Factors influencing the enrollment in randomized controlled trials in orthopedics

Abstract

Background: Low enrollment rates are a threat to the external validity of clinical trials. The purpose of this study was to identify factors associated with lower enrollment rates in randomized controlled trials (RCTs) involving orthopedic procedures.

Methods: We performed a search in PubMed/MEDLINE for RCTs that involved any orthopedic surgical procedure, compared different intraoperative interventions, were published in English in a peer-reviewed journal between 2003 and 2014, and reported the numbers of both enrolled and eligible subjects. The primary outcome was the enrollment rate, defined as the number of enrolled subjects divided by the number of eligible subjects. We used a meta-regression to identify factors associated with lower enrollment rates.

Results: The combined estimate of enrollment rate across all 393 studies meeting inclusion criteria was 90% (95% CI: 89-92%). Trials in North America had significantly lower enrollment rates compared to trials in the rest of the world (80% vs. 92%, p < 0.0001). Trials comparing operative and non-operative treatments had significantly lower enrollment rates than trials comparing two different operative interventions (80% vs. 91%, p < 0.0001). Among trials comparing operative and non-operative interventions, there was a marked difference in enrollment rate by region: 49% in North America and 86% elsewhere (p < 0.0001).

Conclusions: RCTs investigating orthopedic procedures have variable enrollment rates depending on their location and the difference between the interventions being studied. North American trials that compare operative and non-operative interventions have the lowest enrollment rates. Investigators planning RCTs would be well advised to consider these data in planning recruitment efforts.

Keywords: Orthopedics; Randomized controlled trials; Recruitment.

Fig. 1

Paper inclusion flow chart.

Fig. 2

Proportion of included papers (i.e., meeting all inclusion criteria) to papers meeting all inclusion criteria except reporting of number of eligible subjects, by publication year (Pearson correlation coefficient r = 0.966, p < 0.0001).