Who decides when medical AI may be updated?
Medical AI can improve with new patient data, but every update must be checked first. In the journal npj Digital Medicine, researchers at Karolinska Institutet present AEGIS, a framework for governing and monitoring medical AI models on the market.
Patients, equipment, and ways of working change, and a model trained on older data can gradually get worse without anyone noticing.
Regulations in the US and the EU state what must be done when medical AI is monitored and updated, but not in detail how. AEGIS defines and demonstrates one way to do this in practice.
Two questions at every update
AEGIS answers two questions: Can the new model be put into use? Does the model already in use need a closer look? The answers follow rules in a change plan approved before the device reached the market.
“Most AI-based medical devices are locked after approval and do not learn from new data. Every improvement needs retraining and validation,” says Farhad Abtahi, head of the SMAILE core facility at the Department of Clinical Science, Intervention and Technology, and corresponding author of the study.
Two demonstrations: sepsis and brain tumours
The researchers demonstrated AEGIS with two models: one that identifies sepsis cases in past intensive care data and one that outlines brain tumours on MRI scans.
“The demonstrations examine the decision rules, but do not show how safe or effective an AI model is in healthcare. Each clinical application requires its own validation and regulatory assessment,” says Farhad Abtahi.
AEGIS currently detects changes in incoming data, but not yet directly whether the relationship between data and outcomes changes. The next step is to test the framework in real-world use with clinical partners and authorities.
The study was funded by SMAILE at KI and EIT Health (the Moodmon project). The framework was partly inspired by a use case from Britenet Med. The researchers report no conflicts of interest.
Publication
"AEGIS: an operational infrastructure for post-market governance of adaptive medical AI under US and EU regulatory frameworks," Afdideh F, Astaraki M, Seoane F, Abtahi F. npj Digital Medicine, online 13 October 2026, doi: 10.1038/s41746-026-03290-1.