[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117998-en":3,"doc-seo-117998-105":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},117998,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Machine learning for healthcare that matters - Reorienting from technical novelty to equitable impact","Despite significant technical advances in machine learning (ML) over recent years, healthcare impact remains limited. The gap is driven not only by healthcare complexity, but also by structural incentives in the machine learning for healthcare (MLHC) community that prioritize technical novelty over equitable, tangible outcomes. The work frames MLHC as an echo of earlier structural critique and introduces clearly defined Impact Challenges. Using narrative review, it examines research environment factors, training and evaluation choices, and deployment protocols limiting real-world applicability. It contrasts ML on healthcare data versus ML for clinical needs and provides recommendations for researchers, clinicians, institutions, and regulators.","PLOS DIGITAL HEALTH  \nOPEN ACCESS  \nCitation: Balagopalan A, Baldini I, Celi LA, Gichoya J, McCoy LG, Naumann T, et al. (2024) Machine learning for healthcare that matters: Reorienting from technical novelty to equitable impact. PLOS Digit Health 3(4): e0000474 . [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.1371/journal.pdig.0000474](10.1371/journal.pdig.0000474)  \nEditor: Omar Badawi, Telemedicine and Advanced Technology Research Center, UNITED STATES  \nReceived: September 6, 2023  \nAccepted: February 18, 2024  \nPublished: April 15, 2024  \nPeer Review History: PLOS recognizes the benefits of transparency in the peer review process; therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. The editorial history of this article is available here:  \n[https://doi.org/10.1371/journal.pdig.0000474](https://doi.org/10.1371/journal.pdig.0000474)  \n[Copyright:](Copyright:) © [2024](2024) Balagopalan et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nData Availability Statement: All data is contained within the manuscript.  \nFunding: A. B. was funded in part by an Amazon Science PhD Fellowship at the MIT Science Hub. I.  \nRESEARCH ARTICLE  \nMachine learning for healthcare that matters: Reorienting from technical novelty to equitable impact  \nAparna Balagopalan1☯, Ioana Baldini2☯, Leo Anthony Celi3,4,5☯, Judy Gichoya6☯, Liam G. McCoy7☯*, Tristan Naumann8☯, Uri Shalit9☯, Mihaela van der Schaar10,11☯, Kiri  \nL. Wagstaff12☯  \n1 Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology; Cambridge, Massachusetts, United States of America, 2 IBM Research; Yorktown Heights, New York, United States of America, 3 Laboratory for Computational Physiology, Massachusetts Institute of Technology; Cambridge, Massachusetts, United States of America, 4 Division of Pulmonary, Critical Care and Sleep Medicine, Beth Israel Deaconess Medical Center; Boston, Massachusetts, United States of America,  \n5 Department of Biostatistics, Harvard T. H. Chan School of Public Health; Boston, Massachusetts, United States of America, 6 Department of Radiology and Imaging Sciences, School of Medicine, Emory University; Atlanta, Georgia, United States of America, 7 Division of Neurology, Department of Medicine, University of Alberta; Edmonton, Alberta, Canada, 8 Microsoft Research; Redmond, Washington, United States of America, 9 The Faculty of Data and Decision Sciences, Technion; Haifa, Israel, 10 Department of Applied Mathematics and Theoretical Physics, University of Cambridge; Cambridge, United Kingdom, 11 The Alan Turing Institute; London, United Kingdom, 12 Independent Researcher; United States of America  \n☯ These authors contributed equally to this work.  \n* [lmccoy@ualberta.ca](lmccoy@ualberta.ca)  \nAbstract  \nDespite significant technical advances in machine learning (ML) over the past several years, the tangible impact of this technology in healthcare has been limited. This is due not only to the particular complexities of healthcare, but also due to structural issues in the machine learning for healthcare (MLHC) community which broadly reward technical novelty over tangible, equitable impact. We structure our work as a healthcare-focused echo of the 2012 paper “Machine Learning that Matters”, which highlighted such structural issues in the ML community at large, and offered a series of clearly defined “Impact Challenges” to which the field should orient itself. Drawing on the expertise of a diverse and international group of authors, we engage in a narrative review and examine issues in the research background environment, training processes, evaluation metrics, and deployment protocols which act to limit the real-world applicability of MLHC.","cbCaigkdart7Ghru","https://ap.wps.com/l/cbCaigkdart7Ghru","pdf",913292,1,22,"English","en",105,"# Abstract\n## Problem: limited healthcare impact\n## Root causes: structural incentives and MLHC practices\n## Review focus: research background, training, evaluation, deployment\n## Central distinction: ML on vs ML for healthcare\n## Recommendations for stakeholders","[{\"question\":\"Why has machine learning made limited tangible impact in healthcare?\",\"answer\":\"Healthcare impact is limited due to both the complexity of healthcare and structural issues in the MLHC community that reward technical novelty more than equitable, real-world outcomes.\"},{\"question\":\"What is the paper’s central distinction about ML and healthcare?\",\"answer\":\"It distinguishes between machine learning on healthcare data, which treats healthcare as technical challenge material, and machine learning for healthcare, which uses ML to meet concrete clinical needs.\"},{\"question\":\"Which parts of the MLHC process does the review examine?\",\"answer\":\"The review focuses on research background conditions, training processes, evaluation metrics, and deployment protocols that constrain real-world applicability.\"}]","Machine learning for healthcare that matters - Reorienting from technical novelty to equitable impact | PDF",1785680689,55,{"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-for-healthcare-that-matters-reorienting-from-technical-novelty-to-equitable-impact","",{"@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-for-healthcare-that-matters-reorienting-from-technical-novelty-to-equitable-impact/117998/",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},"Why has machine learning made limited tangible impact in healthcare?","Question",{"text":75,"@type":76},"Healthcare impact is limited due to both the complexity of healthcare and structural issues in the MLHC community that reward technical novelty more than equitable, real-world outcomes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the paper’s central distinction about ML and healthcare?",{"text":80,"@type":76},"It distinguishes between machine learning on healthcare data, which treats healthcare as technical challenge material, and machine learning for healthcare, which uses ML to meet concrete clinical needs.",{"name":82,"@type":73,"acceptedAnswer":83},"Which parts of the MLHC process does the review examine?",{"text":84,"@type":76},"The review focuses on research background conditions, training processes, evaluation metrics, and deployment protocols that constrain real-world applicability.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]