• Risk Management for ML medical devices following BS/AAMI 34971:2023 and ISO 14971
  • Risk Management for ML medical devices following BS/AAMI 34971:2023 and ISO 14971

    • Speaker : Edwin Waldbusser
    • Session Code : EWFEB2724
    • Date : 27th February 2024
    • Time : This Event is Over and the Recorded Content is Available
    • Duration : 60 Mins

Overview:

 

FDA has always prioritized the risk management of medical devices, adhering to its regulations while also endorsing the use of ISO 14971. The complexity of risk management escalates with software as a medical device (SaMD) and software in a medical device (SiMD), especially when machine learning (ML) is involved.

 

The issuance of BS/AAMI 34971:2023, "Guidance on the application of ISO 14971 to AI and ML," represents a significant development. This document, a joint effort by the BSI and AAMI, has been recognized by the FDA and offers comprehensive guidelines tailored for AI and ML technologies in medical devices.

 

This webinar aims to demystify the ISO 14971 risk management process, highlighting the unique challenges posed by ML. We will delve into Hazard Analysis as outlined in ISO 14971, a pivotal risk management technique assessing risks during normal operation and fault conditions.

 

Participants will gain insights into conducting a thorough hazard analysis, with a clear explanation of terms such as “hazard,” “hazardous situation,” “harm,” “causative event,” “ALARP,” and “risk index.” The session will guide attendees through the risk analysis process step by step, using examples to illustrate hazards and hazardous situations, including those specific to ML technologies.


This session is not a programming or technical coding workshop but rather focuses on guiding manufacturers, quality assurance professionals, and regulatory affairs specialists through the landscape of BS/AAMI 34971:2023 and ISO 14971 compliance.

 

Areas covered during the session:

 

  • Hazard analysis terminology
  • The process of conducting a hazard analysis
  • Quality control (QC) of datasets and ML algorithm updating
  • The significance of "explainability" in ML models
  • Cybersecurity considerations in the context of ML medical devices

 

Why should you attend?

 

With the evolving landscape of medical device regulation and the integration of advanced technologies like AI and ML, staying abreast of the latest guidance is crucial. BS/AAMI 34971:2023 offers a framework for managing the risks associated with these innovations. This webinar will equip you with the knowledge to navigate these complexities, ensuring compliance and the safety of medical devices.

 

Who should attend?

 

  • Medical Device Manufacturers and Developers
  • Quality Assurance and Regulatory Affairs Specialists
  • Risk Management Professionals
  • Clinical Engineers and Healthcare Technology Managers
  • Software Engineers and Developers in the Medical Sector
  • Compliance Officers and Legal Advisors
  • R&D Personnel
  • Product Managers
  • Healthcare Providers


This webinar is designed to provide attendees with a understanding of the latest standards and best practices in risk management for medical devices, with a special focus on the complexities introduced by machine learning and artificial intelligence.


Edwin Waldbusser is a consultant retired from industry after 20 years in management of development of medical devices (5 patents). He has been consulting in the US and internationally in the areas of design control, risk analysis and software validation for the past 11 years.


Mr. Waldbusser has a BS in Mechanical Engineering and an MBA. He is a Lloyds of London certified ISO 9000 Lead Auditor and a member of the Thomson Reuters Expert Witness network.

Write a review

Please login or register to review

Enrollment Options

 

Tags: ISO 14971, BS/AAMI 34971:2023, Machine Learning Medical Devices, Risk Management Healthcare, AI Medical Device Safety, Medical Device Software Compliance, Cybersecurity in Healthcare, Medical Dataset Quality Control, Regulatory Compliance Webinar, AI Explainability in Healthcare, Edwin, Waldbusser, February 2024