The U.S. Food and Drug Administration (FDAHealth Canada and the UK Medicines and Healthcare products Regulatory Agency (MHRA) identified the principles for good machine learning practices.
The FDA, Health Canada and the MHRA jointly identified ten guiding principles for developing good practices in machine learning (GMLP). The main idea is to promote the use of safe, regulated, and quality medical devices that utilize Artificial Intelligence (AI) and machine learning.
“With artificial intelligence and the machine learning Given the rapid progress, our three regulatory agencies, working together, see a global opportunity to help foster good practices in machine learning ”By providing guiding principles that we believe will support the development and maturation of good machine learning practices,” explained Bakul Patel, director of the Center of Excellence of Digital Health of the FDA.
He also explained that the guiding principles developed in collaboration with health authorities in Canada and the United Kingdom will provide crucial support to developers of devices based on machine learning that “have the potential to significantly improve the quality of patient care and transform healthcare,” Patel emphasized.
The “Guide to Good Practices of machine learning "Guiding principles for the development of medical devices" was published on October 27, 2021. In summary, the ten principles are as follows:
- Multidisciplinary expertise is leveraged throughout the product lifecycle
- Good software engineering and security practices are implemented
- The clinical study participants and datasets are representative of the intended patient population.
- The sets of training data They are independent of the test sets
- The selected reference datasets are based on the best available methods
- The model design is adapted to the available data and reflects the intended use of the product.
- The focus is on the performance of the human team of AI
- The tests demonstrate the device's performance under clinically relevant conditions
- Users receive clear and essential information: Users have easy access to clear and contextually relevant information that is appropriate for the intended audience (such as healthcare providers or patients).
- Deployed models are monitored for performance and retraining risks are managed
You can consult the complete guide at the following link: https://www.gov.uk/government/publications/good-machine-learning-practice-for-medical-device-development-guiding-principles/good-machine-learning-practice-for-medical-device-development-guiding-principles
AI MEAS
FDA
UK GOV
