Machine Learning for Pre-Culture ESBL Risk Stratification to Guide Empiric Antibiotic Selection: A 12-Hospital Study of Enterobacteriaceae Cultures
Abstract
Empiric antibiotic therapy for suspected ESBL-producing Enterobacteriaceae must be selected 48-72 hours before culture results, forcing clinicians to choose between undertreating resistant infections and overusing carbapenems that drive further resistance. We developed a cost-sensitive XGBoost model predicting an ESBL phenotype (resistance to ceftriaxone, ceftazidime, cefepime or piperacillin-tazobactam) at culture ordering using 45 pre-culture EHR features across 132,955 cultures from 72,217 patients at 12 hospitals (14.41% with the ESBL phenotype). Cultures were partitioned at the patient level. At 90% sensitivity, the model achieved 95.8% NPV, reducing post-test ESBL probability to 4.2%, a threshold that may support safe carbapenem-sparing in non-ICU settings, while sparing 307 of every 1,000 cultures an unnecessary broad-spectrum course at the cost of 14 missed ESBL cases per 1,000. SHAP analysis identified prior ESBL colonization as the dominant predictor, ahead of prior organism burden and neighborhood deprivation; removing deprivation features caused minimal performance loss (ΔAUROC = −0.020), enabling equitable bedside deployment. Discrimination was unchanged under a strict IDSA ESBL-E definition (AUROC 0.766), with specimen type added as a predictor (0.764) and without any class-imbalance correction (0.762), and ranged from 0.71 to 0.78 across organism strata.
Related
- A theory of stratification learning
- Learning rate selection via weighted Fisher divergence
- Learning from pandemics: Feature selection and clustering for robust digital disease nowcasting
- Continuous-Time Mean-Variance Portfolio Selection Reinforcement Learning Problems for a Markov Regime-Switching System with No-Shorting Constraints
- Covariate Selection for Doubly Robust Double/debiased Machine Learning Estimators for Causal Inference
BibTeX
@misc{kuruvikkattil2026machine,
title = {{Machine Learning for Pre-Culture ESBL Risk Stratification to Guide Empiric Antibiotic Selection: A 12-Hospital Study of Enterobacteriaceae Cultures}},
author = {Aravind V. Kuruvikkattil and Lalitha Pranathi Pulavarthy and Rashmita Kudamala and Saptarshi Purkayastha},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.05970},
eprint = {2609.05970},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.05970},
}
RIS
TY - UNPB
TI - Machine Learning for Pre-Culture ESBL Risk Stratification to Guide Empiric Antibiotic Selection: A 12-Hospital Study of Enterobacteriaceae Cultures
AU - Aravind V. Kuruvikkattil
AU - Lalitha Pranathi Pulavarthy
AU - Rashmita Kudamala
AU - Saptarshi Purkayastha
PY - 2026
DA - 2026/09/05
PB - arXiv
DO - 10.48550/arxiv.2609.05970
UR - https://arxiv.org/abs/2609.05970
AB - Empiric antibiotic therapy for suspected ESBL-producing Enterobacteriaceae must be selected 48-72 hours before culture results, forcing clinicians to choose between undertreating resistant infections and overusing carbapenems that drive further resistance. We developed a cost-sensitive XGBoost model predicting an ESBL phenotype (resistance to ceftriaxone, ceftazidime, cefepime or piperacillin-tazobactam) at culture ordering using 45 pre-culture EHR features across 132,955 cultures from 72,217 patients at 12 hospitals (14.41% with the ESBL phenotype). Cultures were partitioned at the patient level. At 90% sensitivity, the model achieved 95.8% NPV, reducing post-test ESBL probability to 4.2%, a threshold that may support safe carbapenem-sparing in non-ICU settings, while sparing 307 of every 1,000 cultures an unnecessary broad-spectrum course at the cost of 14 missed ESBL cases per 1,000. SHAP analysis identified prior ESBL colonization as the dominant predictor, ahead of prior organism burden and neighborhood deprivation; removing deprivation features caused minimal performance loss (ΔAUROC = −0.020), enabling equitable bedside deployment. Discrimination was unchanged under a strict IDSA ESBL-E definition (AUROC 0.766), with specimen type added as a predictor (0.764) and without any class-imbalance correction (0.762), and ranged from 0.71 to 0.78 across organism strata.
ER -