The competence cluster Metrology for Artificial intelligence in Medicine (M4AIM) is a QI-Digital pilot project. We are developing solutions for effective quality assurance for Artificial Intelligence (AI) methods in medicine. These meet the technological challenge of sound testing of AI systems and fulfill the special requirements of health-critical applications.

The use of Artificial Intelligence (AI) methods in medicine promises more efficient diagnosis and individually adapted therapies. However, due to potentially direct health effects on the patient, such AI systems require close monitoring by the quality infrastructure throughout their life cycle.

Explainability

AI system behavior must be explainable to ensure that it makes its predictions based on relevant information in the data.

Robustness

In medical technology, robustness and generalisability of AI methods play a major role, i.e., the case where input data deviates from the data used to train the method. This is especially true when certain features are not reflected in the training data.

Uncertainty

Along with the AI’s predictions, its uncertainty must also be available. Inherent limitations of the AI system and data quality application contexts deviating from training and test conditions must be taken into account.

Data Quality

The quality of AI methods is largely based on the quality of its training data. Ensuring this requires careful selection and assessment of the data and its enrichment with semantic information and other metadata.