Bedside Risk Scoring for Carbapenem-Resistant Gram-Negative Bacterial Infections in Patients with Hematological Malignancies.

BACKGROUND/OBJECTIVES: This study aimed to create a 'carbapenem resistance score' with the risk factors of carbapenem-resistant Gram-negative bacterial infections (GNBIs) in patients with hematological malignancies.

METHODS

Patients with carbapenem-resistant and susceptible GNBIs were included in this study and compared in terms of risk factors. Three models of "carbapenem resistance risk scores" were created with statistically significant variables.

RESULTS

The study included 154 patients with hospital-acquired GNBIs, of whom 64 had carbapenem-resistant GNBIs and 90 had carbapenem-susceptible GNBIs. Univariate and multivariate analyses identified several statistically significant risk factors for carbapenem resistance, including transfer from another hospital or clinic ( = 0.038), prior use of antibiotics like fluoroquinolones ( = 0.009) and carbapenems ( = 0.001), a history of carbapenem-resistant infection in the last six months ( < 0.001), rectal colonization ( < 0.001), hospitalization for ≥30 days ( = 0.001), and the presence of a urinary catheter ( = 0.002). Notably, the 14-day mortality rate was significantly higher in the carbapenem-resistant group ( < 0.001). Based on these findings, three risk-scoring models were developed. Common factors in all three models were fluoroquinolone use in the last six months, rectal colonization, and the presence of a urinary catheter. The fourth variable was transfer from another hospital (Model 1), a history of carbapenem-resistant infection (Model 2), or hospitalization for ≥30 days (Model 3). All models demonstrated strong discriminative power (AUC for Model 1: 0.830, Model 2: 0.826, Model 3: 0.831). For all three models, a cutoff value of >2.5 was adopted as the threshold to identify patients at high risk for carbapenem resistance, a value which yielded high positive and negative predictive values.

CONCLUSIONS

This study successfully developed three practical risk-scoring models to predict carbapenem resistance in patients with hematological malignancies using common clinical risk factors. A cutoff score of >2.5 proved to be a reliable threshold for identifying high-risk patients across all models, providing clinicians with a valuable tool to guide appropriate empirical antibiotic therapy.