用人工智能预测尿路感染的抗生素敏感性--多中心队列中的模型表现。

IF 3.7 Q2 INFECTIOUS DISEASES JAC-Antimicrobial Resistance Pub Date : 2024-08-07 eCollection Date: 2024-08-01 DOI:10.1093/jacamr/dlae121
Alfred Lok Hang Lee, Curtis Chun Kit To, Ronald Cheong Kin Chan, Janus Siu Him Wong, Grace Chung Yan Lui, Ingrid Yu Ying Cheung, Viola Chi Ying Chow, Christopher Koon Chi Lai, Margaret Ip, Raymond Wai Man Lai
{"title":"用人工智能预测尿路感染的抗生素敏感性--多中心队列中的模型表现。","authors":"Alfred Lok Hang Lee, Curtis Chun Kit To, Ronald Cheong Kin Chan, Janus Siu Him Wong, Grace Chung Yan Lui, Ingrid Yu Ying Cheung, Viola Chi Ying Chow, Christopher Koon Chi Lai, Margaret Ip, Raymond Wai Man Lai","doi":"10.1093/jacamr/dlae121","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>To develop an artificial intelligence model to predict an antimicrobial susceptibility pattern in patients with urinary tract infection (UTI).</p><p><strong>Materials and methods: </strong>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).</p><p><strong>Results: </strong>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.</p><p><strong>Conclusions: </strong>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.</p>","PeriodicalId":14594,"journal":{"name":"JAC-Antimicrobial Resistance","volume":null,"pages":null},"PeriodicalIF":3.7000,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11304604/pdf/","citationCount":"0","resultStr":"{\"title\":\"Predicting antibiotic susceptibility in urinary tract infection with artificial intelligence-model performance in a multi-centre cohort.\",\"authors\":\"Alfred Lok Hang Lee, Curtis Chun Kit To, Ronald Cheong Kin Chan, Janus Siu Him Wong, Grace Chung Yan Lui, Ingrid Yu Ying Cheung, Viola Chi Ying Chow, Christopher Koon Chi Lai, Margaret Ip, Raymond Wai Man Lai\",\"doi\":\"10.1093/jacamr/dlae121\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>To develop an artificial intelligence model to predict an antimicrobial susceptibility pattern in patients with urinary tract infection (UTI).</p><p><strong>Materials and methods: </strong>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).</p><p><strong>Results: </strong>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.</p><p><strong>Conclusions: </strong>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.</p>\",\"PeriodicalId\":14594,\"journal\":{\"name\":\"JAC-Antimicrobial Resistance\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.7000,\"publicationDate\":\"2024-08-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11304604/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JAC-Antimicrobial Resistance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/jacamr/dlae121\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/8/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"INFECTIOUS DISEASES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JAC-Antimicrobial Resistance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/jacamr/dlae121","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/8/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"INFECTIOUS DISEASES","Score":null,"Total":0}
引用次数: 0

摘要

摘要开发一种人工智能模型,用于预测尿路感染(UTI)患者的抗菌药敏感性模式。材料与方法:纳入 2015-2020 年间香港一所大学教学医院和三所社区医院的 26 087 例经培养证实的UTI成人患者。排除了无症状菌尿(无UTI诊断代码或尿液镜检无白细胞)的病例。训练集包括 2015 年至 2019 年的患者,测试集包括 2020 年的患者。为预测UTI细菌分离株的药敏性,选择了三种一线抗生素:硝基呋喃妥因、环丙沙星和阿莫西林-克拉维酸。基线流行病学因素、既往抗菌药物使用情况、病史和既往培养结果均被列为特征。数据集采用了逻辑回归和随机森林方法。通过 F1 分数和曲线下面积-接收器操作特征(AUC-ROC)对模型进行评估:随机森林是预测三种抗生素(硝基呋喃妥因、阿莫西林-克拉维酸和环丙沙星)药敏性的最佳算法。AUC-ROC 值分别为 0.941、0.939 和 0.937。F1 分数分别为 0.938、0.928 和 0.906:随机森林模型可帮助UTI患者合理使用抗生素。鉴于其合理的性能和准确性,这些精确的模型可帮助临床医生在UTI治疗中选择不同的一线抗生素。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Predicting antibiotic susceptibility in urinary tract infection with artificial intelligence-model performance in a multi-centre cohort.

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.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.30
自引率
0.00%
发文量
0
审稿时长
16 weeks
期刊最新文献
Outcomes of Enterococcus faecalis infective endocarditis according to MIC of amoxicillin: a multicentric study. Experience with expanded use of oritavancin in a tertiary hospital: indications, tolerability and outcomes. Antimicrobial use in hospitalized patients: a point prevalence survey across four tertiary hospitals in Niger. Aetiology, susceptibility and outcomes of fever in patients receiving chemotherapy in Malawi: a prospective study. Community pharmacists' knowledge and practices towards antimicrobial stewardship: findings and implications.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1