Machine Learning for Antimicrobial Resistance Prediction: Current Practice, Limitations, and Clinical Perspective.

IF 19 1区 医学 Q1 MICROBIOLOGY
Clinical Microbiology Reviews Pub Date : 2022-09-21 Epub Date: 2022-05-25 DOI:10.1128/cmr.00179-21
Jee In Kim, Finlay Maguire, Kara K Tsang, Theodore Gouliouris, Sharon J Peacock, Tim A McAllister, Andrew G McArthur, Robert G Beiko
{"title":"Machine Learning for Antimicrobial Resistance Prediction: Current Practice, Limitations, and Clinical Perspective.","authors":"Jee In Kim, Finlay Maguire, Kara K Tsang, Theodore Gouliouris, Sharon J Peacock, Tim A McAllister, Andrew G McArthur, Robert G Beiko","doi":"10.1128/cmr.00179-21","DOIUrl":null,"url":null,"abstract":"<p><p>Antimicrobial resistance (AMR) is a global health crisis that poses a great threat to modern medicine. Effective prevention strategies are urgently required to slow the emergence and further dissemination of AMR. Given the availability of data sets encompassing hundreds or thousands of pathogen genomes, machine learning (ML) is increasingly being used to predict resistance to different antibiotics in pathogens based on gene content and genome composition. A key objective of this work is to advocate for the incorporation of ML into front-line settings but also highlight the further refinements that are necessary to safely and confidently incorporate these methods. The question of what to predict is not trivial given the existence of different quantitative and qualitative laboratory measures of AMR. ML models typically treat genes as independent predictors, with no consideration of structural and functional linkages; they also may not be accurate when new mutational variants of known AMR genes emerge. Finally, to have the technology trusted by end users in public health settings, ML models need to be transparent and explainable to ensure that the basis for prediction is clear. We strongly advocate that the next set of AMR-ML studies should focus on the refinement of these limitations to be able to bridge the gap to diagnostic implementation.</p>","PeriodicalId":10378,"journal":{"name":"Clinical Microbiology Reviews","volume":null,"pages":null},"PeriodicalIF":19.0000,"publicationDate":"2022-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9491192/pdf/cmr.00179-21.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Microbiology Reviews","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1128/cmr.00179-21","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2022/5/25 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"MICROBIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Antimicrobial resistance (AMR) is a global health crisis that poses a great threat to modern medicine. Effective prevention strategies are urgently required to slow the emergence and further dissemination of AMR. Given the availability of data sets encompassing hundreds or thousands of pathogen genomes, machine learning (ML) is increasingly being used to predict resistance to different antibiotics in pathogens based on gene content and genome composition. A key objective of this work is to advocate for the incorporation of ML into front-line settings but also highlight the further refinements that are necessary to safely and confidently incorporate these methods. The question of what to predict is not trivial given the existence of different quantitative and qualitative laboratory measures of AMR. ML models typically treat genes as independent predictors, with no consideration of structural and functional linkages; they also may not be accurate when new mutational variants of known AMR genes emerge. Finally, to have the technology trusted by end users in public health settings, ML models need to be transparent and explainable to ensure that the basis for prediction is clear. We strongly advocate that the next set of AMR-ML studies should focus on the refinement of these limitations to be able to bridge the gap to diagnostic implementation.

抗菌药耐药性预测的机器学习:当前实践、局限性和临床视角。
抗菌素耐药性(AMR)是对现代医学构成巨大威胁的全球健康危机。迫切需要有效的预防策略来减缓 AMR 的出现和进一步传播。由于可以获得包含成百上千病原体基因组的数据集,机器学习(ML)正越来越多地用于根据基因含量和基因组组成预测病原体对不同抗生素的耐药性。这项工作的一个主要目的是倡导将 ML 应用于一线环境,但同时也强调了进一步的改进,这对于安全、自信地应用这些方法是必不可少的。由于实验室对 AMR 有不同的定量和定性测量方法,因此预测什么的问题并不简单。ML 模型通常将基因视为独立的预测因子,而不考虑结构和功能上的联系;当已知 AMR 基因出现新的突变变体时,这些模型也可能不准确。最后,为了使这项技术得到公共卫生领域最终用户的信任,ML 模型必须是透明的、可解释的,以确保预测的依据是明确的。我们强烈主张,下一组 AMR-ML 研究应侧重于改进这些局限性,以弥补诊断实施方面的差距。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Clinical Microbiology Reviews
Clinical Microbiology Reviews 医学-微生物学
CiteScore
54.20
自引率
0.50%
发文量
38
期刊介绍: Clinical Microbiology Reviews (CMR) is a journal that primarily focuses on clinical microbiology and immunology.It aims to provide readers with up-to-date information on the latest developments in these fields.CMR also presents the current state of knowledge in clinical microbiology and immunology.Additionally, the journal offers balanced and thought-provoking perspectives on controversial issues in these areas.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信