Predictive Rule for Mortality of Inpatients With Escherichia coli Bacteremia: Chi-Square Automatic Interaction Detector Decision Tree Analysis Model

Aim: A predictive rule for risk factors for mortality due to Escherichia coli (E. coli)bacteremia has not been defined, especially using the chi-square automatic interaction detector (CHAID) decision tree analysis. Here we aimed to create the predictive rule for risk factors for in-hospital mortality due to E. coli bacteremia. Methods: The outcome of this retrospective cross-sectional survey was death in the hospital due to E. coli bacteremia. Factors potentially predictive of death in the hospital due to E. coli bacteremia were analyzed using the CHAID decision tree analysis. Results: A total of 420 patients (male:female=196:224; mean±standard deviation [SD] age, 75.81±13.13 years) were included in this study. 56 patients (13.3%) died in the hospital. The CHAID decision tree analysis revealed that patients with total protein level ≤5.10 g/dL (incidence, 46.2%), total protein level ≤5.90 g/dL with disturbance of consciousness (incidence, 39.4%), and total protein level >5.90 g/dL with hemoglobin level ≤11.10 g/dL and lactate dehydrogenase level ≥312.0 IU/L (incidence, 42.3%) were included in the high-risk group. Conclusions: Appropriate preventative therapy should be facilitated in patients with E. coliat a high risk of mortality.