Charlson comorbidity indices and in-hospital deaths in patients with hip fractures

Abstract

Background: The Charlson Comorbidity Index (CCI) and its modifications are comorbidity-based measures that predict mortality. It was developed for patients without trauma and inconsistently predicted mortality and adverse events in several previous studies of patients with trauma.

Purpose: We therefore (1) determined whether the three different CCIs were predictors for in-hospital deaths in patients with hip fractures, (2) verified if the CCI mortality prediction had changed with time, (3) evaluated other predictors of in-hospital death in patients with hip fractures, and (4) determined if the CCI has predicted in-hospital adverse events.

Methods: We retrospectively reviewed a nationwide probability sample survey, the National Hospital Discharge Survey. More than 6 million adult patients with hip fractures and their associated comorbidities were scored by the original 1987 CCI, the 1994 age-adjusted CCI, and the 2011 updated, reweighted CCI. The three mortality indices' predictive values and predictors of in-hospital adverse events were compared.

Results: For patients with hip fractures, all three CCI variations predicted in-hospital mortality. The receiver operating curves (ROC) of the models were less than 0.68, but they improved when we used statistical models that included age, sex, concomitant injuries, and other comorbidities not contained in the CCI models (ROC > 0.74). The age-adjusted CCI accuracy was slightly better than the other two CCIs. Adverse events during hospital stays were associated with a higher CCI, pertrochanteric fracture (versus transcervical), abdominal, chest, or head trauma, atrial fibrillation, multiple fractures, female sex, and longer hospital stays; however, the accuracy of this model was poor (ROC = 0.65).

Conclusions: While all three CCI variations predicted in-hospital mortality in patients with hip fractures, other factors may be of value in patients with trauma.