disease severity based on smoking status. • Case series involving less than 20 patients, review articles, editorials, conference abstracts, and nonclinical studies as well as Preprints. • Search limits • No language limitations
- 13. Register your study • Register in Prospero
- 14. Performing the review • Be systematic in your search • Source of articles • Pubmed (medline) • EMBASE • Cochrane central register of trials • Other topic specific • Grey literature (google scholar) • Reference section of articles
- 15. Searching for articles • Controlled vocabulary • MeSH headings – for medline • Embase - Emtree
- 18. Tools to stay organized • Rayyan • Covidence • Revman • Cochrane
- 20. Quality assessment • Observational studies • Newcastle Ottawa scales (better if 2 people do it independitly) • Robins-1 • Randomized trials • Cochrane tool
- 22. When to meta analysis • Multiple high quality studies with: • Similar design • Population • Comparator(s), and • Similar outcomes
- 23. When to not meta analyze • Studies or (study outcomes) are too heterogeneous • Too few studies available • Studies are too low quality
- 24. What does meta analysis gives you • Graphical display to: • Illustrate the strength of effects among studies • Examine uncertainty around individual studies • Visually apprise evidence of heterogeneity • Report combined effect of the individual studies • Concisely summarize strength of effect, precision and heterogeneity
- 25. Estimating a summary measure (Pooled effect) Weighting options: • Fixed effects • Random effects
- 26. Types of between study heterogeneity • Clinical • Participant characteristics • Exposures/interventions • outcomes • Methodological • Study design • Study quality • Statistical
- 28. Forest plot showing the effect of current smoking on severe COVID‐19
- 29. Forest plot showing the effect of current smoking on severe or critical COVID‐19
- 30. Forest plot showing the effect of current smoking on mortality
- 32. Forest plot showing the effect of a smoking history on severe COVID‐19
- 33. Forest plot showing the effect of a smoking history on severe or critical COVID‐19
- 34. Forest plot showing the effect of a smoking history on mortality
- 36. Advantages of meta-analysis • Results can be generalized to a larger population • The precision and accuracy of estimates can be improved as more data is used. This, in turn, may increase the statistical power to detect an effect. • Inconsistency of results across studies can be quantified and analyzed. For instance, does inconsistency arise from sampling error, or are study results (partially) influenced by between-study heterogeneity. • Hypothesis testing can be applied on summary estimates, • Moderators can be included to explain variation between studies
- 37. Pitfalls • A meta-analysis of several small studies does not predict the results of a single large study. • Some have argued that a weakness of the method is that sources of bias are not controlled by the method: • a good meta-analysis of badly designed studies will still result in bad statistics • this would mean that only methodologically sound studies should be included in a meta-analysis, a practice called 'best evidence synthesis'. • Other meta-analysts would include weaker studies, and add a study-level predictor variable that reflects the methodological quality of the studies to examine the effect of study quality on the effect size.
- 38. Publication bias: the file drawer problem • Another potential pitfall is the reliance on the available corpus of published studies, which may create exaggerated outcomes due to publication bias, as studies which show negative results or insignificant results are less likely to be published. • For example, one may have overlooked dissertation studies or studies that have never been published. • This is not easily solved, as one cannot know how many studies have gone unreported. • The distribution of effect sizes can be visualized with a funnel plot which is a scatter plot of sample size and effect sizes.
- 39. Agenda-driven bias • The most severe fault in meta-analysis often occurs when the person or persons doing the meta-analysis have an economic, social, or political agenda such as the passage or defeat of legislation. • People with these types of agendas may be more likely to abuse meta-analysis due to personal bias. • For example, researchers favorable to the author's agenda are likely to have their studies cherry-picked while those not favorable will be ignored or labeled as "not credible". • In addition, the favored authors may themselves be biased or paid to produce results that support their overall political, social, or economic goals in ways such as selecting small favorable data sets and not incorporating larger unfavorable data sets. • The influence of such biases on the results of a meta-analysis is possible because the methodology of meta-analysis is highly malleable
- 41. تشکر ! ؟