arXiv：cs.LG· Yikun Ou, Wei Li·· 4 小时前AI 评分31
SepsisLens：保结构序列建模实现可分解的脓毒症早期预警
SepsisLens: Structure-Preserving Sequence Modelling for Decomposable Early Sepsis Warning
AI 导读
SepsisLens 通过保留变量索引的时间状态直到风险合成，实现可分解的脓毒症早期预警。模型用观测感知表示编码各变量的动态与测量历史，并以 StructuredRiskHead 从变量级和器官级组件合成多时间跨度风险。在三个公开 ICU 队列与一个私立医院队列上均取得较强区分度，在 MIMIC-IV 上同等事件召回率下警报负担更低。
正文
Abstract: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.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.08046 [cs.LG] |
| (or arXiv:2610.08046v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.08046 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yikun Ou [view email]
[v1]
Tue, 6 Oct 2026 09:45:34 UTC (2,080 KB)
来源：arXiv：cs.LG · arxiv.org