Work

Machine learning to predict urine culture antibiotic sensitivities in the emergency department

Year: 2025

Type: article

Abstract: Background Urinary tract infections (UTIs) are among the most common bacterial infections diagnosed in the emergency department. Treatment of UTIs is largely empiric because urine culture results are not rapidly available. Objectives We examined whether machine learning could predict antibiotic sensitivities of the urine cultures by using only data available during the clinical encounter. Methods We used extreme gradient boosting (XGBoost) to examine 62,963 emergency department patient encounters from January 1, 2017, through December 31, 2021. All encounters included a urinalysis and urine culture. We included 1303 variables in the full model and examined 21 antibiotics. An antibiotic was characterized as sensitive only if all bacteria in the culture were susceptible; if ≥ 1 bacteria was not susceptible, then it was characterized as intermediate or resistant . Results We predicted urine cultures to be sensitive vs intermediate or resistant with area under the receiver operating curve (AUROC) values ranging from 70 % (for amikacin) to 90 % (for linezolid) (median, 82 %) when negative urine cultures were characterized as antibiotic susceptible. AUROCs were as follows: nitrofurantoin (84 %); trimethoprim + sulfamethoxazole (80 %); ciprofloxacin (85 %); levofloxacin (85 %); first-generation cephalosporins (84 %); and third-generation cephalosporins (80 %). When models excluded urine cultures with no bacterial growth, AUROCs ranged from 66 % (for ampicillin) to 87 % (for amikacin) (median, 74 %). When models included only patients diagnosed with a UTI plus bacteriuria (≥10,000 colony-forming units per mL in urine culture), AUROCs ranged from 63 % (for ampicillin) to 85 % (for tetracycline) (median, 74 %). Conclusion XGBoost can predict bacteriuria antibiotic sensitivities.

Source: Heliyon

DOI: 10.1016/j.heliyon.2025.e42737

Authors: Johnathan M. Sheele, Ronna L. Campbell, Derick D. Jones

Institutions: Mayo Clinic in Florida, Mayo Clinic

Language: English

Topic: Urinary Tract Infections Management

Subfield: Epidemiology

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $2,270