[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117130-en":3,"doc-seo-117130-105":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},117130,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Fair Machine Learning in Healthcare - A Survey","Digitization of healthcare data and rapid advances in computation have accelerated adoption of machine learning, yet these systems can reinforce or worsen existing inequities, creating fairness risks such as unequal resource allocation and differential diagnostic errors across demographic groups. This survey examines how machine learning fairness meets healthcare disparities by applying a distributive justice framework to classify fairness issues into equal allocation and equal performance. It reviews fairness metrics, analyzes bias across the ML lifecycle, and discusses mitigation strategies and remaining open challenges, proposing future research directions toward ethical, equitable healthcare ML.","Fair Machine Learning in Healthcare: A Survey  \nQizhang Feng, Mengnan Du, Na Zou, and Xia Hu  \narXiv :2206 . 14397v 3 [ cs .LG] 1 Feb 2024  \nAbstract—The digitization of healthcare data coupled with advances in computational capabilities has propelled the adoption of machine learning (ML) in healthcare. However, these methods can perpetuate or even exacerbate existing disparities, leading to fairness concerns such as the unequal distribution of resources and diagnostic inaccuracies among different demographic groups. Addressing these fairness problem is paramount to prevent further entrenchment of social injustices. In this survey, we analyze the intersection of fairness in machine learning and healthcare disparities. We adopt a framework based on the principles of distributive justice to categorize fairness concerns into two distinct classes: equal allocation and equal performance. We provide a critical review of the associated fairness metrics from a machine learning standpoint and examine biases and mitigation strategies across the stages of the ML lifecycle, discussing the relationship between biases and their countermeasures. The paper concludes with a discussion on the pressing challenges that remain unaddressed in ensuring fairness in healthcare ML, and proposes several new research directions that hold promise for developing ethical and equitable ML applications in healthcare.  \nImpact Statement—Along with the rapid growth in the use of machine learning in healthcare in recent years, there has been a growing concern about the fairness problems that come along with it. This survey article helps break down the barriers between fair machine learning and healthcare, and aims to: 1) improve healthcare practitioners’ understanding of the bias of machine learning in healthcare from a computational perspective; 2) assist machine learning researchers in establishing a clear picture on how to develop fair algorithms in various healthcare scenarios from a healthcare perspective; and 3) increase public trust in machine learning algorithms and promote the use of machine learning methods in real-world healthcare settings.  \nIndex Terms—Artificial Intelligence, Fairness, Healthcare, Machine Learning.  \nI. INTRODUCTION  \nWITH the advent of sophisticated machine learning  \n(ML) applications in healthcare, from medical image analysis to electronic health records processing, we stand on the cusp of a transformative era in medicine [84], [116],[117], [137], [92] . Despite these advancements, there remains a significant yet understudied challenge: ensuring fairness in algorithmic decisions, particularly as they relate to the equitable treatment of diverse patient populations [135] .  \nFairness in healthcare ML refers to the equitable distribution of benefits and burdens across all demographic groups, with  \nManuscript submitted June 17, 2022; date of current version Nov 7, 2023 . This work is in part supported by NSF grants IIS-1939716 and IIS-1900990 .  \nQizhang Feng is with the Department of Computer Science & Engineering, Texas A&M University, TX 77843, US (e-mail: [qf31@tamu.edu](qf31@tamu.edu)).  \nMengnan Du is with the Department of Data Science, New Jersey Institute of Technology, NJ 07102, US ([e-mail: mengnan.du@njit.edu](e-mail: mengnan.du@njit.edu)).  \nNa Zou is with the Department of Engineering Technology & Industrial Distribution, Texas A&M University, TX 77843, US (e-mail: [nzou1@tamu.edu](nzou1@tamu.edu)).  \nXia Hu is with the Department of Computer Science, Rice University, TX 77251, US (e-mail: [xia.hu@rice.edu](xia.hu@rice.edu)) .  \nThis paragraph will include the Associate Editor who handled your paper.  \nparticular attention to historically marginalized communities. It encompasses a range of issues, from the allocation of healthcare resources to diagnostic accuracy across different patient demographics. Notable instances include genetic tests where AI models disproportionately misrepresent risks for minority groups [10","cbCaifYXRa8B06dN","https://ap.wps.com/l/cbCaifYXRa8B06dN","pdf",2486592,1,16,"English","en",105,"# Introduction\n## Fairness in healthcare ML\n# Framework and fairness categories\n## Equal allocation\n## Equal performance\n# Fairness metrics and bias mitigation\n## Metrics from an ML perspective\n## Bias across the ML lifecycle\n# Challenges and future research directions","[{\"question\":\"What fairness problems does the survey focus on in healthcare machine learning?\",\"answer\":\"It focuses on unequal distribution of benefits and burdens across demographic groups, including unequal resource allocation and diagnostic inaccuracies.\"},{\"question\":\"How does the survey classify fairness concerns?\",\"answer\":\"It uses a distributive justice framework to categorize fairness into two classes: equal allocation and equal performance.\"},{\"question\":\"What does the survey cover regarding bias and mitigation?\",\"answer\":\"It provides a critical review of fairness metrics, examines biases across stages of the ML lifecycle, and discusses related mitigation strategies and their relationship with biases.\"}]","Fair Machine Learning in Healthcare - A Survey | PDF",1785674034,40,{"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},"fair-machine-learning-in-healthcare-a-survey","",{"@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/fair-machine-learning-in-healthcare-a-survey/117130/",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","2026-08-02",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 fairness problems does the survey focus on in healthcare machine learning?","Question",{"text":75,"@type":76},"It focuses on unequal distribution of benefits and burdens across demographic groups, including unequal resource allocation and diagnostic inaccuracies.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the survey classify fairness concerns?",{"text":80,"@type":76},"It uses a distributive justice framework to categorize fairness into two classes: equal allocation and equal performance.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the survey cover regarding bias and mitigation?",{"text":84,"@type":76},"It provides a critical review of fairness metrics, examines biases across stages of the ML lifecycle, and discusses related mitigation strategies and their relationship with biases.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"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"]