[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119110-en":3,"doc-seo-119110-105":30,"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":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},119110,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",7,"Healthcare","Physicians should build their own machine-learning models","Doctors should be able to develop their own machine-learning models, because effective medical AI depends not only on computation but on usability, communication, and clinical fit. The proposal focuses on physicians through user-friendly “spotlight” frameworks that reduce the need for extensive prior ML knowledge. By bridging technical and medical teams, such tools improve interdisciplinary collaboration, address UX learning barriers, and enable physicians to customize and validate models within real clinical workflows.","ll  \nOPEN ACCESS  \nOpinion  \nPhysicians should build their own machine-learning models  \nYosra Magdi Mekki1,2,3,*  \n1College of Medicine, Qatar University, QU Health, Qatar University, PO Box 2713, Doha, Qatar  \n2Machine Learning Lab Group, College of Engineering, Qatar University, PO Box 2713, Doha, Qatar  \n3The Clinician Engineer Hub, University of Cambridge Hospitals, Cambridge, UK  \n*Correspondence: [ym1707134@qu.edu.qa](ym1707134@qu.edu.qa)[ ](ym1707134@qu.edu.qa)[https://doi.org/10.1016/j.patter.2024.100948](https://doi.org/10.1016/j.patter.2024.100948)  \nYosra Mekki suggests that doctors should have the ability to develop their own machine-learning models. She proposes an approach with the ‘‘spotlight’’ on physicians, to create user-friendly frameworks that allow doctors to develop customized models without requiring extensive previous knowledge of machine learning.  \n‘‘Today’s ‘AI’ revolution is more of a UX revolution than an AIrevolution.’’  \nI build machine-learning (ML) solutionsand teach artificial intelligence (AI)tomedical students, parallel to my medical training. This dual role has afforded me a front-row seat in the rapid integration of ML into healthcare. I have come to recognize the pressing need for improvements in AI healthcare development. As I toggle between computational and clinical‘‘teams’’ at our lab, I have the opportunity to experience both the computational and clinical facets of creating medical AI. I can build models from the ground up, and also see them through clinical trials. I may also conduct these trials myself during my shifts atthe hospital. This exposure has allowed me to witnessfirsthand the collaborative nature required in the development of these systems, and most importantly, the pitfalls that come with creating models in interdisciplinary environments. I argue that the future ofAI in healthcare lies in taking a versatile, foundational approach.  \nMy role revealed the communication issues that can happen in a team of ‘‘allstar’’ doctors and ML experts. It involves translating between the technical and medical teams. If a model did not perform as intended due to a development issue, I would step in to adjust the pipeline based on my understanding of the medical aspects, and vice versa, where I would communicate with physicians in terms they could understand, explaining the expectations and limitations of a specific model for their use case.  \nThe current landscape of AI in healthcare is largely shaped by collaborations  \nthat bring together ML experts, healthcare workers, and professionals with dual expertise in both fields. There is a need for a new collaborative model in medical AI labs worldwide, given the rarity of individuals with dual expertise in both medicine and ML. Expecting every ML expert to have medical knowledge, or every physician to be versed in ML, is unrealistic. I advocate for empowering doctors to independently build their own AI models. Developers should redirect themselves to creating simple, userfriendly frameworks that enable a physician’s autonomy and creativity, particularly benefiting senior physicians who may not have had exposure to AI and technology in their earlier training. As a teacher, I can see a parallel between the evolution of AI in healthcare and the evolution of photography. Just as early photographers needed technical knowledge of cameras, current AI developers need deep understanding of model building. However, the future lies in doctors using AI toolkits with a focus on application and outcome, much like modern photographers focus on composition rather than camera mechanics.  \nI quote Cassie Kozyrkov,1 former Chief Decision Scientist at Google: ‘‘Today’s‘AI’ revolution is more of a UX revolution than an AI revolution.’’ This quote succinctly captures the essence of my argument: the true power of AI in healthcare lies not just in its computational capabilities but in how intuitively and effectively it can be used by healthcare professionalsin var","cbCaicGfpoWbdycE","https://ap.wps.com/l/cbCaicGfpoWbdycE","pdf",257201,1,3,"English","en",105,"# Physicians should build their own machine-learning models\n## Spotlight on physicians and user-friendly frameworks\n## Communication between ML experts and medical teams\n## Rethinking collaboration models in medical AI labs\n## UX-driven use of AI and education for students\n## Platform vision for practical AI adoption in clinical work","[{\"question\":\"Why does the author argue physicians should build their own machine-learning models?\",\"answer\":\"Because medical AI’s real value depends on usability and clinical integration, which is best achieved when physicians can develop and tailor models for their own use cases.\"},{\"question\":\"What is meant by the “spotlight” approach in the document?\",\"answer\":\"A focus on physicians to create user-friendly frameworks that let doctors build customized models without requiring deep prior machine-learning expertise.\"},{\"question\":\"How does the author describe the main challenge when developing medical AI in teams?\",\"answer\":\"The core issue is communication gaps between technical ML teams and clinical teams, requiring translation and adjustments to align model pipelines with medical expectations and limitations.\"}]","Physicians should build their own machine-learning models | PDF",1785722433,8,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":28},"physicians-should-build-their-own-machine-learning-models","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"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":21},"https://docshare.wps.com/document/healthcare/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/physicians-should-build-their-own-machine-learning-models/119110/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why does the author argue physicians should build their own machine-learning models?","Question",{"text":74,"@type":75},"Because medical AI’s real value depends on usability and clinical integration, which is best achieved when physicians can develop and tailor models for their own use cases.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What is meant by the “spotlight” approach in the document?",{"text":79,"@type":75},"A focus on physicians to create user-friendly frameworks that let doctors build customized models without requiring deep prior machine-learning expertise.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the author describe the main challenge when developing medical AI in teams?",{"text":83,"@type":75},"The core issue is communication gaps between technical ML teams and clinical teams, requiring translation and adjustments to align model pipelines with medical expectations and limitations.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,117,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":115,"slug":116},40,"healthcare",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},"Research & Report",30,"research-report",{"id":122,"doc_module":4,"doc_module_name":46,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]