重症监护室时间序列预测中的生物失忆：一种具有时间检索的漂移自适应双流架构
Freezing the Physiological Encoder: Explanation Stability Under Bounded Updates of an ICU Model
- Patuakhali Science and Technology University（帕图阿卡利科学技术大学）
- University of Dhaka（达卡大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究重症监护室时间序列预测中临床决策支持系统退化问题，提出自适应临床智能架构，通过解耦生理与治疗表征、限制参数更新等实现漂移自适应，实验验证其有效性，为高风险临床环境中部署自适应模型提供模板。
AI中文摘要：
背景：随着治疗方案的演变，临床决策支持系统会悄然退化，但标准的适应方法将模型视为整体模块，无法区分稳定的患者生理特征和不断变化的机构实践。方法：我们提出了一种用于重症监护室干预预测的自适应临床智能架构，该架构在结构上使生理表征与治疗表征解耦，在双重分布和准确性触发时将参数更新限制在治疗流中。自动审计日志记录哪些治疗特征驱动了每个适应事件及其重要性如何变化。在推理时，一个归因驱动的时间检索模块将每个预测基于特定患者、与时代匹配的PubMed证据，这些证据锚定在患者的主要生理特征上。实验使用了84,792例MIMIC-IV住院病例（2008 - 2022年），采用严格的时间顺序划分。结果：漂移完全局限于治疗流，验证了结构先验。选择性适应在血管升压药和脓毒症休克的辨别及校准方面优于静态源模型。一个完全重新训练的基线在总体辨别上略高，但错过了框架正确识别的26例脓毒症休克病例，且反向没有误判；框架保持了与适应前源模型检索的一致性，但重新训练的基线中一致性大幅下降。结论：在保留稳定生理表征的同时，对漂移组件的适应进行结构约束，使临床人工智能能够随着实践发展，而不会扭曲所学的患者生物学特征。这种架构为在高风险临床环境中可管理、可解释地部署自适应模型提供了一个模板。
英文摘要：
Clinical prediction models deployed in intensive care units may require model updating when data distributions shift, yet unconstrained adaptation can alter model behavior in ways that are difficult to audit. We propose a structurally bounded updating framework that separates physiological dynamics from treatment context and restricts post-drift adaptation to the treatment pathway and fusion head, while leaving the physiological encoder unchanged. Rather than assuming that physiological information remains stable, we investigate how this predefined update boundary affects model explanations after distribution shift. Using 84,792 MIMIC-IV ICU stays across four temporal transitions, we compare selective adaptation with full model adaptation under treatment-side distributional and performance drift. Selective adaptation produces more stable physiological attribution ordering than full adaptation, with rank correlation of 0.875 versus 0.812 and top-5 feature agreement of 0.674 versus 0.552, while retrieval stability also improves (Jaccard similarity 0.614 versus 0.517). Importantly, freezing does not make explanations globally invariant; instead, it constrains where model changes can occur, redirecting explanatory changes toward the treatment pathway and fusion component. Predictive performance remains task-dependent, with selective adaptation outperforming full adaptation for some outcomes while showing a slight disadvantage for intubation prediction. These results suggest that explanation behavior after model updating is influenced not simply by whether a component is frozen, but by the structural boundary defining which components are permitted to absorb adaptation. Such predefined boundaries provide a practical basis for auditable and controlled updating of clinical prediction models under distribution shift.
