SepsisLens：面向可分解早期脓毒症预警的结构保持序列建模

中文摘要 AI 辅助

从ICU记录中进行早期脓毒症预警可被视作一个结构保持的预测问题。模型需要在检测到来自不规则测量的恶化情况的同时，保持每个警报与支持它的生理信号相关联。许多时序模型将临床变量融合为患者级别的表示，支持标量风险预测，但削弱了临床分解所需的结构。我们提出了SepsisLens，它在风险组合之前保留变量索引的时序状态。观测感知表示编码每个变量的动态和测量历史，而共享的时序编码器对每条轨迹进行建模，而不折叠变量轴。StructuredRiskHead从显式的变量级和器官级组件中组合多时间范围的风险。我们在三个公共ICU队列和一个私立医院队列上，在共同的发作前协议下评估了SepsisLens。SepsisLens在全部四个队列上实现了强判别能力，并在MIMIC-IV上以匹配的事件召回率降低了警报负担。结构消融支持了该设计，而输入侧掩蔽表明排序后的组件反映了对预测影响更大的变量。

英文摘要

Early sepsis warning from ICU records can be cast as a structure-preserving prediction problem. A model needs to detect deterioration from irregular measurements while keeping each alert connected to the physiological signals that support it. Many temporal models fuse clinical variables into a patient-level representation, supporting scalar risk prediction but weakening the structure needed for clinical decomposition. We present SepsisLens, which preserves variable-indexed temporal states until risk composition. Observation-aware representations encode each variable's dynamics and measurement history, while a shared temporal encoder models each trajectory without collapsing the variable axis. The StructuredRiskHead composes multi-horizon risk from explicit variable-level and organ-level components. We evaluate SepsisLens on three public ICU cohorts and one private-hospital cohort under a common pre-onset protocol. SepsisLens achieves strong discrimination on all four cohorts and lower alert burden at matched event recall on MIMIC-IV. Structural ablations support the design, while input-side masking shows that the ranked components reflect variables with greater influence on prediction.

发表机构

• School of Computer Science, University of Sydney（悉尼大学计算机科学学院）

机构由 AI 辅助整理，请以论文原文为准。