A modified urinary tract infection detection algorithm can be used to safely withhold antibiotics in low-risk patients



Urinary tract infections are usually diagnosed and treated in primary care. The gold standard for diagnosing a UTI is a urine culture.

However, waiting for culture results delays treatment, so doctors often prescribe antibiotics while waiting for these results. The researchers modified a urinary tract infection detection algorithm that was developed and validated in an emergency room suite to be usable in a primary care setting. The main modification was the removal of requirements for microscopy because results are often not available in primary care.

The researchers found that removing microscopy features did not severely affect the performance of the urologic detection algorithm in emergency department patients. In addition, the algorithm performed well in the primary care sample. The results indicate that the new algorithm can be used to safely withhold antibiotics in low-risk patients, thus reducing antibiotic overuse.

Source:

Journal reference:

Danda, c. et al. (2023) Adaptation and external validation of pathogenic urine culture predictors in primary care using machine learning. Annals of Family Medicine. doi.org/10.1370/afm.2902.



Source link

Related Posts

Precaliga