A multicenter propensity score matched analysis in 73,843 patients of an association of nutritional risk with mortality, length of stay and readmission rates

Abstract

The reported prevalences and effects of nutritional risk vary widely in the literature because of both methodological differences (e.g., screening tools and statistical analyses) and different patient populations. In this study the authors analyzed in-hospital mortality, 30-d mortality, readmission within 4 mo, and justified length of stay (jLoS) (determined by governmental assessment to justify financial compensation) in hospitalized patients nutritionally at risk compared with hospitalized patients not at risk. This was a multicenter retrospective cohort study in 6 Belgian hospitals among inpatients in 2018. Propensity score matching was applied, including comorbidity score and exact matching for hospital, age group, sex, type of admission, living situation, and medical specialty. In total, 73,843 of 85,677 patients were screened at admission, with 16,141 found to have nutritional risk (prevalence of 21.9%). Oncology patients had the highest risk prevalence of 38.3%, whereas patients receiving plastic or reconstructive surgery had a prevalence of 5.2%. Patients nutritionally at risk had higher odds of dying in the hospital (5.1% compared with 3.3%; OR: 1.56; 95% CI: 1.37, 1.76), dying within 30 d of admission (6.8% compared with 4.3%; OR: 1.62; 95% CI: 1.45, 1.81) and being readmitted within 4 mo after discharge (35.5% compared with 32.9%; OR: 1.12; 95% CI: 1.07, 1.18). These differences were consistent across hospitals. The association between being nutritionally at risk and jLoS was ambiguous. One out of 5 patients included in this study was nutritionally at risk. Using propensity score matching, higher odds of in-hospital mortality, readmission, and 30-d mortality were observed. In contrast to oft-reported increased length of stay with poor nutrition, propensity matched data for jLoS suggested that this association was less pronounced in this cohort.