Blog
The U.S. Food and Drug Administration (FDA), Health Canada, and the United Kingdom’s Medicines and Healthcare products Regulatory Agency (MHRA) have recently identified 10 guiding principles for the development of Good Machine Learning Practice (GMLP).
These guiding software development principles should be used to:
- Adopt good practices that have been proven in other sectors
- Tailor practices from other sectors so they are applicable to medical technology and the health care sector
- Create new practices specific for medical technology and the health care sector
Need help putting these principles into action? Talk to our Experts →
What is Artificial intelligence and FDA machine learning (AI/ML)?
Artificial intelligence and machine learning use software algorithms to learn from real-world use of the device to help improve the product’s performance.
Good Machine Learning Practice Guiding Principles
- Multi-Disciplinary Expertise Is Leveraged Throughout the Total Product Lifecycle. Helps ensure that ML-enabled medical devices are safe and effective and address clinically meaningful needs over the lifecycle of the device.
- Good Software Engineering and Security Practices Are Implemented. Implementation with attention to the “fundamentals”: good software engineering practices, data quality assurance, data management, and robust cybersecurity practices.
- Clinical Study Participants and Data Sets Are Representative of the Intended Patient Population. Manage bias, promote appropriate and generalizable performance across the intended patient population, assess usability, and identify circumstances where the model may underperform.
- Training Data Sets Are Independent of Test Sets. Training and test datasets are selected and maintained to be appropriately independent of one another.
- Selected Reference Datasets Are Based Upon Best Available Methods. Using the best available methods for developing a reference dataset ensures that clinically relevant and well-characterized data is collected and the limitations of the reference are understood.
- Design Is Tailored to the Available Data and Reflects the Intended Use of the Device. Design is suited to the available data and supports the active mitigation of known risks, like overfitting, performance degradation, and security risks.
- Focus Is Placed on the Performance of the Human-AI Team. Human factors considerations and human interpretability are addressed with emphasis on the performance of the Human-AI team.
- Testing Demonstrates Device Performance during Clinically Relevant Conditions. Developed and executed statistically sound test plans to generate clinically relevant device performance information independently of the training data set.
- Users Are Provided Clear, Essential Information. Users are provided ready access to clear, contextually relevant information that is appropriate for the intended audience.
- Deployed Models Are Monitored for Performance and Re-training Risks are Managed. Models have the capability to be monitored in “real world” use with a focus on maintained or improved safety and performance, as well as periodic training after deployment.
