[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126323-en":3,"doc-seo-126323-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":11,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},126323,2336475104957,"Seraphina","https://ap-avatar.wpscdn.com/avatar/22000c4c6bd8a5076e1?x-image-process=image/resize,m_fixed,w_180,h_180&k=1787554080175789136",8,"Research & Report","Machine learning and clinician predictions of antibiotic resistance in Enterobacterales bloodstream infections - Research","Gram-negative bloodstream infections carry high risk of adverse outcomes when effective antibiotics are not chosen promptly, yet identifying antimicrobial resistance (AMR) for empirical therapy remains difficult. Using XGBoost machine learning, the study predicts resistance to seven antibiotics in Enterobacterales bloodstream infection episodes trained on Oxfordshire hospital and community data (2017–2021) and evaluated against microbiology results (2022–2023) and clinician prescribing. Model inclusion of species identification improves discrimination, and predictions without species would shift patients toward more over- or under-treatment.","Journal of Infection 90 (2025) 106388  \nContents lists available at ScienceDirect Journal of Infection  \njournal [homepage:](homepage: www.elsevier.com/locate/j)[ www.elsevier.com/locate/j](homepage: www.elsevier.com/locate/j)inf  \n| Infectious Disease Practice |  |  |  |\n| --- | --- | --- | --- |\n| Machine learning and clinician predictions of antibiotic resistance in Enterobacterales bloodstream infections |  |  |  |\n| Kevin Yuan a, Augustine Luk b, Jia Wei b, A. Sarah Walker b,c,d, Tingting Zhu e, David W. Eyre a,c,d,f,⁎\u003Cbr>a Big Data Institute, Nuffield Department of Population Health, University of Oxford, Oxford, UK b Nuffield Department of Medicine, University of Oxford, Oxford, UK\u003Cbr>c NIHR Health Protection Research Unit in Healthcare Associated Infections and Antimicrobial Resistance, University of Oxford, Oxford, UK dNIHR Oxford Biomedical Research Centre, Oxford, UK\u003Cbr>e Institute of Biomedical Engineering, University of Oxford, Oxford, UK f Oxford University Hospitals NHS Foundation Trust, Oxford, UK |  |  |  |\n| a r t i c l e i n f o |  | s u m m a r y |  |\n| Article history:\u003Cbr>Accepted 20 December 2024 Available online 30 December 2024 |  | Background: Patients with Gram-negative bloodstream infections are at risk of serious adverse outcomes without active treatment, but identifying who has antimicrobial resistance (AMR) to target empirical treatment is challenging.\u003Cbr>Methods: We used XGBoost machine learning models to predict antimicrobial resistance to seven antibiotics in patients with Enterobacterales bloodstream infection. Models were trained using hospital and community data from Oxfordshire, UK, for patients with positive blood cultures between 01-January-2017 and 31-December-2021. Model performance was evaluated by comparing predictions to final microbiology results in test datasets from 01-January-2022 to 31-December-2023 and to clinicians’ prescribing. Findings: 4709 infection episodes were used for model training and evaluation; antibiotic resistance rates ranged from 7–67%. In held-out test data, resistance prediction performance was similar for the seven antibiotics (AUCs 0.680 [95%CI 0.641–0. 720] to 0.737 [0.674–0. 797]). Performance improved for most antibiotics when species identifications (available ∼24 h later) were included as model inputs (AUCs 0.723 [0.652–0. 791] to 0.827 [0.797–0.857]). In patients treated with a beta-lactam, clinician prescribing led to 70% receiving an active beta-lactam: 44% were over-treated (broader spectrum treatment than needed), 26% optimally-treated (narrowest spectrum active agent), and 30% under-treated (inactive beta-lactam). Model predictions without species data could have led to 79% of patients receiving an active beta-lactam: 45% over-treated, 34% optimally-treated, and 21% under-treated.\u003Cbr>Conclusions: Predicting AMR in bloodstream infections is challenging for both clinicians and models. Despite modest performance, machine learning models could still increase the proportion of patients receiving active empirical treatment by up to 9% over current clinical practice in an environment prioritising antimicrobial stewardship.