[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119545-en":3,"doc-seo-119545-105":30,"detail-sidebar-cat-0-en-105":95},{"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":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},119545,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Investigating anatomical bias in clinical machine learning algorithms","Clinical machine learning algorithms show promise for diagnostic support, improved patient treatment, and reduced clinician workload, yet their adoption is limited by bias—systematic and unfair discrimination. This work measures anatomical bias in clinical text algorithms by defining unfair outcomes against patients with the same medical condition located in specific anatomical regions. Across two models and two Danish clinical text classification tasks, results indicate strong susceptibility to anatomical bias. The study recommends careful dataset curation to isolate anatomical-location effects and prevent harm to patient subgroups.","University of Southern Denmark  \nInvestigating anatomical bias in clinical machine learning algorithms  \nPedersen, Jannik Skyttegaard; Laursen, Martin Sundahl; Vinholt, Pernille Just; Alnor, Anne Bryde; Savarimuthu, Thiusius Rajeeth  \nPublished in:  \nFindings of the Association for Computational Linguistics: EACL 2023  \nPublication date: 2023  \nDocument version:  \nFinal published version  \nDocument license: Unspecified  \nCitation for pulished version (APA):  \nPedersen, J. S. , Laursen, M. S. , Vinholt, P. J. , Alnor, A. B. , & Savarimuthu, T. R. (2023) . Investigating anatomical bias in clinical machine learning algorithms. In Findings of the Association for Computational Linguistics: EACL 2023 (pp. 1368-1380) . Association for Computational Linguistics (ACL) .  \nGo to publication entry in University of Southern Denmark's Research Portal  \nTerms of use  \nThis work is brought to you by the University of Southern Denmark.  \nUnless otherwise specified it has been shared according to the terms for self-archiving.  \nIf no other license is stated, these terms apply:  \n• You may download this work for personal use only.  \n• You may not further distribute the material or use it for any profit-making activity or commercial gain  \n• You may freely distribute the URL identifying this open access version  \nIf you believe that this document breaches copyright please contact us providing details and we will investigate your claim. Please direct all enquiries to [puresupport@bib.sdu.dk](puresupport@bib.sdu.dk)  \nDownload date: 02. Aug. 2026  \nInvestigating anatomical bias in clinical machine learning algorithms  \nJannik Skyttegaard Pedersen* Martin Sundahl Laursen*  \nThe Maersk Mc-Kinney Moller Institute The Maersk Mc-Kinney Moller Institute  \nUniversity of Southern Denmark University of Southern Denmark  \n[jasp@mmmi.sdu.dk](jasp@mmmi.sdu.dk) [msla@mmmi.sdu.dk](msla@mmmi.sdu.dk)  \nPernille Just Vinholt  \nDepartment of Clinical Biochemistry Odense University Hospital  \nAnne Bryde Alnor  \nDepartment of Clinical Biochemistry Odense University Hospital  \nThiusius Rajeeth Savarimuthu  \nThe Maersk Mc-Kinney Moller Institute University of Southern Denmark  \nAbstract  \nClinical machine learning algorithms have shown promising results and could potentially be implemented in clinical practice to provide diagnosis support and improve patient treatment. Barriers for realisation of the algorithms’full potential include bias which is systematic and unfair discrimination against certain individuals in favor of others.  \nThe objective of this work is to measure anatomical bias in clinical text algorithms. We define anatomical bias as unfair algorithmic outcomes against patients with medical conditions in specific anatomical locations. We measure the degree of anatomical bias across two machine learning models and two Danish clinical text classification tasks, and find that clinical text algorithms are highly prone to anatomical bias. We argue that datasets for creating clinical text algorithms should be curated carefully to isolate the effect of anatomical location in order to avoid bias against patient subgroups.  \n1 Introduction  \nResearch in clinical machine learning algorithms have shown promising results for automating clinical tasks. The algorithms could potentially be implemented in clinical practice to provide diagnosis support, improve patient treatment and provide time-savings for medical doctors (Topol, 2019 ; Matheny et al., 2020) .  \nHowever, despite appealing research results, there are currently limited examples of algorithms being successfully deployed into clinical practice (Kelly et al., 2019) . Barriers for realisation of the algorithms’ full potential include bias and generali-  \n*Equal contribution  \nsation issues (Char et al., 2018 ; Hovy and Prabhumoye, 2021 ; Carrell et al., 2017) .  \nAlgorithmic bias can be defined as systematic and unfair discrimination against certain individuals or groups of individuals in favor of others (Friedm","cbCait1EbPGlQSvz","https://ap.wps.com/l/cbCait1EbPGlQSvz","pdf",671259,1,14,"English","en",105,"# Abstract\n# Introduction\n## Algorithmic bias and clinical deployment barriers\n## Anatomical bias definition and scope","[{\"question\":\"What does the paper mean by anatomical bias in clinical text algorithms?\",\"answer\":\"It defines anatomical bias as unfair algorithmic outcomes where performance varies depending on the anatomical location of a patient's medical condition.\"},{\"question\":\"How is anatomical bias evaluated in the study?\",\"answer\":\"The study measures bias across two machine learning models and two Danish clinical text classification tasks, using clinical narrative text from electronic health records.\"},{\"question\":\"What is the main finding about clinical text algorithms?\",\"answer\":\"The results show clinical text algorithms are highly prone to anatomical bias, leading to different outcomes for patient subgroups.\"},{\"question\":\"What mitigation strategy does the paper recommend?\",\"answer\":\"It argues that datasets for clinical text algorithms should be curated carefully to isolate the effect of anatomical location and avoid bias against patient subgroups.\"}]","Investigating anatomical bias in clinical machine learning algorithms | PDF",1785724879,35,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"investigating-anatomical-bias-in-clinical-machine-learning-algorithms","",{"@graph":36,"@context":89},[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/investigating-anatomical-bias-in-clinical-machine-learning-algorithms/119545/",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","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What does the paper mean by anatomical bias in clinical text algorithms?","Question",{"text":75,"@type":76},"It defines anatomical bias as unfair algorithmic outcomes where performance varies depending on the anatomical location of a patient's medical condition.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is anatomical bias evaluated in the study?",{"text":80,"@type":76},"The study measures bias across two machine learning models and two Danish clinical text classification tasks, using clinical narrative text from electronic health records.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the main finding about clinical text algorithms?",{"text":84,"@type":76},"The results show clinical text algorithms are highly prone to anatomical bias, leading to different outcomes for patient subgroups.",{"name":86,"@type":73,"acceptedAnswer":87},"What mitigation strategy does the paper recommend?",{"text":88,"@type":76},"It argues that datasets for clinical text algorithms should be curated carefully to isolate the effect of anatomical location and avoid bias against patient subgroups.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]