1. Multidisciplinary expertise is leveraged throughout the total product life cycle. In-depth understanding of a model’s intended integration into clinical workflow, and the desired benefits and associated patient risks, can help ensure that machine learning-enabled medical devices are safe and effective and address clinically meaningful needs over the life cycle of the device.
2. Good software engineering and security practices are implemented. These practices include methodical risk management and design process that can appropriately capture and communicate design, implementation and risk management decisions and rationale as well as ensure data authenticity and integrity.
3. Clinical study participants and datasets are representative of the intended patient population. Data collection protocols should ensure that the relevant characteristics of the intended patient population … and measurement inputs are sufficiently represented in a sample of adequate size in the clinical study and training and test datasets so that results can be reasonably generalized to the population of interest.
4. Training datasets are independent of test sets. All potential sources of dependence, including patient, data acquisition and site factors are considered and addressed to assure independence.
5. Selected reference datasets are based upon best available methods. If available, accepted reference datasets in model development and testing that promote and demonstrate model robustness and generalizability across the intended patient population are used.
6. Model design is tailored to the available data and reflects the intended use of the device. Considerations include the impact of both global and local performance and uncertainty/variability in the device inputs, outputs, intended patient populations and clinical use conditions.
7. Focus is placed on the performance of the human-AI team. Where the model has a “human in the loop,” human factors considerations and the human interpretability of the model outputs are addressed with emphasis on the performance of the Human-AI team, rather than just the performance of the model in isolation.
8. Testing demonstrates device performance during clinically relevant conditions. Considerations include the intended patient population, important subgroups, clinical environment and use by the Human-AI team, measurement inputs and potential confounding factors.
9. Users are provided clear, essential information. Users are also made aware of device modifications and updates from real-world performance monitoring, the basis for decision-making when available, and a means to communicate product concerns to the developer.
10. Deployed models are monitored for performance and retraining risks are managed. [W]hen models are periodically or continually trained after deployment, there are appropriate controls in place to manage risks of overfitting, unintended bias, or degradation of the model … that may impact the safety and performance of the model as it is used by the Human-AI team.