From: Systematic review of methods for individual patient data meta- analysis with binary outcomes
Reason | Included only randomized controlled trials (n = 15) N (%) | Included observational studies (n = 11) N (%) | Overall N (%) |
---|---|---|---|
To estimate a treatment effect | 10 (67%) | 3 (27%) | 13 (50%) |
To investigate safety of a treatment | 2 (13%) | 1 (9%) | 3 (12%) |
To estimate diagnostic accuracy | 1 (7%) | 4 (36%) | 5 (19%) |
To identify predictors | 1 (7%) | 3 (27%) | 4 (15%) |
Other/Unclear | 2 (13%) | 1 (9%) | 3 (12%) |