\u003Cbr>© 2024 The Authors. Published by Elsevier Ltd on behalf of The British Infection Association. This is an open access article under the CC BY license ([http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0/)). |  |\n| Keywords:\u003Cbr>Antibiotics Bloodstream infection Antimicrobial resistance Machine learning Antibiotic stewardship |  |  |  |\n\nIntroduction  \nActive and timely antibiotic treatment of severe bacterial infections potentially saves lives and improves patient outcomes.1 However, it can take 24–48 h or more to obtain microbiology results to guide treatment, and many important infections remain culture  \n⁎ Correspondence to: Big Data Institute, University of Oxford, Old Road Campus, Oxford OX3 7LF, UK.  \nE-mail address: [david.eyre@bdi.ox.ac.uk](david.eyre@bdi.ox.ac.uk) (D.W. Eyre).  \nnegative.","cbCaidTA9SBQ9Msq","https://ap.wps.com/l/cbCaidTA9SBQ9Msq","pdf",2358623,1,12,"English","en",105,"# Introduction\n# Methods\n# Results\n# Discussion\n# Conclusions","[{\"question\":\"Why is predicting antimicrobial resistance for bloodstream infections challenging?\",\"answer\":\"Effective treatment depends on rapid identification of resistance, but microbiology results often take 24–48 hours or more, and many infections remain culture-negative. Patient-level refinement of guidelines is also inconsistently applied due to retrieval delays and variable prescriber experience.\"},{\"question\":\"How did the study predict antibiotic resistance?\",\"answer\":\"It used XGBoost machine learning models to predict resistance to seven antibiotics for patients with Enterobacterales bloodstream infection. Training used Oxfordshire hospital and community data for 2017–2021 and performance was evaluated on 2022–2023 test datasets compared with final microbiology results and clinicians’ prescribing.\"},{\"question\":\"What effect did including species identification have on model performance and prescribing?\",\"answer\":\"Including species identification (available about 24 hours later) improved performance for most antibiotics, raising AUC ranges up to 0.827. Model predictions without species data could have changed treatment choices, increasing the proportion of patients receiving an active beta-lactam less effectively and shifting over-, optimal-, and under-treatment rates.\"}]","Machine learning and clinician predictions of antibiotic resistance in Enterobacterales bloodstream infections - Research | PDF",1785904449,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-and-clinician-predictions-of-antibiotic-resistance-in-enterobacterales-bloodstream-infections-research","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-and-clinician-predictions-of-antibiotic-resistance-in-enterobacterales-bloodstream-infections-research/126323/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":11},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is predicting antimicrobial resistance for bloodstream infections challenging?","Question",{"text":76,"@type":77},"Effective treatment depends on rapid identification of resistance, but microbiology results often take 24–48 hours or more, and many infections remain culture-negative. Patient-level refinement of guidelines is also inconsistently applied due to retrieval delays and variable prescriber experience.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How did the study predict antibiotic resistance?",{"text":81,"@type":77},"It used XGBoost machine learning models to predict resistance to seven antibiotics for patients with Enterobacterales bloodstream infection. Training used Oxfordshire hospital and community data for 2017–2021 and performance was evaluated on 2022–2023 test datasets compared with final microbiology results and clinicians’ prescribing.",{"name":83,"@type":74,"acceptedAnswer":84},"What effect did including species identification have on model performance and prescribing?",{"text":85,"@type":77},"Including species identification (available about 24 hours later) improved performance for most antibiotics, raising AUC ranges up to 0.827. Model predictions without species data could have changed treatment choices, increasing the proportion of patients receiving an active beta-lactam less effectively and shifting over-, optimal-, and under-treatment rates.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":122},"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]