[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122875-en":3,"doc-seo-122875-105":29,"detail-sidebar-cat-0-en-105":90},{"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":20,"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":11},122875,1099523882182,"Eliana","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Applications of Machine Learning in Anaesthesiology and Critical Care","The thesis investigates how machine learning can support clinical decision-making in anaesthesiology and critical care, with a focus on mortality prediction and practical deployment. It examines the trade-off between false positives and true negatives in low-mortality populations, highlights the cautious interpretation of variable importance, and evaluates prognostic signals such as early postoperative urea. The work also tests whether combining continuous intraoperative data with postoperative data improves performance, explores time-series clustering for critical-care sub-phenotypes, and assesses the implementation gap between model development and real-world use.","University of Groningen  \nApplications of Machine Learning in Anaesthesiology and Critical Care  \nAlves Castela Cardoso Forte, José  \nDOI:  \n10.33612/diss.892808451  \nIMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from it. Please check the document version below.  \nDocument Version  \nPublisher's PDF, also known as Version of record  \nPublication date: 2024  \nLink to publication in University of Groningen/UMCG research database  \nCitation for published version (APA):  \nAlves Castela Cardoso Forte, J. (2024) . Applications of Machine Learning in Anaesthesiology and Critical Care. [Thesis fully internal (DIV), University of Groningen] . University of Groningen.  \n[https://doi.org/10.33612/diss.892808451](https://doi.org/10.33612/diss.892808451)  \nCopyright  \nOther than for strictly personal use, it is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license (like Creative Commons) .  \nThe publication may also be distributed here under the terms of Article 25fa of the Dutch Copyright Act, indicated by the “Taverne” license. More information can be found on the University of Groningen website: [https://www.rug.nl/library/open-access/self-archiving-pure/taverne](https://www.rug.nl/library/open-access/self-archiving-pure/taverne)amendment.  \nTake-down policy  \nIf you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.  \nDownloaded from the University of Groningen/U MCG research database (Pure): [http://www.rug. nl/research/portal. For technical reasons the](http://www.rug. nl/research/portal. For technical reasons the)[ ](http://www.rug. nl/research/portal. For technical reasons the)[number of authors shown on this cover page is limited to 10 maximum.](number of authors shown on this cover page is limited to 10 maximum.)  \nDownload date: 29-12-2025  \nProposi'ons accompanying the thesis  \nApplica'ons of Machine Learning in Anaesthesiology and  \nCri'cal Care  \n1 – In populations with relatively low mortality rates such as cardiac surgery patients, it is crucial to seek a favorable trade-off between false positives and true negatives, with a too-high threshold risking missing many “non-survivors”.  \nThis thesis  \n2 – Variable importance is an important element of predictive studies, but should be interpreted with caution.  \nThis thesis  \n3 – Early postoperative urea may be an oft-overlooked predictor of mortality in all types of cardiac operations. However, further research is required to explore physiological processes that may explain this.  \nThis thesis  \n4 – The addition of continuous intraoperative data to postoperative data does not improve model performance or deliver more clinically usable predictions.  \nThis thesis  \n5 – The characterisation of patient sub-phenotypes in critical care can benefit from the inclusion of time-series data in clustering analyses.  \nThis thesis  \n6 – The greatest benefit of blending human and artificial intelligence is in the work done before and after any algorithm is run.  \nBased on practical experience obtained during and beyond this thesis  \n7 – Integration into already existing clinical workflows is perhaps the biggest challenge faced by researchers, clinicians, and others in the implementation of ML-based decision support systems.  \nBased on practical experience beyond this thesis  \n8 – There is a substantial implementation gap between the development of clinical predictive models and their real-world application.  \nBased on practical experience beyond this thesis  \n9 – AI-based systems will not replace clinicians. Clinicians who use AI-based systems will replace clinicians who don’t.  \nA whole lot of people  \n10 – Selecting the right data on which to develop predictive models is the most important step","cbCaiaaWgTB3nNRy","https://ap.wps.com/l/cbCaiaaWgTB3nNRy","pdf",278876,3,1,"English","en",105,"# Propositions accompanying the thesis\n## Patient populations and threshold trade-offs\n## Interpretation of variable importance\n## Prognostic value of early postoperative urea\n## Intraoperative plus postoperative data integration\n## Time-series clustering for sub-phenotypes\n## Human–AI blending before and after algorithms\n## Integration into clinical workflows\n## Implementation gap to real-world application\n## Role of AI versus clinicians\n## Selecting data for predictive models\n## Ethical and practical considerations","[{\"question\":\"How does the thesis address the balance between false positives and true negatives?\",\"answer\":\"In populations with relatively low mortality, such as cardiac surgery patients, the thesis emphasizes a favorable trade-off; using too high a threshold risks missing many non-survivors.\"},{\"question\":\"What does the thesis suggest about variable importance in predictive studies?\",\"answer\":\"Variable importance is described as important, but it should be interpreted with caution to avoid overconfidence in what drives predictions.\"},{\"question\":\"Does adding continuous intraoperative data to postoperative data improve predictions?\",\"answer\":\"The thesis propositions state that adding continuous intraoperative data to postoperative data does not improve model performance or produce more clinically usable predictions.\"}]","Applications of Machine Learning in Anaesthesiology and Critical Care | PDF",1785813463,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":28},"applications-of-machine-learning-in-anaesthesiology-and-critical-care","",{"@graph":35,"@context":84},[36,52,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":20},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/applications-of-machine-learning-in-anaesthesiology-and-critical-care/122875/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-09-11","2026-08-04",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"How does the thesis address the balance between false positives and true negatives?","Question",{"text":74,"@type":75},"In populations with relatively low mortality, such as cardiac surgery patients, the thesis emphasizes a favorable trade-off; using too high a threshold risks missing many non-survivors.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What does the thesis suggest about variable importance in predictive studies?",{"text":79,"@type":75},"Variable importance is described as important, but it should be interpreted with caution to avoid overconfidence in what drives predictions.",{"name":81,"@type":72,"acceptedAnswer":82},"Does adding continuous intraoperative data to postoperative data improve predictions?",{"text":83,"@type":75},"The thesis propositions state that adding continuous intraoperative data to postoperative data does not improve model performance or produce more clinically usable predictions.","https://schema.org",{"og:url":50,"og:type":86,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":88,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]