[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123278-en":3,"doc-seo-123278-105":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},123278,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Lifecycle Management Framework for IVDR and EU AI Act Compliant Machine Learning Enabled Medical Device Software - Master’s Thesis","Machine Learning (ML) in In Vitro Diagnostic (IVD) medical software offers improved diagnostic accuracy but creates additional regulatory complexity in the European Union due to the interaction between the In Vitro Diagnostic Regulation (IVDR) and the EU AI Act. This thesis performs a comparative gap analysis of the two frameworks, highlighting overlaps and legal differences, and addresses missing transparency around algorithmic bias and limited IVD-specific clinical validation guidance. It proposes an integrated lifecycle management framework that incorporates AI Act requirements into the existing IVDR lifecycle, enabling operability-restricted, ML-enabled IVD software compliance with an open-access regulatory foundation for startups.","Diponkor Mondal  \nLifecycle Management Framework for IVDR and EU AI Act Compliant Machine Learning Enabled Medical Device Software  \nMetropolia University of Applied Sciences Master of Engineering  \nInformation Technology Master’s Thesis  \n10 Jun 2025  \nPreface  \nThis research work was conducted at the Hematoscope Lab, an academic team of physicians, programmers, scanner engineers, and students affiliated with the Hospital District of Helsinki and Uusimaa HUS and HUSLAB. The lab focuses on combining high-resolution automated imaging and deep learning methods to enhance the diagnosis, monitoring , and understanding of hematological diseases. Hematoscope Oy is the spin-off company emerging from this research group.  \nDuring the research and writing process, I received invaluable guidance and support from my supervisors, Principal Lecturer Mikael Soini and Mikko Purhonen. Specifically, Mikko’s expert insights and constructive feedback significantly enhanced the clarity of my work. I am also truly grateful to Oscar Brück , the principal investigator of the Hematoscope Lab, for his continuous support and inspiration.  \nAdditionally, I would like to extend my heartfelt thanks to my colleagues at Hematoscope Lab and fellow students at Metropolia University of Applied Sciences for their collaboration and meaningful discussions.  \nAs I am still at the early stage of my career in regulatory affairs, writing this thesis has been a great learning experience for me. It helped me understand how artificial intelligence is not only changing MedTech industries but also changing the way we look at quality and regulatory work.  \nLastly, and it would be unfair not to mention, a special thanks goes to my wife, Snigdha. Her patience, understanding, and unconditional support during countless late office hours and long nights of work have been truly invaluable.  \nDiponkor Mondal  \nSyöpäkeskus HUS, 10 June 2025  \nAbstract  \nAuthor: Diponkor Mondal  \nTitle: Lifecycle Management Framework for IVDR and EU AI Act  \nCompliant Machine Learning Enabled Medical Device  \nNumber of Pages: 54 pages + 2 Appendices  \nDate: 10 Jun 2025  \nDegree: Master of Engineering  \nDegree Programme: Information Technology  \nProfessional Major: Medical Technology  \nSupervisors: Mikael Soini, Principal Lecturer  \nMikko Purhonen, MSc. (Tech.)  \nThe application of Machine Learning (ML) in In Vitro Diagnostic (IVD) medical software presents significant possibilities for improving diagnostic accuracy , but also introduces additional regulatory hurdles within the European Union (EU) due to the interplay between the In Vitro Diagnostic Regulation (IVDR) and the AI Act. This thesis undertakes a comparative gap analysis of two legislative frameworks to identify and address legal differences and overlaps. The IVDR is governed by scientific validity, safety, and clinical performance , but lacks transparency regarding algorithmic bias and verifiable machine learning components. In contrast, the AI Act brings more structure by providing a comprehensive risk-based approach for high-risk AI systems. However, it lacks detailed clinical validation guidance within IVD boundaries. To mitigate these regulatory hurdles, this thesis proposes an integrated lifecycle management framework that incorporates AI Act requirements into the existing lifecycle framework , complying with the IVDR. The framework supports complete compliance with operability restrictions on the development of ML-based IVD medical software. This study makes a significant academic and practical contribution by laying the groundwork for an openaccess regulatory framework that enables startup companies to navigate complex compliance requirements efficiently.  \nKeywords: IVDR, AI Act, ML in Diagnostics, Lifecycle Management Framework, Regulatory Strategy for IVD Software  \nThe originality of this thesis has been checked using Turnitin Originality Check service  \nContents  \nList of Abbreviations  \n1 Introduction 1  \n2 Research Objectiv","cbCaiv9HfNnoAjH5","https://ap.wps.com/l/cbCaiv9HfNnoAjH5","pdf",963737,1,103,"English","en",105,"# Introduction\n## Research Objectives\n## Methods\n### Research Design: Constructive Research\n### Regulatory Framework Analysis\n### Data Collection\n# Regulatory and Standards Background\n## EU Legislation\n### In Vitro Diagnostic Regulation (IVDR) 2017/746\n### Overview of the AI Act and Its Impact on ML-Enabled IVD Software\n## International Standards for Life Cycle Management\n### ISO 13485 Quality Management System\n### ISO 14971: Risk Management\n### IEC 62304: Software Lifecycle Processes\n## Regulatory Pathways for ML-Enabled Medical Devices\n## The Need for a Lifecycle Management Framework\n# Results: Gap Analysis and Key Findings\n## Key Challenges in Regulatory Compliance\n### ML-Specific Guidance Gaps\n### Data Privacy and Security Concerns\n### Transparency and Explainability Requirements\n### Validation and Verification of ML Algorithms\n### Data Bias, Fairness, and Validation Requirements\n## Comparative Analysis IVDR Vs. AI Act\n## Gap Analysis: IVDR Vs. AI Act\n## Bridging the Gap Between the AI Act and IVDR\n### Unified Classification and Risk Management Approach\n### Enhanced Technical Documentation and Traceability\n### Proactive Ethical Compliance and Governance Mechanisms\n### Lifecycle Management Integration\n### Continuous Regulatory Surveillance and Update Mechanism\n# Proposed Lifecycle Management Framework\n## Framework Objectives and Design Principles\n## Integration of IVDR and AI Act Requirements\n### Mapping IVDR (Annex I & II) into the ML lifecycle\n### Mapping AI Act (Articles 10–15) into the ML lifecycle\n## Model Development and Validation Process\n### Define Intended Purpose and Risk Classification\n### Data Acquisition and Preparation\n### Model Design and Training\n### Verification and Validation\n### Human Factors Validation and Oversight Testing","[{\"question\":\"What regulatory problem does the thesis address for ML-enabled IVD medical software?\",\"answer\":\"It addresses the regulatory hurdles created when Machine Learning for In Vitro Diagnostic (IVD) software must satisfy both the IVDR and the EU AI Act, including overlaps and gaps between the two frameworks.\"},{\"question\":\"How does the thesis compare IVDR and the EU AI Act?\",\"answer\":\"It conducts a comparative gap analysis, describing IVDR’s focus on scientific validity, safety, and clinical performance while noting limited transparency on algorithmic bias and verifiable ML components, and contrasting this with the AI Act’s risk-based structure alongside limited IVD-boundary clinical validation guidance.\"},{\"question\":\"What is the proposed lifecycle management framework intended to achieve?\",\"answer\":\"It integrates AI Act requirements into the existing IVDR lifecycle to support compliance for operability-restricted development of ML-based IVD medical software, including mapping requirements and improving governance and documentation across the ML lifecycle.\"}]","Lifecycle Management Framework for IVDR and EU AI Act Compliant Machine Learning Enabled Medical Device Software - Master’s Thesis | PDF",1785815682,260,{"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},"lifecycle-management-framework-for-ivdr-and-eu-ai-act-compliant-machine-learning-enabled-medical-device-software-masters-thesis","",{"@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/lifecycle-management-framework-for-ivdr-and-eu-ai-act-compliant-machine-learning-enabled-medical-device-software-masters-thesis/123278/",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","2026-08-04",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 regulatory problem does the thesis address for ML-enabled IVD medical software?","Question",{"text":75,"@type":76},"It addresses the regulatory hurdles created when Machine Learning for In Vitro Diagnostic (IVD) software must satisfy both the IVDR and the EU AI Act, including overlaps and gaps between the two frameworks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis compare IVDR and the EU AI Act?",{"text":80,"@type":76},"It conducts a comparative gap analysis, describing IVDR’s focus on scientific validity, safety, and clinical performance while noting limited transparency on algorithmic bias and verifiable ML components, and contrasting this with the AI Act’s risk-based structure alongside limited IVD-boundary clinical validation guidance.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the proposed lifecycle management framework intended to achieve?",{"text":84,"@type":76},"It integrates AI Act requirements into the existing IVDR lifecycle to support compliance for operability-restricted development of ML-based IVD medical software, including mapping requirements and improving governance and documentation across the ML lifecycle.","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"]