File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Predicting antibiotic susceptibility in urinary tract infection with artificial intelligence—model performance in a multi-centre cohort

TitlePredicting antibiotic susceptibility in urinary tract infection with artificial intelligence—model performance in a multi-centre cohort
Authors
Issue Date7-Aug-2024
PublisherOxford University Press
Citation
JAC-Antimicrobial Resistance, 2024, v. 6, n. 4 How to Cite?
Abstract

Objective: To develop an artificial intelligence model to predict an antimicrobial susceptibility pattern in patients with urinary tract infection (UTI). Materials and methods: 26 087 adult patients with culture-proven UTI during 2015–2020 from a university teaching hospital and three community hospitals in Hong Kong were included. Cases with asymptomatic bacteriuria (absence of diagnosis code of UTI, or absence of leucocytes in urine microscopy) were excluded. Patients from 2015 to 2019 were included in the training set, while patients from the year 2020 were included as the test set. Three first-line antibiotics were chosen for prediction of susceptibility in the bacterial isolates causing UTI: namely nitrofurantoin, ciprofloxacin and amoxicillin-clavulanate. Baseline epidemiological factors, previous antimicrobial consumption, medical history and previous culture results were included as features. Logistic regression and random forest were applied to the dataset. Models were evaluated by F1-score and area under the curve-receiver operating characteristic (AUC-ROC). Results: Random forest was the best algorithm in predicting susceptibility of the three antibiotics (nitrofurantoin, amoxicillin-clavulanate and ciprofloxacin). The AUC-ROC values were 0.941, 0.939 and 0.937, respectively. The F1 scores were 0.938, 0.928 and 0.906 respectively. Conclusions: Random forest model may aid judicious empirical antibiotics use in UTI. Given the reasonable performance and accuracy, these accurate models may aid clinicians in choosing between different first-line antibiotics for UTI. 


Persistent Identifierhttp://hdl.handle.net/10722/353881

 

DC FieldValueLanguage
dc.contributor.authorLee, Alfred Lok Hang-
dc.contributor.authorTo, Curtis Chun Kit-
dc.contributor.authorChan, Ronald Cheong Kin-
dc.contributor.authorWong, Janus Siu Him-
dc.contributor.authorLui, Grace Chung Yan-
dc.contributor.authorCheung, Ingrid Yu Ying-
dc.contributor.authorChow, Viola Chi Ying-
dc.contributor.authorLai, Christopher Koon Chi-
dc.contributor.authorIp, Margaret-
dc.contributor.authorLai, Raymond Wai Man-
dc.date.accessioned2025-01-28T00:35:36Z-
dc.date.available2025-01-28T00:35:36Z-
dc.date.issued2024-08-07-
dc.identifier.citationJAC-Antimicrobial Resistance, 2024, v. 6, n. 4-
dc.identifier.urihttp://hdl.handle.net/10722/353881-
dc.description.abstract<p>Objective: To develop an artificial intelligence model to predict an antimicrobial susceptibility pattern in patients with urinary tract infection (UTI). Materials and methods: 26 087 adult patients with culture-proven UTI during 2015–2020 from a university teaching hospital and three community hospitals in Hong Kong were included. Cases with asymptomatic bacteriuria (absence of diagnosis code of UTI, or absence of leucocytes in urine microscopy) were excluded. Patients from 2015 to 2019 were included in the training set, while patients from the year 2020 were included as the test set. Three first-line antibiotics were chosen for prediction of susceptibility in the bacterial isolates causing UTI: namely nitrofurantoin, ciprofloxacin and amoxicillin-clavulanate. Baseline epidemiological factors, previous antimicrobial consumption, medical history and previous culture results were included as features. Logistic regression and random forest were applied to the dataset. Models were evaluated by F1-score and area under the curve-receiver operating characteristic (AUC-ROC). Results: Random forest was the best algorithm in predicting susceptibility of the three antibiotics (nitrofurantoin, amoxicillin-clavulanate and ciprofloxacin). The AUC-ROC values were 0.941, 0.939 and 0.937, respectively. The F1 scores were 0.938, 0.928 and 0.906 respectively. Conclusions: Random forest model may aid judicious empirical antibiotics use in UTI. Given the reasonable performance and accuracy, these accurate models may aid clinicians in choosing between different first-line antibiotics for UTI. <br></p>-
dc.languageeng-
dc.publisherOxford University Press-
dc.relation.ispartofJAC-Antimicrobial Resistance-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titlePredicting antibiotic susceptibility in urinary tract infection with artificial intelligence—model performance in a multi-centre cohort-
dc.typeArticle-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1093/jacamr/dlae121-
dc.identifier.scopuseid_2-s2.0-85201011939-
dc.identifier.volume6-
dc.identifier.issue4-
dc.identifier.eissn2632-1823-
dc.identifier.issnl2632-1823-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats