Identification of clinical and urine biomarkers for uncomplicated urinary tract infection using machine learning algorithms

Abstract

Women with uncomplicated urinary tract infection (UTI) symptoms are commonly treated with empirical antibiotics, resulting in overuse of antibiotics, which promotes antimicrobial resistance. Available diagnostic tools are either not cost-effective or diagnostically sub-optimal. Here, we identified clinical and urinary immunological predictors for UTI diagnosis. We explored 17 clinical and 42 immunological potential predictors for bacterial culture among women with uncomplicated UTI symptoms using random forest or support vector machine coupled with recursive feature elimination. Urine cloudiness was the best performing clinical predictor to rule out (negative likelihood ratio [LR−] = 0.4) and rule in (LR+ = 2.6) UTI. Using a more discriminatory scale to assess cloudiness (turbidity) increased the accuracy of UTI prediction further (LR+ = 4.4). Urinary levels of MMP9, NGAL, CXCL8 and IL-1β together had a higher LR+ (6.1) and similar LR− (0.4), compared to cloudiness. Varying the bacterial count thresholds for urine culture positivity did not alter best clinical predictor selection, but did affect the number of immunological predictors required for reaching an optimal prediction. We conclude that urine cloudiness is particularly helpful in ruling out negative UTI cases. The identified urinary biomarkers could be used to develop a point of care test for UTI but require further validation.

Point-of-care diagnostics for infectious diseases: From methods to devices

“…The current commercialized fifth generation of mobile network will provide a massively increased data rate and accelerate the application of IoT for POC detection. Besides, due to the mushrooming of machine learning in recent years, it has also been harnessed with POC devices to improve the medicine practice by integrating clinical detection and disease diagnostics based on big data and intensive evidences [511] , [517] , [518] . Finally, the deep learning methods in AI would advance the fabrication of POC devices towards AI-based devices, which will revolutionize medical diagnostics and endow them the ability to achieve automated and intelligent medical practice with precise diagnostics in complex biological environments at POC and provide personalized therapeutics in time.…”

Asymptomatic Bacteriuria or Urinary Tract Infection? New and Old Biomarkers

“…UTIs induce a significant increase in serum IL-6, and its level could differentiate lower and upper UTIs. Unfortunately, only two small studies evaluated this aspect and in two different clinical settings [15,21] Urine IL-6 was explored by eleven small studies [11,12,15,[19][20][21][22][23][26][27][28], usually performed in the elderly. Not all studies suggested a significant increase in urine IL-6 during UTIs, and the studies were too heterogenous to obtain a univocal recommendation.…”

A Two-Dimensional Affinity Capture and Separation Mini-Platform for the Isolation, Enrichment, and Quantification of Biomarkers and Its Potential Use for Liquid Biopsy

“…In most cases, urinary tract infections are commonly treated with empirical antibiotics, resulting in overuse of antibiotics, which promotes antimicrobial resistance. Interestingly, when urine from patients suffering from urinary tract infection is cultured, approximately only one in three patients are found to have urinary tract infection as defined by positive bacterial culture [ 181 ]. Results from bacterial culture may take from one to three or more days, depending on the type of bacteria [ 182 ].…”