Objectives: We aimed to investigate center effects on hospital mortality of ICU patients with hematologic malignancies and to explore interactions between center and patients characteristics.
Design: Multicenter prospective cohort.
Setting: Seventeen ICUs across France and Belgium.
Patients: One-thousand eleven patients with hematologic malignancies hospitalized in ICUs.
Interventions: Reanalysis of the original data using state-of-the-art statistical methods with permutation procedures for testing multiple random effects.
Measurements and main results: Average crude mortality was 39% and varied from 11% to 58% across centers. There was a significant center effect on the mean hospital mortality, after adjustment on individual prognostic factors (p < 0.001; median adjusted odds ratio for center effect 1.57 [interquartile range, 1.24-2.18]). There was also a quantitative interaction between center and the effect of the Sequential Organ Failure Assessment score: higher scores were associated with higher mortality (odds ratio for 1 point = 1.24 on average; 95% CI, 1.15-1.33) but with a magnitude that depended on center (p = 0.028).
Conclusions: Between-center heterogeneity in hospital mortality was confirmed after adjustment for individual prognostic factors. It was partially explained by center experience in treating oncology patients. Interestingly, center effect was similar in magnitude to that of known mortality risk factors.