Support Centre

You have out of 5 free articles left for the month

Signup for a trial to access unlimited content.

Start Trial

Continue reading on DataGuidance with:

Free Member

Limited Articles

Create an account to continue accessing select articles, resources, and guidance notes.

Free Trial

Unlimited Access

Start your free trial to access unlimited articles, resources, guidance notes, and workspaces.

Canada: Health Canada releases draft guidance for machine learning-enabled medical devices

On August 30, 2023, Health Canada released draft pre-market guidance for machine learning-enabled medical devices. Health Canada explained that the draft guidance provides supporting information to consider when manufacturers are demonstrating the safety and effectiveness of a machine learning-enabled medical device (MLMD). The draft guidance identifies the MLMD lifecycle as the following, and outlines best practices for the same:

  • design;
  • risk management;
  • data selection and management;
  • development and training;
  • testing and evaluation;
  • clinical validation;
  • transparency; and
  • post-market performance monitoring.

In regard to risk management, the draft guidance notes that manufacturers should conduct the necessary risk management and consider providing descriptions of:

  • the risks identified for the MLMD and the associated risk controls in place to eliminate or reduce those risks;
  • the technique used to perform the initial and ongoing risk assessment and the system used for risk level categorization and acceptability; and
  • the results of the risk assessment.

Furthermore, on data selection and management, the draft guidance states that, when describing the selection and management of data for an MLMD, manufacturers should consider providing the following elements:

  • descriptions of the training, tuning, and test datasets used to develop and evaluate the MLMD system;
  • data inclusion and exclusion criteria and a justification for removing any data;
  • descriptions of techniques used to address data imbalances and a justification;
  • a description of how data integrity was maintained during curation and how data quality and accuracy were ensured; and
  • an explanation of how bias in the dataset was controlled during development.

You can read the press release and the draft guidance here.