cs.LGNov 10, 2026

SepsisFlow: an event-stream foundation model for continuous risk warning and trajectory modelling in ICU sepsis

Authors: Yawen Zhang, Wanzhe Xu, Zhenhua Zhang, Jinyu Wu, Yizhou Zhuang, Yitao Yang, Kenta Nakai

Organizations: Department of Computational Biology and Medical Science, The University of Tokyo, Kashiwa, Japan · National and Local United Engineering Lab of Druggability and New Drugs Evaluation, Guangdong Provincial Key Laboratory of New Drug Design and Evaluation, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou 510006, China · Human Genome Center, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan

Abstract

Sepsis is a leading cause of ICU death with heterogeneous onset and course, yet most warning models predict only whether sepsis will occur, leaving clinicians uncertain of its onset context and early trajectory once an alarm sounds. To answer these questions on one hourly clock from ICU admission, we built SepsisFlow: before onset, it combines a Mamba model pretrained on 2.57 million EHRs with about 1,700 hourly features in gradient-boosted trees to predict 6/12/24-h risk; at onset, it fuses Mamba and tabular encoders via a gated network into continuous patient states defining onset contexts; after onset, it encodes 72-h organ-support and physiological trajectories via an attention bidirectional recurrent network into early courses. For pre-onset warning in MIMIC-IV, SepsisFlow detected more cases than NEWS2, qSOFA, and SIRS at equal alarms, gaining about 8 cases per 100 from hourly updating, while outperforming 16 retrained algorithms and maintaining risk ranking in eICU. At onset, its contexts separated 2% cardiovascular-ICU from 15%-17% other 28-day mortality, and within each context after onset, persistent support carried fivefold higher mortality than de-escalation. SepsisFlow establishes a foundation-model paradigm for continuous risk and trajectory stratification in critical care.

Explore similar work

CardsList
  1. SepsisLens: Structure-Preserving Sequence Modelling for Decomposable Early Sepsis Warning

    Oct 6, 2026Yikun Ou, Wei LiSepsis PredictionInterpretable ML

  2. Clinically Interpretable Sepsis Early Warning via LLM-Guided Simulation of Temporal Physiological Dynamics

    Apr 22, 2026Weizhi Nie, Zhen Qu, Weijie Wang +4Interpretable MLLLM-Based Time Series Forecasting

  3. A Framework for Early Sepsis Prediction via Self-Supervised (JEPA) and Federated Representation Learning

    Jul 18, 2026Umair bin Mansoor, Munaf Rashid, Roomi NaqviSepsis PredictionSelf-Supervised Pre-Training