Bridging the interpretability gap for medical artificial intelligence models using class-association manifold learning
Cet article propose une méthode d'apprentissage de variétés par association de classes (class-association manifold learning) pour combler le manque d'interprétabilité des modèles d'intelligence artificielle en médecine sans sacrifier leur précision
Explainability has increasingly become a core requirement for intelligent medical devices. Current medical artificial intelligence (AI) technologies suffer from the ‘interpretability gap’ despite tremendous efforts for enhancing explainability. Here we propose class-association manifold learning, a generative approach that enhances explainability of medical AI models. Our method efficiently decouples common decision-related patterns from individual backgrounds, enabling us to represent global class-associated knowledge in a low-dimensional mapping while preserving near-perfect diagnostic accuracy. The extracted knowledge is further used to enable AI-generated modifications on arbitrary samples and visualize differential diagnosis rules. Moreover, we develop a topology map to model the entire decision rule set, so that the logic underlying black-box models can be intuitively explicated by traversing the map and generating virtual contrastive examples. Extensive experiments show that our method not only achieves higher accuracy in explaining the behaviour of medical AI models but also helps with extracting medical-compliant knowledge that are unknown during model training, thus providing a potential means of assisting clinical rule and medical knowledge discovery with AI techniques.
Nature Biomedical Engineering , article en libre accès, 2026