{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T06:27:34Z","timestamp":1783232854522,"version":"3.54.6"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T00:00:00Z","timestamp":1770940800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell. Infect. Microbiol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      <jats:italic>Escherichia coli<\/jats:italic>\n                      is the predominant uropathogen in urinary tract infections (UTIs), but culture-based identification is time-consuming. This study aimed to develop an explainable, culture-independent model to distinguish\n                      <jats:italic>E. coli<\/jats:italic>\n                      from other uropathogens using routinely collected clinical data.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We retrospectively analyzed 308 hospitalized patients with culture-confirmed UTIs at Fuding Hospital, Fujian University of Traditional Chinese Medicine (January\u2013December 2023), classified as\n                      <jats:italic>E. coli<\/jats:italic>\n                      (n = 158) or non\u2013\n                      <jats:italic>E. col<\/jats:italic>\n                      i (n = 150). Species identification was performed using an automated microbiology system. Nineteen predictors (sex, urinary leukocyte grade, and 17 routine laboratory variables) were used. Associations with\n                      <jats:italic>E. coli<\/jats:italic>\n                      UTI were examined using univariate and multivariable logistic regression. A Random Forest (RF) classifier was developed with SHapley Additive exPlanations (SHAP) for interpretability. Data were split using a stratified 70\/30 train\u2013test split; 5-fold stratified cross-validation within the training set was used for hyperparameter tuning, and final performance (discrimination and calibration) was reported on the held-out test set. RF was additionally benchmarked against regularized logistic regression, calibrated linear SVM, and gradient boosting using the same protocol.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      <jats:italic>E. coli<\/jats:italic>\n                      accounted for 51.3% of isolates, followed by\n                      <jats:italic>Enterococcus<\/jats:italic>\n                      spp. (18.5%) and\n                      <jats:italic>Klebsiella<\/jats:italic>\n                      spp. (7.8%). Compared with non\u2013\n                      <jats:italic>E. coli<\/jats:italic>\n                      cases,\n                      <jats:italic>E. coli<\/jats:italic>\n                      infections were more common in females and showed higher lymphocyte counts (LYM), alanine aminotransferase (ALT), and albumin (ALB) (all P &amp;lt; 0.05). Multivariable logistic regression identified sex, LYM, and urinary leukocyte grade as independent predictors. On the held-out test set, RF achieved moderate discrimination (ROC-AUC = 0.66; average precision = 0.66) with calibration assessed by Brier score and calibration slope. SHAP highlighted Sex, LYM, and ALT as the most influential predictors and revealed patient-level heterogeneity in feature effects.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>\n                      <jats:italic>E. coli<\/jats:italic>\n                      remains the predominant pathogen among hospitalized UTIs. An explainable RF model using routine laboratory variables provided moderate, reproducible discrimination of\n                      <jats:italic>E. coli<\/jats:italic>\n                      vs non\u2013\n                      <jats:italic>E. coli<\/jats:italic>\n                      UTIs and may support earlier decision-making while awaiting culture results.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcimb.2026.1740707","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T07:11:17Z","timestamp":1770966677000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Explainable machine learning for early detection of Escherichia coli urinary tract infections: integrating SHAP interpretation and bacterial epidemiology"],"prefix":"10.3389","volume":"16","author":[{"given":"Jie","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Clinical Laboratory, Fuding Hospital, Fujian University of Traditional Chinese Medicine","place":["Fuding, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying-Ying","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Fuding Hospital, Fujian University of Traditional Chinese Medicine","place":["Fuding, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Fuding Hospital, Fujian University of Traditional Chinese Medicine","place":["Fuding, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chu-Ying","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Fuding Hospital, Fujian University of Traditional Chinese Medicine","place":["Fuding, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling-Hui","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Fuding Hospital, Fujian University of Traditional Chinese Medicine","place":["Fuding, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying-Ying","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Fuding Hospital, Fujian University of Traditional Chinese Medicine","place":["Fuding, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi-Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory, Fuding Hospital, Fujian University of Traditional Chinese Medicine","place":["Fuding, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinbao","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Nephrology, Fuding Hospital, Fujian University of Traditional Chinese Medicine","place":["Fuding, Fujian, China"]},{"name":"Department of Nephrology, Ningde Hospital of Traditional Chinese Medicine","place":["Ningde, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,13]]},"reference":[{"key":"B10","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s41512-024-00177-1","article-title":"Understanding overfitting in random forest for probability estimation: a visualization and simulation study","volume":"8","author":"Barre\u00f1ada","year":"2024","journal-title":"Diagn. Progn Res."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0284315","article-title":"Interpretable machine learning with tree-based shapley additive explanations: Application to metabolomics datasets for binary classification","volume":"18","author":"Bifarin","year":"2023","journal-title":"PloS One"},{"key":"B5","doi-asserted-by":"publisher","first-page":"633","DOI":"10.5811\/westjem.2020.1.45944","article-title":"Appropriateness of antibiotic prescriptions for urinary tract infections","volume":"21","author":"Chardavoyne","year":"2020","journal-title":"West J. Emerg. Med."