[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128487-en":3,"doc-seo-128487-105":29,"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":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},128487,13056712833777,"Logic","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","A Methodology Based on Quality Gates for Certifiable AI in Medicine - Towards a Reliable Application of Metrics in Machine Learning","Medicine is a high-risk domain where rapid AI adoption requires concrete ways to satisfy legal and quality expectations. The proposed methodology translates abstract certification concepts into actionable guidance across the entire life cycle using Quality Gates. It emphasizes stakeholder inclusion, domain embedding, and risk analysis, and connects these gates to quality gate metrics for machine learning. The work focuses on performance metrics for binary classification in a medical context, aiming at reliable metric selection and auditing.","# A Methodology Based on Quality Gates for Certifiable AI in Medicine:Towards a Reliable Application of Metrics in Machine Learning\n\nMiriam EliaDand Bernhard BauerDb  \nFaculty of Applied Computer Science,University of Augsburg,Germany(miriam.elia,bernhard.bauer)@informatik.uni-augsburg.de  \nCertifiable AI,Quality Management,Machine Learning,Healthcare,Metrics,Deep Learning,PerformanceKeywords:Evaluation,Algorithm Auditing.  \nAbstract:As of now,intelligent technologies experience a rapid growth.For a reliable adoption of those new andpowerful systems into day-to-day life,especially with respect to high-risk settings such as medicine,technicalmeans to realize legal requirements correctly,are indispensible.Our proposed methodology comprises anapproach to translate such partly more abstract concepts into concrete instructions -it is based on QualityGates along the intelligent system's complete life cycle,which are composed of use-case adapted Criteriathat need to be addressed with respect to certification.Also,the underlying philosophy regarding stakeholderinclusion,domain embedding and risk analysis is illustrated.In the present paper,the Quality Gate Metrics isoutlined for the application of machine learning performance metrics focused on binary classification.  \n## 1 INTRODUCTION\n\nknowledge and risk analysis.The focus lies on defin-ing general guidelines towards metrics selection for acomprehensive evaluation of the ML model,adaptedto the respective medical context.Section 2 explainsthe current legal situation regarding intelligent medi-cal devices with respect to software quality manage-ment and metrics for ML in healthcare.In section  \nThanks to astonishing results,the adoption of AI inmedicine is moving more and more into the center ofattention.Many requirements for a conscious integra-tion of the new technology,especially regarding high-risk contexts,have been published.Recently,the EUreleased its AI Act that stands as a legislative guide-line (European Commission,2021).However,tech-nical means to realize these requirements in medicineare yet to be developed and standardized.In addi-tion,”[t]he healthcare application field introduces re-quirements and potential pitfalls that are not imme-diately obvious from the'general data science'view-point”(Jussi,2021,1).Challenges regarding the de-sired adoption of this complex technology into clini-cal day-to-day life are partly based on the necessity ofcomprehensive Machine Learning(ML)knowledgeto accurately evaluate the system.The present workis part of our approach towards a generic and cus-tomizable methodology -introduced in this paper andbased on Quality Gates (QG)-that comprises exist-ing research on the development of ML models forCertifiable AI in Medicine into guidelines for devel-opers and auditing offices,while paying special atten-tion to end-user perspectives,the inclusion of domain  \n3,our methodology's basic concepts are introduced,while section 4 specializes on the QG Metrics andpresents guidelines for a reliable selection,adaptedto the medical context.Finally,section 5 summarizesthe present work and derives open research questions.  \n## 2 RELATED WORK\n\nFunctional &Safety Standards:Since 2021,anupdated version of the Medical Device Regulation(MDR)is in place that guarantees the Conformité Eu-ropéenne(CE),i.e.conformity with”[….]EU safety,health and environmental protection requirements,aswell as with norms set by the International Orga-nization for Standardization (ISO)”(Ben-Menahem,2020,1).ISO does not perform certification activitiesitself,but provides internationally accepted norms,asDIN ENISO 9001:2015-11 for process-oriented qual-ity management systems,or ISO 13485 for medicaldevices,for instance.Another important concept issafety,i.e.protecting the user from potentially harm-  \n486  \nful behavior of the software.Functional requirementsare summarized under IEC 61508,while DIN ENIEC 60601 and DIN EN IEC 62304 specifically fo-cus on medical devices.Moreover,Safety ","cbCais0ZPx92wQmc","https://ap.wps.com/l/cbCais0ZPx92wQmc","pdf",433829,1,"English","en",105,"# Introduction\n# Related Work\n## Functional & Safety Standards\n## Certification & Medical AI\n## Quality Gates & Metrics\n# Methodology and QG Metrics\n# Conclusion","[{\"question\":\"Why is a methodology needed for certifiable AI in medicine?\",\"answer\":\"AI must be reliably adopted in medicine, a high-risk setting with legal requirements and quality expectations. The paper argues that technical means for meeting these demands are not yet fully developed or standardized.\"},{\"question\":\"What are Quality Gates and how are they used in the approach?\",\"answer\":\"Quality Gates are based on software quality management and act as objective verification gates. The methodology uses use-case adapted criteria across the system life cycle to support certification needs.\"},{\"question\":\"How does the paper link quality gates to machine learning evaluation?\",\"answer\":\"It outlines quality gate metrics that guide the selection and use of machine learning performance metrics. The presentation focuses on metrics for machine learning performance in the case of binary classification.\"}]","A Methodology Based on Quality Gates for Certifiable AI in Medicine - Towards a Reliable Application of Metrics in Machine Learning | PDF",1786001339,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"a-methodology-based-on-quality-gates-for-certifiable-ai-in-medicine-towards-a-reliable-application-of-metrics-in-machine-learning","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"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":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/a-methodology-based-on-quality-gates-for-certifiable-ai-in-medicine-towards-a-reliable-application-of-metrics-in-machine-learning/128487/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-25","2026-08-06",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is a methodology needed for certifiable AI in medicine?","Question",{"text":75,"@type":76},"AI must be reliably adopted in medicine, a high-risk setting with legal requirements and quality expectations. The paper argues that technical means for meeting these demands are not yet fully developed or standardized.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What are Quality Gates and how are they used in the approach?",{"text":80,"@type":76},"Quality Gates are based on software quality management and act as objective verification gates. The methodology uses use-case adapted criteria across the system life cycle to support certification needs.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the paper link quality gates to machine learning evaluation?",{"text":84,"@type":76},"It outlines quality gate metrics that guide the selection and use of machine learning performance metrics. The presentation focuses on metrics for machine learning performance in the case of binary classification.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":28,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":28,"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":106,"slug":137},19,"General","general"]