Using observational study data as an external control group for a clinical trial: an empirical comparison of methods to account for longitudinal missing data

Abstract

Background Observational data are increasingly being used to conduct external comparisons to clinical trials. In this study, we empirically examined whether different methodological approaches to longitudinal missing data affected study conclusions in this setting. Methods We used data from one clinical trial and one prospective observational study, both Norwegian multicenter studies including patients with recently diagnosed rheumatoid arthritis and implementing similar treatment strategies, but with different stringency. A binary disease remission status was defined at 6, 12, and 24 months in both studies. After identifying patterns of longitudinal missing outcome data, we evaluated the following five approaches to handle missingness: analyses of patients with complete follow-up data, multiple imputation (MI), inverse probability of censoring weighting (IPCW), and two combinations of MI and IPCW. Results We found a complex non-monotone missing data pattern in the observational study (N = 328), while missing data in the trial (N = 188) was monotone due to drop-out. In the observational study, only 39.0% of patients had complete outcome data, compared to 89.9% in the trial. All approaches to missing data indicated favorable outcomes of the treatment strategy in the trial and resulted in similar study conclusions. Variations in results across approaches were mainly due to variations in estimated outcomes for the observational data. Conclusions Five different approaches to handle longitudinal missing data resulted in similar conclusions in our example. However, the extent and complexity of missing observational data affected estimated comparative outcomes across approaches, highlighting the need for careful consideration of methods to account for missingness in this setting. Based on this empirical examination, we recommend using a prespecified advanced missing data approach to account for longitudinal missing data, and to conduct alternative approaches in sensitivity analyses.

Use of external control arms in immune-mediated inflammatory diseases: a systematic review

“…Characteristics of included studies Ten of the 43 included studies (23%) compared the active arm(s) of an RCT to an ECA (table 1). [19][20][21][22][23][24][25][26][27][28] Five of the included RCTs (5/10; 50%) prospectively leveraged external control data as part of the study design. [19][20][21][22][23] Four of these studies (4/5; 80%) randomised participants to 1 of 2 active arms and used an ECA to completely replace the function of a placebo arm, while 1 (1/5; 20%) was a placebo-controlled RCT that incorporated external data to augment the sample size of the placebo group.…”

“…The remaining five RCTs (5/10; 50%) retrospectively compared data from the active arm(s) of prior (4/5; 80%) or ongoing (1/5; 20%) phase 1-3 trials with an ECA. [24][25][26][27][28] Most of the included RCTs enrolled adults (7/10; 70%), with 3 of the 10 trials (30%) conducted in paediatric populations. Study populations comprised patients with inflammatory bowel disease (4/10; 40% (ulcerative colitis: 2/10; 20%, Crohn's disease: 2/10; 20%)), rheumatoid arthritis (4/10; 40%), psoriasis (1/10; 10%), and ankylosing spondylitis (1/10; 10%).…”