[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128381-en":3,"doc-seo-128381-105":31,"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128381,962085564807,"Aurelia","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Integrating Nonindividual Patient Features in Machine Learning Models of Hospital-Onset Bacteremia","Hospital-onset bacteremia and fungemia are common, potentially preventable hospital complications, and this prognostic study evaluates whether features reflecting interactions beyond the individual patient can improve machine learning models. Adult patients admitted to Barnes-Jewish Hospital in 2021 were analyzed, extracting individual features from electronic health records and engineering nonindividual features involving interactions with healthcare workers and room-contact patterns. Three gradient boosting models were compared using AUROC and AUPRC, while causal effects were assessed with difference in average effects and sensitivity analyses.","Washington University School of Medicine  \nDigital Commons@Becker  \n\n| 2020-Current year OA Pubs | Open Access Publications |\n| --- | --- |\n| 7-1-2025\u003Cbr>Integrating nonindividual patient features in machine learning models of hospital-onset bacteremia\u003Cbr>M Cristina Vazquez-Guillamet\u003Cbr>Washington University School of Medicine in St. Louis Jingwen Zhang\u003Cbr>Washington University in St. Louis Alice Bewley\u003Cbr>Washington University School of Medicine in St. Louis Andrew Atkinson\u003Cbr>Washington University School of Medicine in St. Louis Heidi Holtz\u003Cbr>Goldfarb School of Nursing at Barnes-Jewish College\u003Cbr>See next page for additional authors\u003Cbr>Follow this and additional works at: [https://digitalcommons.wustl.edu/oa_4](https://digitalcommons.wustl.edu/oa_4)\u003Cbr> Part of the Medicine and Health Sciences Commons\u003Cbr>Please let us know how this document benefits you. |  |\n\nRecommended Citation  \nVazquez-Guillamet, M Cristina; Zhang, Jingwen; Bewley, Alice; Atkinson, Andrew; Holtz, Heidi; Wang, Ziqian; Brougham, Nicole; Lu, Chenyang; Kollef, Marin H; Payne, Philip; Warren, David; and Fraser, Victoria J, \"Integrating nonindividual patient features in machine learning models of hospital-onset bacteremia.\"JAMA Network Open. 8, 7. e2518815 (2025) .  \n[https://digitalcommons.wustl.edu/oa_4/5163](https://digitalcommons.wustl.edu/oa_4/5163)  \nThis Open Access Publication is brought to you for free and open access by the Open Access Publications at Digital Commons@Becker. It has been accepted for inclusion in 2020-Current year OA Pubs by an authorized administrator of Digital Commons@Becker. For more information, [please contact](please contact vanam@wustl.edu)[ vanam@wustl.edu](please contact vanam@wustl.edu).  \nAuthors  \nM Cristina Vazquez-Guillamet, Jingwen Zhang, Alice Bewley, Andrew Atkinson, Heidi Holtz, Ziqian Wang, Nicole Brougham, Chenyang Lu, Marin H Kollef, Philip Payne, David Warren, and Victoria J Fraser  \nThis open access publication is available at Digital Commons@Becker: [https://digitalcommons.wustl.edu/oa_4/5163](https://digitalcommons.wustl.edu/oa_4/5163)  \nOriginal Investigation | Infectious Diseases  \nIntegrating Nonindividual Patient Features in Machine Learning Models of Hospital-Onset Bacteremia  \nM. CristinaVazquez-Guillamet, MD; Jingwen Zhang, PhD; Alice Bewley, MS; Andrew Atkinson, PhD; Heidi Holtz, PhD, RN; Ziqian Wang, BS; Nicole Brougham, MSN, RN; Chenyang Lu, PhD; Marin H. Kollef, MD; Philip Payne, PhD; David Warren, MD, MPH; Victoria J. Fraser, MD  \n\n| Abstract\u003Cbr>IMPORTANCE Hospital-onset bacteremia and fungemia (HOB) are common and potentially preventable complications of hospital care.\u003Cbr>\u003Cbr>OBJECTIVE To assess whether nonindividual patient features, which summarize interactions with other patients and health care workers (HCWs), can contribute to predictive and causal machine learning models for HOB.\u003Cbr>\u003Cbr>DESIGN, SETTING, AND PARTICIPANTS This prognostic study included adult patients admitted to Barnes-Jewish Hospital, an academic hospital in St Louis, Missouri, in 2021. Analyses were developed between October 2023 and August 2024 and in April 2025 .\u003Cbr>\u003Cbr>EXPOSURE Individual patient features were extracted from electronic health records and used to engineer nonpatient features, including interactions with HCWs and direct or indirect (consecutive room occupancy) patient contact.\u003Cbr>MAIN OUTCOMESAND MEASURES HOB was defined as a positive blood culture after the\u003Cbr>third day of hospitalization. Patients who were hospitalized for more than 3 days were considered at risk for the outcome. We developed 3 gradient boosting models: 2 predictive (with patient features\u003Cbr>only and with both patient and nonpatient features to predict the occurrence of HOB) and 1 causal to test the association of nonpatient features and HOB. Predictive performance is reported using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC), and the results of the causal model are r","cbCaiaswc1tpxGvl","https://ap.wps.com/l/cbCaiaswc1tpxGvl","pdf",4711233,3,1,15,"English","en",105,"# Key Outcomes and Measures\n## Model Design and Evaluation\n## Sensitivity Analyses and Adjustment\n# Results Overview\n## Cohort Characteristics\n## Predictive and Causal Findings\n# Key Points","[{\"question\":\"What is the main objective of this study?\",\"answer\":\"To assess whether nonindividual patient features—summarizing interactions with other patients and healthcare workers—can contribute to predictive and causal machine learning models for hospital-onset bacteremia.\"},{\"question\":\"How was hospital-onset bacteremia defined in the analysis?\",\"answer\":\"Hospital-onset bacteremia was defined as a positive blood culture after the third day of hospitalization, with patients staying longer than 3 days considered at risk.\"},{\"question\":\"Which modeling approaches were used to evaluate the features?\",\"answer\":\"Three gradient boosting models were developed: two predictive models (patient-only vs patient plus nonpatient features) and one causal model to test associations of nonpatient features with hospital-onset bacteremia.\"}]","Integrating Nonindividual Patient Features in Machine Learning Models of Hospital-Onset Bacteremia | PDF",1785947195,38,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"integrating-nonindividual-patient-features-in-machine-learning-models-of-hospital-onset-bacteremia","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/integrating-nonindividual-patient-features-in-machine-learning-models-of-hospital-onset-bacteremia/128381/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-26","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main objective of this study?","Question",{"text":76,"@type":77},"To assess whether nonindividual patient features—summarizing interactions with other patients and healthcare workers—can contribute to predictive and causal machine learning models for hospital-onset bacteremia.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How was hospital-onset bacteremia defined in the analysis?",{"text":81,"@type":77},"Hospital-onset bacteremia was defined as a positive blood culture after the third day of hospitalization, with patients staying longer than 3 days considered at risk.",{"name":83,"@type":74,"acceptedAnswer":84},"Which modeling approaches were used to evaluate the features?",{"text":85,"@type":77},"Three gradient boosting models were developed: two predictive models (patient-only vs patient plus nonpatient features) and one causal model to test associations of nonpatient features with hospital-onset bacteremia.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]