arXiv AI By Fatema Ferdous Tamanna, K. M. Merajul Arefin, Md. Abdul Masud

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

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
4d ago

Freezing the Physiological Encoder: Explanation Stability Under Bounded Updates of an ICU Model

The paper introduces a bounded updating framework for ICU prediction models that freezes the physiological encoder while allowing updates only to the treatment pathway and fusion head. Experiments on 84,792 MIMIC-IV ICU stays across four temporal shifts show that selective adaptation yields more stable explanations—higher rank correlation, better top‑5 feature agreement, and improved retrieval stability—compared to full model adaptation. Predictive performance varies by outcome, but the results demonstrate that explanation stability is governed by the structural boundaries of allowed adaptation rather than merely by freezing components.

By Fatema Ferdous Tamanna, K. M. Merajul Arefin, Md. Abdul Masud
arXiv AI
Jul 22

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

arXiv:2607. 19020v1 Announce Type: cross 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.

By Fatema Ferdous Tamanna, K. M. Merajul Arefin, Md. Abdul Masud
arXiv Machine Learning
Aug 14

CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility

arXiv:2608. 12805v1 Announce Type: new Abstract: Access to clinical data is essential for developing reliable healthcare machine learning systems, but direct use of electronic health records is constrained by privacy regulation, institutional review, data-use agreements, and the risk of re-identification.

By Akanta Das, Al Amin Farhad, Mrinmoy Sarkar Anto, David Rehkopf, Ayin Vala, Tanmoy Sarkar Pias
arXiv Machine Learning
Jul 30

CalTwin: Towards Calibrated, Shift-Robust Medical World Models via Fisher-Information Regularisation

arXiv:2607. 26752v1 Announce Type: new Abstract: Medical world models aim to learn a latent state of patient or organ physiology and a transition function that forecasts how that state evolves under interventions, supporting downstream tasks from imaging-based diagnosis to digital-twin treatment planning.

By Behraj Khan, Shabir Ahmad, Syed Ahmad Chan Bukhari, Tahir Qasim Syed
arXiv AI
Jul 24

A Knowledge-Injection Framework for Zero-Shot Adaptation of LLMs to Delirium Prediction

arXiv:2607. 20453v1 Announce Type: cross Abstract: Large language models show promise for clinical prediction, but zero-shot performance on specialized tasks is limited by incomplete domain knowledge, especially for smaller locally deployable models.

By Jessica Sena, Shesadree Priyadarshani, Miguel Contreras, Bharat Gandhi, Scott Siegel, Subhash Nerella, Parisa Rashidi
arXiv AI
Sep 1

INTERVenE: Temporal-Abstraction-Interval Based Transformers for Short-Horizon Medical Event Prediction

INTERVenE introduces Transformer models that use a knowledge‑based temporal abstraction (KBTA) token stream of named clinical concepts instead of raw measurements, enabling per‑token attributions to resolve directly to clinical concepts. Two variants are offered: an auto‑regressive decoder that generates future abstraction trajectories with step‑wise risk readouts, and a bidirectional encoder that jointly predicts risk and time‑to‑event in a single pass. On 57,078 MIMIC‑IV admissions, the encoder variant outperforms neural baselines with a support‑weighted AUPRC of 0.672 and AUROC of 0.901, while the decoder provides complementary token‑level risk trajectories.

By Shahar Oded, Yuval Shahar