Triaging antibiotic use

Antibiotics The use of broad-spectrum, second-line antibiotics in treating urinary tract infections (UTIs) is increasing, likely because of the prevalence of antibiotic resistance. Kanjilal et al. applied a machine-learning approach calibrated to local hospital electronic health record data to predict the probability of resistance to first- and second-line antibiotic therapies for uncomplicated UTIs. The algorithm then recommended the least broad-spectrum antibiotic to which a given isolate was predicted to be nonresistant. Use of the pipeline reduced both broad-spectrum and ineffective antibiotic prescription for UTIs in the patient cohort relative to clinicians. Sci. Transl. Med. 12 , eaay5067 (2020).