Skip to main content

Advertisement

Table 1 Summary statistics on reporting of visit irregularity, predictors of visit times, and methods of analysis

From: Longitudinal studies that use data collected as part of usual care risk reporting biased results: a systematic review

Outcomes of Interest N (out of 44) %
Study design
 Prospective 10 23
 Retrospective 31 70
 Unclear 3 7
Clearly defined end of study
 Yes 34 77
 No 10 23
Comparison of those with and without full follow-up among studies with a clearly defined end of follow-up (out of 34)  
 Yes 5 15
 No 24 71
 Not Applicable (all participants had full follow-up) 5 15
Method of analysis
 Linear or logistic regression 8 18
 Gaussian process regression 1 2
 Repeated measures 11 25
 Mixed model or generalized mixed model 20 45
 GEE 3 7
 IIW-GEE 1 2
Reported summary statistics on
 Number of visits per patient 25 57
 Gaps between visits per patient 3 7
 Follow-up time per patient 25 57
Predictors of visit time assessed
 Yes 2 5
 No 41 93
 Unclear 1 2
Was there a need to account for informative visit times?
 Yes 6 14
of which
 Analysis specifically designed to check for informativeness 1 (out of 6) 18
 Informativeness inferred by reviewers 5 (out of 6) 82
Unclear 38 86
Method used to account for informative visit times for studies with sufficient reporting of an identifiable need (out of 6)  
 Yes 1 19
 No 5 81