FDA’s Approach to SaMD Modifications

by | May 10, 2019 | AI, FDA, Medical Devices, Quality Systems, Regulatory

As part of our blog series on Artificial Intelligence and Machine Learning Medical Devices, this time we will discuss the FDA’s take on how modifications made to the software after its initial review will be addressed within the SaMD pre-specifications and Algorithm Change Protocol submitted by the manufacturer to the FDA as part of the predetermined change control plan. 

For reference, you can read the following previous blogs on AI/ML devices: 

ARTIFICIAL INTELLIGENCE & MACHINE LEARNING TECHNOLOGIES 

QUALITY SYSTEMS AND GOOD MACHINE LEARNING PRACTICES 

INITIAL PREMARKET ASSURANCE OF SAFETY AND EFFECTIVENESS FOR AI/ML MEDICAL DEVICES 

After a SaMD receives market authorization from the FDA, any modifications to its software would have to go through a pre-market review as outlined in the software modification guidance- Deciding when to submit a 510(k) for a software change to an existing device. 

Due to the continuous learning and adaptive nature of AI/ML devices, these capabilities would be considered modifications. The FDA’s new guidance allows for a riskbased approach to tackle such modifications without having companies worry about submitting a pre-market submission every time the device modifies its algorithm based on realworld data. 

A SaMD device manufacturer or developer is expected to evaluate the modifications based on the risks to the patients as outlined in the software modifications guidance, perform a risk assessment and perform appropriate risk mitigation activities. 

The current software guidance results in either:  

  • A new 510(k) for the proposed modification 
  • Documentation of the modification in the risk management file 

According to the FDA’s new guidance, if the AI/ML developer has a SaMD pre-specifications and an Algorithm Change control Plan approved as part of the predetermined change control plan, and if the changes or modifications to the device are within the bounds of the SPS and the ACP, then the manufacturer can simply document the change within the change history/change control program devised within their quality system with appropriate records.i 

In cases where it is anticipated that the modifications may change the intended use, beyond the intended use for which the SaMD was previously authorized, FDA will conduct a ‘focused review’ of the SPS and ACP that includes the said intended use modification in its plan. 

FDA suggests that manufacturers engage with them on SPS and ACP for a particular SaMD. Some options include:1 

  • Contact the appropriate review division of the FDA to determine if the modification fits the current SPS and ACP. 
  • Submit a pre-sub for a discussion with the FDA on the modification. 
  • Submit a premarket submission or application of the modification to the SPS and ACP. 

FDA is accepting feedback on this proposed guidance on the public docket. FDA seeks specific feedback on the following items:1 

How should FDA handle changes outside of the approved SPS and ACP? 

How should FDA go about conducting the proposed focused review of the SPS and the ACP and what content should it include? 

You can submit your suggestions or comments on FDA’s Proposed Regulatory Framework for Modifications to Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) – Discussion Paper and Request for Feedback using the following link: https://www.regulations.gov/comment?D=FDA-2019-N-1185-0001 


For any other questions that you may have about the proposed regulatory framework, please contact us at 248-987-4497 or info@emmainternational.com 

Nikita Angane

Nikita Angane

Solutions Delivery Specialist - Ms. Angane is a Bioengineering graduate with experience in medical device commercialization, product development, quality system compliance and regulatory affairs. Her portfolio includes working on medical devices, combination products, and pharmaceuticals. As a Solutions Delivery Specialist at EMMA International, she offers her expertise to help our clients achieve an effective and sustainable quality system, and develop regulatory strategies for market access and compliance of new products in the US and international markets. Ms. Angane earned a Bachelor of Engineering in Biomedical Engineering from the University of Mumbai, India and an M.S. in Bioengineering from University of Illinois at Chicago.

More Resources

FDA Adverse Event Reporting 

FDA Adverse Event Reporting 

When reporting an Adverse Event to the Food and Drug Administration (FDA) the best method is to utilize the FDA Adverse Event Reporting System (FAERS). FAERS is a database that contains adverse event reports, product quality complaints that led to an adverse event, and medication error reports1. All FAERS reports are easily accessible to the public. 
De Novo Classification

De Novo Classification

A device can be registered for the De Novo pathway if there is evidence of the safety and effectiveness of the device and there is not a previously legally marketed predicate device1. When determining if your device can go through the De Novo process there are two pathways available to determine the device classification.
Abbreviated 510k submission

Abbreviated 510k submission

There are three types of 510K, Premarket Notifications, which can be submitted to the Food and Drug Administration (FDA) traditional, abbreviated, and special. Abbreviated and Special 510K submissions can be utilized when the submissions meet the certain factors presented by the FDA. When submitting an abbreviated 510K the submission must include the elements that are identified in 21CFR 807.87 for the information required in a premarket notification submission.

Ready to learn more about working with us?

Pin It on Pinterest

Share This