[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121786-en":3,"doc-seo-121786-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},121786,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine learning-based clinical decision support for infection risk prediction","Healthcare-associated infection (HAI) continues to threaten hospitalized patients and impose substantial strain on healthcare systems. This study develops a clinical decision support tool that generates an infection risk score prior to overt symptoms, enabling earlier secondary assessments for pre-symptomatic at-risk patients. Using ensemble boosted decision trees trained on a stratified retrospective dataset of 36,782 HAI cases, the model predicts HAI before clinical suspicion by leveraging vital signs, laboratory measurements, and demographics. It achieves strong AUC performance up to 48 hours before suspicion and provides interpretability via feature importance.","TYPE Original Research PUBLISHED 18 December 2023 DOI 10.3389/fmed.2023.1213411  \nOPEN ACCESS  \nEDITED BY  \nFrancisco Martín-Rodríguez, University of Valladolid, Spain  \nREVIEWED BY  \nNuria Montes,  \nHospital Universitario de La Princesa, Spain Ulrich Bodenhofer,  \nUniversity of Applied Sciences Upper Austria, Austria  \n*CORRESPONDENCE  \nBryan Conroy  \n [bryan.conroy@philips.com](bryan.conroy@philips.com)  \nRECEIVED 09 May 2023  \nACCEPTED 21 November 2023  \nPUBLISHED 18 December 2023  \nCITATION  \nFeng T, Noren DP, Kulkarni C, Mariani S, Zhao C, Ghosh E, Swearingen D, Frassica J, McFarlane D and Conroy B (2023) Machine learning-based clinical decision support for infection risk prediction.  \nFront. Med. 10:1213411 .  \ndoi: 10.3389/fmed.2023.1213411  \nCOPYRIGHT  \n© 2023 Feng, Noren, Kulkarni, Mariani, Zhao, Ghosh, Swearingen, Frassica, McFarlane and Conroy. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nMachine learning-based clinical decision support for infection risk prediction  \nTing Feng 1, David P. Noren 1, Chaitanya Kulkarni 2, Sara Mariani 1, Claire Zhao 1, Erina Ghosh 1, Dennis Swearingen3, 4,  \nJoseph Frassica 5, Daniel McFarlane 1 and Bryan Conroy 1*  \n1 Philips Research North America, Cambridge, MA, United States, 2 Philips Research Bangalore, Bengaluru, India, 3 Department of Medical Informatics, Banner Health, Phoenix, AZ, United States,  \n4 Department of Biomedical Informatics, University of Arizona College of Medicine, Phoenix, AZ, United States, 5 Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA, United States  \nBackground: Healthcare-associated infection (HAI) remains a significant risk for hospitalized patients and a challenging burden for the healthcare system. This study presents a clinical decision support tool that can be used in clinical workflows to proactively engage secondary assessments of pre-symptomatic and at-risk infection patients, thereby enabling earlier diagnosis and treatment.  \nMethods: This study applies machine learning, specifically ensemble-based boosted decision trees, on large retrospective hospital datasets to develop an infection risk score that predicts infection before obvious symptoms present. We extracted a stratified machine learning dataset of 36,782 healthcare-associated infection patients. The model leveraged vital signs, laboratory measurements and demographics to predict HAI before clinical suspicion, defined as the order of a microbiology test or administration of antibiotics.  \nResults: Our best performing infection risk model achieves a cross-validated AUCof 0.88 at 1 h before clinical suspicion and maintains an AUC >0 .85 for 48 h before suspicion by aggregating information across demographics and a set of 163 vital signs and laboratory measurements. A second model trained on a reduced feature space comprising demographics and the 36 most frequently measured vital signs and laboratory measurements can still achieve an AUC of 0.86 at 1 h before clinical suspicion. These results compare favorably against using temperature alone and clinical rules such as the quick sequential organ failure assessment (qSOFA) score. Along with the performance results, we also provide an analysis of model interpretability via feature importance rankings.  \nConclusion: The predictive model aggregates information from multiple physiological parameters such as vital signs and laboratory measurements to provide a continuous risk score of infection that can be deployed in hospitals to provide advance warning of patient deterioration.  \nKEYWORDS  \nhe","cbCaifoKGCpzTyml","https://ap.wps.com/l/cbCaifoKGCpzTyml","pdf",1477990,1,12,"English","en",105,"# Background\n## Burden and importance of early HAI detection\n# Methods\n## Data and model development using boosted decision trees\n## Prediction window before clinical suspicion\n# Results\n## AUC performance at 1h and up to 48h\n## Reduced feature model and comparison baselines\n## Model interpretability\n# Conclusion","[{\"question\":\"What problem does the study address in hospitalized patients?\",\"answer\":\"The study targets healthcare-associated infection (HAI), which remains a significant risk and causes a heavy burden for healthcare systems. It emphasizes the need for earlier detection before obvious symptoms appear.\"},{\"question\":\"How is the infection risk score predicted and what data is used?\",\"answer\":\"An ensemble-based boosted decision tree model predicts HAI before clinical suspicion. The model uses vital signs, laboratory measurements, and demographics, trained on a stratified retrospective dataset of 36,782 HAI patients.\"},{\"question\":\"How well does the model perform compared with simpler approaches?\",\"answer\":\"The best model reaches a cross-validated AUC of 0.88 at 1 hour before clinical suspicion and remains above 0.85 up to 48 hours before suspicion. Performance compares favorably against using temperature alone and clinical rules such as qSOFA.\"}]","Machine learning-based clinical decision support for infection risk prediction | PDF",1785806831,30,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-based-clinical-decision-support-for-infection-risk-prediction","",{"@graph":36,"@context":85},[37,54,68],{"@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-based-clinical-decision-support-for-infection-risk-prediction/121786/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address in hospitalized patients?","Question",{"text":75,"@type":76},"The study targets healthcare-associated infection (HAI), which remains a significant risk and causes a heavy burden for healthcare systems. It emphasizes the need for earlier detection before obvious symptoms appear.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the infection risk score predicted and what data is used?",{"text":80,"@type":76},"An ensemble-based boosted decision tree model predicts HAI before clinical suspicion. The model uses vital signs, laboratory measurements, and demographics, trained on a stratified retrospective dataset of 36,782 HAI patients.",{"name":82,"@type":73,"acceptedAnswer":83},"How well does the model perform compared with simpler approaches?",{"text":84,"@type":76},"The best model reaches a cross-validated AUC of 0.88 at 1 hour before clinical suspicion and remains above 0.85 up to 48 hours before suspicion. Performance compares favorably against using temperature alone and clinical rules such as qSOFA.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]