دورية أكاديمية
Predicting antibiotic susceptibility in urinary tract infection with artificial intelligence-model performance in a multi-centre cohort.
العنوان: | Predicting antibiotic susceptibility in urinary tract infection with artificial intelligence-model performance in a multi-centre cohort. |
---|---|
المؤلفون: | Lee ALH; Department of Microbiology, Prince of Wales Hospital, Shatin, Hong Kong SAR, China., To CCK; Department of Anatomical and Cellular Pathology, Faculty of Medicine, Chinese University of Hong Kong, Shatin, Hong Kong SAR, China., Chan RCK; Department of Anatomical and Cellular Pathology, Faculty of Medicine, Chinese University of Hong Kong, Shatin, Hong Kong SAR, China., Wong JSH; Department of Orthopaedics and Traumatology, School of Clinical Medicine, LKS Faculty of Medicine, University of Hong Kong, Pokfulam, Hong Kong SAR, China., Lui GCY; Department of Medicine and Therapeutics, Prince of Wales Hospital, Shatin, Hong Kong SAR, China., Cheung IYY; Department of Microbiology, Prince of Wales Hospital, Shatin, Hong Kong SAR, China., Chow VCY; Department of Microbiology, Prince of Wales Hospital, Shatin, Hong Kong SAR, China., Lai CKC; Department of Microbiology, Faculty of Medicine, Chinese University of Hong Kong, Shatin, Hong Kong SAR, China., Ip M; Department of Microbiology, Faculty of Medicine, Chinese University of Hong Kong, Shatin, Hong Kong SAR, China., Lai RWM; Chief Infection Control Officer Office, Hospital Authority, Kowloon, Hong Kong SAR, China. |
المصدر: | JAC-antimicrobial resistance [JAC Antimicrob Resist] 2024 Aug 07; Vol. 6 (4), pp. dlae121. Date of Electronic Publication: 2024 Aug 07 (Print Publication: 2024). |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: Oxford University Press Country of Publication: England NLM ID: 101765283 Publication Model: eCollection Cited Medium: Internet ISSN: 2632-1823 (Electronic) Linking ISSN: 26321823 NLM ISO Abbreviation: JAC Antimicrob Resist Subsets: PubMed not MEDLINE |
أسماء مطبوعة: | Original Publication: [Oxford] : Oxford University Press, [2019]- |
مستخلص: | 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. (© The Author(s) 2024. Published by Oxford University Press on behalf of British Society for Antimicrobial Chemotherapy.) |
References: | Infect Control Hosp Epidemiol. 2017 Feb;38(2):186-188. (PMID: 27852357) Eur J Clin Microbiol Infect Dis. 2021 May;40(5):1049-1061. (PMID: 33399979) J Med Microbiol. 2020 Jan;69(1):52-62. (PMID: 31846419) Am J Emerg Med. 2017 Apr;35(4):594-598. (PMID: 28010959) Sci Rep. 2023 Feb 25;13(1):3282. (PMID: 36841917) Clin Microbiol Infect. 2020 Oct;26(10):1291-1299. (PMID: 32061798) Antimicrob Resist Infect Control. 2015 Dec 01;4:54. (PMID: 26634119) Front Microbiol. 2019 Jun 05;10:1182. (PMID: 31231323) Sci Transl Med. 2020 Nov 4;12(568):. (PMID: 33148625) J Clin Microbiol. 2021 Jun 18;59(7):e0126020. (PMID: 33536291) Open Forum Infect Dis. 2019 Mar 14;6(4):ofz164. (PMID: 31041359) Am J Emerg Med. 2015 Sep;33(9):1129-33. (PMID: 26027885) J Hosp Infect. 2021 Feb;108:81-89. (PMID: 33181278) Sci Rep. 2022 Nov 15;12(1):18315. (PMID: 36380053) Nat Rev Urol. 2010 Dec;7(12):653-60. (PMID: 21139641) Commun Med (Lond). 2022 Apr 8;2:38. (PMID: 35603264) Nat Med. 2019 Jul;25(7):1143-1152. (PMID: 31273328) |
تواريخ الأحداث: | Date Created: 20240808 Latest Revision: 20240809 |
رمز التحديث: | 20240809 |
مُعرف محوري في PubMed: | PMC11304604 |
DOI: | 10.1093/jacamr/dlae121 |
PMID: | 39114564 |
قاعدة البيانات: | MEDLINE |
تدمد: | 2632-1823 |
---|---|
DOI: | 10.1093/jacamr/dlae121 |