Risk Management for ML Medical Devices following AAMI/ BSI TR 34971 and ISO 14971

FDA has always maintained risk management of medical devices as a top priority. FDA has it’s regulations and has also endorsed the use of ISO 14971. Risk management for software as a medical device (SaMD) and software in a medical device (SiMD) is a complex subject and ML adds another level of complexity.

Recently AAMI/BSI TR 34971 was issued: “Guidance on the application of ISO 14971 to AI and ML”. It’s predecessor, AAMI CR 34971, has been endorsed by the FDA. This webinar will explain the ISO 14971 risk management process and explain the additional risks ML poses. Hazard Analysis is described in ISO 14971. This is the most powerful of the risk management techniques because it evaluates risks in normal operation as well as fault conditions. 

In this webinar we will explain the process of conducting a hazard analysis. The confusing terms “hazard”, hazardous situation”, “harm”, “causative event”, “ALARP”, and “risk index” will be explained. We will go step by step through the risk analysis process so that the process is clear. Examples of hazards and hazardous situations will be presented.  The additional hazards and hazardous situations attributable to ML will be discussed.  Issues important to ML such as the Predetermined Change Control Plan (PCCP), data quality and bias will be discussed.

WHY YOU SHOULD ATTEND:

FDA has always maintained risk management of medical devices as a top priority. FDA has it’s regulations and has also endorsed the use of ISO 14971. Risk management for software as a medical device (SaMD) and software in a medical device (SiMD) is a complex subject and ML adds another level of complexity.

Recently AAMI/BSI TR 34971 was issued: “Guidance on the application of 14971 to AI and ML”

This webinar will explain the ISO 14971 risk management process and explain the additional risks ML poses. 

In this webinar we will explain the process of conducting a hazard analysis. The confusing terms “hazard”, hazardous situation”, “harm”, “causative event”, “ALARP”, “risk index”,  and “residual risk” will be explained. We will go step by step through the risk analysis process so that the process is clear. Examples of hazards and hazardous situations will be presented.  The additional hazards and hazardous situations attributable to ML will be discussed.  

Issues important to ML such as the Predetermined Change Control Plan (PCCP), data quality and bias will be discussed.

AREAS COVERED IN THE SESSION:

• Hazard analysis terms
• Hazard analysis process
• QC of datasets
• ML Algorithm updating
• Reference standard development
• Importance of  “explainability”
• Cybersecurity
  
  

WHO SHOULD ATTEND:

• Quality Assurance Departments
• Regulatory Affairs Departments
• Engineering Departments
• Software Professionals/Engineers
• Upper Management
• Marketing Departments
• Risk Management Professionals

Course Director: EDWIN WALDBUSSER

Edwin Waldbusser retired from industry after 30 years in management of development of medical device products and development of company Quality Systems. He was involved in the development of products such as IVD devices, kidney dialysis systems and inhalation devices. His QS experience includes, design control, risk analysis, CAPA, software validation, supplier qualification/ control and manufacturing/non-conforming product programs. He now consults in the area of quality systems for medical devices with emphasis on design control, software validation, risk analysis and human factors analysis. Ed has a B.S. Mechanical Engineering from NYU and a M.B.A from Drexel University. He is certified by Lloyds of London as an ISO 9000 Lead Auditor and is a member of the Thomson Reuters Expert Witness network. He has 5 issued patents.