Send to

Choose Destination
Infect Control Hosp Epidemiol. 2019 Apr;40(4):400-407. doi: 10.1017/ice.2019.17. Epub 2019 Mar 4.

A methodological comparison of risk scores versus decision trees for predicting drug-resistant infections: A case study using extended-spectrum beta-lactamase (ESBL) bacteremia.

Author information

Department of Epidemiology,Johns Hopkins Bloomberg School of Public Health,Baltimore,Maryland.
Department of Epidemiology and Public Health,University of Maryland School of Medicine,Baltimore,Maryland.
Division of Infectious Diseases, Department of Pediatrics,Johns Hopkins University School of Medicine,Baltimore,Maryland.



Timely identification of multidrug-resistant gram-negative infections remains an epidemiological challenge. Statistical models for predicting drug resistance can offer utility where rapid diagnostics are unavailable or resource-impractical. Logistic regression-derived risk scores are common in the healthcare epidemiology literature. Machine learning-derived decision trees are an alternative approach for developing decision support tools. Our group previously reported on a decision tree for predicting ESBL bloodstream infections. Our objective in the current study was to develop a risk score from the same ESBL dataset to compare these 2 methods and to offer general guiding principles for using each approach.


Using a dataset of 1,288 patients with Escherichia coli or Klebsiella spp bacteremia, we generated a risk score to predict the likelihood that a bacteremic patient was infected with an ESBL-producer. We evaluated discrimination (original and cross-validated models) using receiver operating characteristic curves and C statistics. We compared risk score and decision tree performance, and we reviewed their practical and methodological attributes.


In total, 194 patients (15%) were infected with ESBL-producing bacteremia. The clinical risk score included 14 variables, compared to the 5 decision-tree variables. The positive and negative predictive values of the risk score and decision tree were similar (>90%), but the C statistic of the risk score (0.87) was 10% higher.


A decision tree and risk score performed similarly for predicting ESBL infection. The decision tree was more user-friendly, with fewer variables for the end user, whereas the risk score offered higher discrimination and greater flexibility for adjusting sensitivity and specificity.


Supplemental Content

Full text links

Icon for Cambridge University Press
Loading ...
Support Center