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3390\/antibiotics13100925","article-title":"Trends in antimicrobial resistance of uropathogens isolated from urinary tract infections in a tertiary care hospital in dhaka, Bangladesh","volume":"13","author":"Chowdhury","year":"2024","journal-title":"Antibiot (Basel)"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1002\/hsr2.2039","article-title":"Prevalence, antibiotic resistance pattern for bacteriuria from patients with urinary tract infections","volume":"7","author":"Hossain","year":"2024","journal-title":"Health Sci. Rep."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fcimb.2025.1540149","article-title":"The immune mechanisms of the urinary tract against infections","volume":"15","author":"Hou","year":"2025","journal-title":"Front. Cell Infect. Microbiol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1002\/psp4.12828","article-title":"Application of SHAP values for inferring the optimal functional form of covariates in pharmacokinetic modeling","volume":"11","author":"Janssen","year":"2022","journal-title":"CPT Pharmacom Syst. Pharmacol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"17216","DOI":"10.1038\/s41598-022-18920-3","article-title":"Machine learning to predict the development of recurrent urinary tract infection related to single uropathogen, Escherichia coli","volume":"12","author":"Jeng","year":"2022","journal-title":"Sci. Rep."},{"key":"B16","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1186\/s12879-025-10634-x","article-title":"Prevalence of recurrent urinary tract infections and its associated factors in female staff of reproductive age group in a medical college in central Kerala: a cross-sectional study","volume":"25","author":"Johny","year":"2025","journal-title":"BMC Infect. Dis."},{"key":"B22","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1007\/s00467-017-3843-9","article-title":"D-dimer as a marker of acute pyelonephritis in infants younger than 24 months with urinary tract infection","volume":"33","author":"Lee","year":"2018","journal-title":"Pediatr. Nephrol."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3346\/jkms.2021.36.e310","article-title":"A multicenter study of real-world practice for management of abnormal liver function tests in children with acute infectious diseases","volume":"36","author":"Lee","year":"2021","journal-title":"J. Korean Med. Sci."},{"key":"B11","doi-asserted-by":"publisher","first-page":"12973","DOI":"10.1038\/s41598-024-63944-6","article-title":"Random forest differentiation of Escherichia coli in elderly sepsis using biomarkers and infectious sites","volume":"14","author":"Li","year":"2024","journal-title":"Sci. Rep."},{"key":"B13","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3390\/pathogens12040623","article-title":"Urinary tract infections: the current scenario and future prospects","volume":"12","author":"Mancuso","year":"2023","journal-title":"Pathogens"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3390\/antibiotics11030308","article-title":"Applying diagnostic stewardship to proactively optimize the management of urinary tract infections","volume":"11","author":"Morado","year":"2022","journal-title":"Antibiot (Basel)"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.44495","article-title":"Guidelines for the prevention, diagnosis, and management of urinary tract infections in pediatrics and adults: A wikiGuidelines group consensus statement","volume":"7","author":"Nelson","year":"2024","journal-title":"JAMA Netw. Open"},{"key":"B23","doi-asserted-by":"publisher","first-page":"8761","DOI":"10.1021\/acs.jmedchem.9b01101","article-title":"Interpretation of compound activity predictions from complex machine learning models using local approximations and shapley values","volume":"63","author":"Rodr\u00edguez-P\u00e9rez","year":"2020","journal-title":"J. Med. Chem."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1961","DOI":"10.2147\/IDR.S251966","article-title":"Blood neutrophil-to-lymphocyte ratio and urine IL-8 levels predict the type of bacterial urinary tract infection in type 2 diabetes mellitus patients","volume":"13","author":"Saheb Sharif-Askari","year":"2020","journal-title":"Infect. Drug Resist."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3390\/jpm15050200","article-title":"From preliminary urinalysis to decision support: machine learning for UTI prediction in real-world laboratory data","volume":"15","author":"Sergounioti","year":"2025","journal-title":"J. Pers. Med."},{"key":"B8","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1007\/s00345-024-05145-4","article-title":"Artificial intelligence and machine learning applications in urinary tract infections identification and prediction: a systematic review and meta-analysis","volume":"42","author":"Shen","year":"2024","journal-title":"World J. Urol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2024.1366012","article-title":"Glucose-albumin ratio (GAR) as a novel biomarker of postoperative urinary tract infection in elderly hip fracture patients","volume":"11","author":"Wang","year":"2024","journal-title":"Front. Med. (Laus)"},{"key":"B21","doi-asserted-by":"publisher","first-page":"3916","DOI":"10.21037\/apm-20-2305","article-title":"Red blood cell distribution width may be a new factor that influence the selection of invasive treatment in patients with renal abscess","volume":"10","author":"Xia","year":"2021","journal-title":"Ann. Palliat Med."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2022.888205","article-title":"Disease burden and long-term trends of urinary tract infections: A worldwide report","volume":"10","author":"Yang","year":"2022","journal-title":"Front. Public Health"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3390\/microorganisms10071425","article-title":"Urinary tract infections caused by uropathogenic escherichia coli strains-new strategies for an old pathogen","volume":"10","author":"Zagaglia","year":"2022","journal-title":"Microorganisms"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3892\/etm.2024.12428","article-title":"Epidemiological insights into seasonal, sex\u2212specific and age\u2212related distribution of bacterial pathogens in urinary tract infections","volume":"27","author":"Zhan","year":"2024","journal-title":"Exp. Ther. Med."}],"container-title":["Frontiers in Cellular and Infection Microbiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2026.1740707\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T10:30:36Z","timestamp":1771929036000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2026.1740707\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,13]]},"references-count":25,"alternative-id":["10.3389\/fcimb.2026.1740707"],"URL":"https:\/\/doi.org\/10.3389\/fcimb.2026.1740707","relation":{},"ISSN":["2235-2988"],"issn-type":[{"value":"2235-2988","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,13]]},"article-number":"1740707"}}