Machine learning-enabled medical devices (MLMDs) can learn from real-world use and, in some cases, improve performance over time. Yet changes to a model or algorithm may be substantive or significant, requiring regulatory oversight such as additional premarket review — which may not always align with the rapid pace of MLMD development.
In October 2023, the MHRA, U.S. FDA, and Health Canada jointly identified five guiding principles for predetermined change control plans (PCCPs). These principles draw upon the overarching Good Machine Learning Practice (GMLP) guiding principles — in particular GMLP Principle 10, which states that deployed models are monitored for performance and re-training risks are managed.
If you have not yet studied the ten GMLP principles, see the IMDRF GMLP learning path on this site for the full framework. This article focuses on PCCPs specifically.
What is a PCCP?
A predetermined change control plan (PCCP) is a plan, proposed by a manufacturer, that specifies:
- certain planned modifications to a device
- the protocol for implementing and controlling those modifications
- the assessment of impacts from modifications
PCCPs can help align regulatory processes with ongoing change management in MLMDs, manage risks through monitoring and maintenance, and uphold high regulatory standards for safety and effectiveness. PCCPs may be developed and implemented differently across regulatory jurisdictions.
The five guiding principles
1. Focused and bounded
A PCCP describes specific changes that a manufacturer intends to implement. Such changes are limited to modifications within the intended use or intended purpose of the original MLMD. This characterization includes:
- the extent of planned changes and scope of the MLMD with changes implemented
- plans in place to safely modify the device within the bounds of the PCCP, including methods for verifying and validating the changes and mechanisms to detect and revert or stop implementation of a change that fails to meet specified performance criteria
- the impacts of the planned changes
2. Risk based
The value and reliability of a PCCP is strengthened when the intent, design, and implementation are driven by a risk-based approach that adheres to the principles of risk management. This risk-informed perspective is relevant:
- throughout the total product lifecycle (TPLC), from inception through implementation and use
- to ensure that individual and cumulative changes remain appropriate over time for the device and its use environment
3. Evidence based
Evidence generated throughout the TPLC is important to:
- ensure the ongoing safety and effectiveness of the device with a PCCP
- demonstrate that the benefits outweigh the associated risks
- establish that risks are adequately managed and controlled
Considerations include scientifically and clinically justified methods and metrics, proportionate to risk, and specified methods to generate evidence demonstrating benefits and risks before and after PCCP changes are implemented.
4. Transparent
For PCCPs, best practice is to provide clear and appropriate information and detailed plans for ongoing transparency to users and other stakeholders. This helps ensure stakeholders stay aware of the device's performance and use before and after changes. Consider, for example:
- characterization of data used in development and modifications, demonstrated to reflect the intended population
- comprehensive testing for planned changes
- characterization of the device before and after implementation of changes
- monitoring, detection, and response to deviations in device performance
This principle connects directly to the transparency guiding principles covered in the next article and to GMLP Principle 9 (clear, essential information for users).
5. Total product lifecycle (TPLC) perspective
Creating and using a PCCP from a TPLC perspective can:
- elevate the quality and integrity of a PCCP by continually considering the perspectives of all stakeholders as well as risk management practices throughout the TPLC
- use and support existing regulatory, quality, and risk management measures throughout the TPLC to ensure device safety by monitoring, reporting, and responding to safety concerns
This aligns with GMLP Principle 10 — monitoring deployed models and managing re-training risks across the lifecycle.
Link to MHRA change programme
Within the MHRA change programme, WP 4-04 proposes secondary legislation for PCCPs for SaMD, and WP 11-03 reviews PCCP suitability for AIaMD — ensuring plans address poor interpretability, data bias, and rapid complex change events.
Practical takeaway for Hong Kong clinicians
When a vendor describes "planned updates" or "continuous learning," ask whether a PCCP exists that is focused and bounded, risk- and evidence-based, transparent to users, and lifecycle-managed. Without such documentation, post-deployment changes may outpace your institution's ability to assess safety and effectiveness.