Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

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

Gadalla, Amal A. M. ORCID: https://orcid.org/0000-0002-3131-725X, Friberg, Ida M., Kift-Morgan, Ann, Zhang, Jingjing ORCID: https://orcid.org/0000-0002-8970-7568, Eberl, Matthias ORCID: https://orcid.org/0000-0002-9390-5348, Topley, Nicholas, Weeks, Ian ORCID: https://orcid.org/0000-0002-6362-2929, Cuff, Simone ORCID: https://orcid.org/0000-0002-0546-3579, Wootton, Mandy, Gal, Micaela ORCID: https://orcid.org/0000-0002-1326-190X, Parekh, Gita, Davis, Paul, Gregory, Clive ORCID: https://orcid.org/0000-0003-4876-3982, Hood, Kerenza ORCID: https://orcid.org/0000-0002-5268-8631, Hughes, Kathryn ORCID: https://orcid.org/0000-0002-8099-066X, Butler, Christopher ORCID: https://orcid.org/0000-0002-0102-3453 and Francis, Nick ORCID: https://orcid.org/0000-0001-8939-7312 2019. Identification of clinical and urine biomarkers for uncomplicated urinary tract infection using machine learning algorithms. Scientific Reports 9 (1) , 19694. 10.1038/s41598-019-55523-x

[thumbnail of 41598_2019_Article_55523.pdf]
Preview
PDF - Published Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview

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.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Medicine
Centre for Trials Research (CNTRR)
Advanced Research Computing @ Cardiff (ARCCA)
Publisher: Nature Publishing Group
ISSN: 2045-2322
Funders: MRC
Date of First Compliant Deposit: 5 December 2019
Date of Acceptance: 19 November 2019
Last Modified: 13 Jan 2024 02:05
URI: https://orca.cardiff.ac.uk/id/eprint/127337

Citation Data

Cited 20 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics