Overview:
AI/ ML will revolutionize medicine by making diagnosis and treatment more accessible and more effective.
FDA has regulated medical device software by means of regulation and guidance’s for years, however, AI/ML programs fall outside the scope of these regulations and guidance’s. This happens because FDA approves the final, validated version of the software. The objective of AI/ML is to learn and update following deployment using real world data to improve performance. Thus the deployed version of the software is no longer the validated approved version. Also, according to current regulation, significant changes require a new 510(k) submission. The objective of AI/ML is to create significant change post release. A new submission for each update would be impractical.
FDA, in January 2025, released a draft Guidance explaining the documentation required to obtain clearance/ approval for a ML product. This training will explain ML terminology and the ML development process, address the inadequacy of the current regulations, and explain in detail the procedures described in the draft Guidance. The new approach, a Predetermined Change Control Program (PCCP) will be explained.
This webinar is not a programming course but will explain the present and future regulatory requirements for AI/ML. Attendees will receive a multipage outline and checklist.
Why you should Attend:
It has not been clear how to get AI/ML programs approved. The regulatory requirements, up to now, don’t control AI/ML adequately.
We will discuss the approaches FDA will take for regulation as described in the 2025 draft Guidance. Necessary submission documentation will be explained including the new approach of a PCCP.
Areas Covered in the Session:
- FDA Discussion Paper on device AI/ML and Action Plan
- Database management
- QC of datasets
- Preliminary Change Control Plan (PCCP)
- Reference standard development
- Standalone performance testing
- Clinical performance testing
- Emphasis on "explainability"
- Cybersecurity
Who Will Benefit:
- Software Engineers
- Engineers
- Regulatory Personnel
- Quality Assurance Personnel
- Marketing
- Management
