Disparities between randomized clinical trial participants and sepsis patients in real-world

The external validity or “generalizability” of randomized controlled trials (RCTs) often needs be considered when making treatment decisions. We evaluate whether participants in large multicenter RCTs investigating sepsis were similar in age, disease severity, comorbidities, and mortality to the general population of sepsis patients. Using MEDLINE, PubMed, and the Cochrane Central Register of Controlled Trials, RCTs that enrolled 100 or more adult sepsis patients from two or more sites published from 01 January 2000 to 04 August 2019 were identified. The weighted mean age of trial participants was calculated as the main variable, and it was compared with the mean ages of the overall populations derived from the MIMIC database and the EICU database. Two researchers independently screened all abstracts and performed data extraction, then aggregated the data using a random effects model. Multiple linear regression was used to determine whether any factors were significantly associated with age disparities. The mean age of the 60,577 participants in the 94 trials included in the analysis was significantly lower than those of the patients in the MIMIC and EICU databases (weighted mean age 62.28 years vs. 64.47 years for MIMIC and 65.20 years for EICU; both p < 0.001). Trial participants were less likely to have known comorbidities such as diabetes (13.96% vs. 30.64% for MIMIC and 35.75% for EICU; both p < 0.001). The weighted mortality rate in trial participants was higher than that in patients in the MIMIC and EICU databases (29.33% vs. 20.72% for MIMIC and 17.53% for EICU; both p < 0.001). Differences in age, severity score, and comorbidities remained statistically significant in sensitivity analyses. Multivariable regression suggested that commercially supported trials were more likely to include patients with higher severity scores (p = 0.002), but after adjustment for study region and sepsis diagnosis inclusion in such trials was not significantly associated with age. On average, trial participants were younger than the general sepsis patient population. Commercial support influenced patient selection. Efforts to understand and address the above-described patient disparities are necessary to improve the generalizability of RCT results. Trial registration:PROSPERO CRD42019145692.