Prediction of ciprofloxacin resistance in hospitalized patients using machine learning
Igor Mintz1,2, Michal Chowers3,4, Uri Obolski5,6
1School of Public Health, Tel Aviv University, Tel Aviv, Israel.
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 Escherichia coli, Klebsiella pneumoniae, Morganella morganii, Pseudomonas aeruginosa, Proteus mirabilis and Staphylococcus 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 are well-calibrated, and yield ROC-AUCs (area under the receiver operating characteristic curve) of 0.737 (95%CI 0.715-0.758) and 0.837 (95%CI 0.821-0.854) on independent test-sets for the agnostic and gnostic datasets, respectively. Shapley additive explanations analysis identifies that influential variables are related to resistance of previous infections, where patients arrived from (hospital, nursing home, etc.), and recent resistance frequencies in the hospital. A decision curve analysis reveals 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 achieve high predictive ability, are well calibrated, have substantial net-benefit across a wide range of conditions, and rely on predictors consistent with the literature. This is a further step on the way to inclusion of ML decision support systems into clinical practice.
Insights
Machine learning models predict ciprofloxacin resistance in hospitalized patients, improving antibiotic stewardship. These models offer high accuracy and clinical utility for guiding ciprofloxacin use amid rising bacterial resistance.
Area of Science:
- * Computational biology and bioinformatics
- * Infectious disease epidemiology
- * Clinical decision support systems
Background:
- * Ciprofloxacin efficacy is declining due to widespread antibiotic resistance.
- * Predicting ciprofloxacin resistance is crucial for effective patient treatment.
- * Machine learning (ML) offers a promising approach to address this challenge.
Purpose of the Study:
- * To develop and validate ML models for predicting ciprofloxacin resistance in hospitalized patients.
- * To assess the predictive performance and clinical utility of these models.
- * To identify key predictors of ciprofloxacin resistance.
Main Methods:
- * Utilized electronic health records from 2016-2019 for patients with positive bacterial cultures.
- * Collected susceptibility data for 10,053 cultures against ciprofloxacin.
- * Developed an ensemble ML model (gnostic and agnostic) to predict resistance.
Main Results:
- * Ensemble models achieved high predictive accuracy (ROC-AUCs of 0.737 and 0.837).
- * Key predictors included prior resistance, patient origin, and recent hospital resistance rates.
- * Decision curve analysis indicated significant net benefit for model implementation.
Conclusions:
- * Developed accurate and well-calibrated ML models for predicting ciprofloxacin resistance.
- * Models demonstrate clinical utility and potential for integration into practice.
- * This work advances the use of ML-driven decision support in healthcare.
