HealthDay News — A new decision support tool could optimize antibiotic prescribing for uncomplicated urinary tract infections (UTI) in the outpatient setting, according to a study published in the Nov. 4 issue of Science Translational Medicine.
Sanjat Kanjilal, MD, from Harvard Medical School in Boston, and colleagues developed machine learning models to predict antibiotic susceptibility using electronic health record data and built a decision algorithm for recommending the narrowest possible antibiotic to which a specimen is susceptible for the treatment of uncomplicated UTI.
The researchers found that when applied to a test cohort of 3629 patients presenting between 2014 and 2016, the algorithm achieved a 67% reduction in the use of second-line antibiotics compared with clinicians. The model simultaneously reduced inappropriate antibiotic therapy by 18% compared with clinicians. In instances where clinicians chose a second-line drug but the algorithm chose a first-line drug, 92% (1066 of 1157) of specimens ended up being susceptible to the first-line drug. The algorithm chose an appropriate first-line drug 47% of the time (183 of 392) when clinicians chose an inappropriate first-line drug.
“Integrating these models into outpatient care could play an important role in reducing the use of broad-spectrum antibiotics,” Kanjilal said in a statement. “Our future work will focus on integrating these clinical decision support tools into provider workflows and evaluating the clinical outcomes using randomized controlled trials.”
One author disclosed financial ties to the technology industry.
This article originally appeared on Infectious Disease Advisor