Biological Amnesia in ICU Time-Series Prediction: A Drift-Adaptive Two-Stream Architecture with Temporal Retrieval

תקציר מקורי באנגליתarXiv:2607.19020v1 Announce Type: new Abstract: Background: Clinical decision support systems degrade silently as treatment protocols evolve, yet standard adaptation methods treat models as monolithic blocks, unable to distinguish stable patient physiology from shifting institutional practice. Methods: We propose an adaptive clinical intelligence architecture for ICU intervention prediction that structurally decouples physiological from treatment representations, confining parameter updates to the treatment stream upon a dual distributional and accuracy trigger. Automated audit logs record which treatment features drove each adaptation event and how their importance shifted. At inference, an attribution-driven Temporal RAG module grounds each prediction in patient-specific, era-matched Pub