Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating

Sicherheitsmeldung mit Schweregrad noch nicht bewertet. Technische Details im Tab „Originaltext“; empfohlene Schritte in der Checkliste.

Originaltext der Quelle (nicht übersetzt) – die deutsche Zusammenfassung findest du im Tab „Kurzfassung".

arXiv:2607.19020v2 Announce Type: replace-cross Abstract: Clinical decision support degrades as treatment protocols evolve, but the obstacle to updating a deployed model is governance as much as accuracy: once retraining touches every parameter, no one can say afterwards where the update acted. We propose a two-stream architecture separating physiological (LSTM) from treatment (MLP) representations. On a dual distributional/accuracy trigger, updates are confined to the treatment stream and fusion head, leaving the physiological encoder bitwise identical to the source model. Audit logs record which treatment features the update relied on, and evidence retrieval couples per-instance PubMed queries to the frozen encoder. We evaluate on 84,792 MIMIC-IV stays split by three-year era. The constraint proved close to free: selective adaptation cost nothing in aggregate discrimination against unconstrained full adaptation (mean AUROC 0.9316 vs. 0.9249; ahead on vasopressor, marginally behind on intubation) while being six-fold more stable across adaptation seeds. Run sequentially over four era transitions, the detector located the 2020 boundary rather than assuming it, firing once and on the distributional leg alone. Confining updates to named architectural blocks therefore costs little discrimination and bounds each update's scope by construction rather than by inference after the fact. Attribution-conditioned retrieval, by contrast, tracked the source model's without reproducing it: a guarantee over weights is not a guarantee over attributions, and this design makes the former …

Vollständiger Originalartikel ↗

• Betroffenheit im eigenen Stack prüfen: Versionen/Komponenten abgleichen.
• Originalquelle / Hersteller-Advisory lesen: https://arxiv.org/abs/2607.19020
• Verfügbaren Patch oder Workaround einspielen und dokumentieren.