Integrating socioeconomic deprivation indices and electronic health record data to predict antimicrobial resistance

Machine learning models have been developed to predict the presence of Antimicrobial Resistance (AMR) organisms in blood cultures at the first patient encounter. The models use three supervised classifiers: penalized logistic regression, random forest, and XGBoost, and classify five AMR organisms: ESBL, CRE, AmpC, MRSA, and VRE. The combination of ADI and SVI increases predictive power, potentially reducing costs and mitigating the global public health threat of antibiotic-resistant infections.