Prediction of Ciprofloxacin Resistance in Hospitalized Patients Using Machine Learning

Abstract

Background: Ciprofloxacin is a widely used antibiotic that has lost efficiency due to extensive resistance. We developed machine learning (ML) models that predict the probability of ciprofloxacin resistance in hospitalized patients. Methods: Data were collected from electronic records of hospitalized patients with positive bacterial cultures, during 2016-2019. Susceptibility results to ciprofloxacin (n=10,053 cultures) were obtained for E. coli, K. pneumoniae, M. morganii, P.aeruginosa, P. mirabilis and S. aureus. An ensemble model, combining several base models, was developed to predict ciprofloxacin resistant cultures, either with (gnostic) or without (agnostic) information on the infecting bacterial species. Results: The ensemble models' predictions were well-calibrated, and yielded ROC-AUCs (area under the receiver operating characteristic curve) of 0.763 (95%CI 0.634-0.785) and 0.849 (95%CI 0.799-0.921) on independent test-sets for the agnostic and gnostic datasets, respectively. Shapley additive explanations analysis identified that influential variables were related to resistance of previous infections, where patients arrived from (hospital, nursing home, etc.), sex, and recent resistance frequencies in the hospital. A decision curve analysis revealed that implementing our models can be beneficial in a wide range of cost-benefits considerations of ciprofloxacin administration. Conclusions: This study develops ML models to predict ciprofloxacin resistance in hospitalized patients. The models achieved high predictive ability, were well calibrated, had substantial net-benefit across a wide range of conditions, and relied on predictors consistent with the literature. This is a further step on the way to inclusion of ML decision support systems into clinical practice.