[论文] Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Super...

论文概要

研究领域: ML 作者: Kevin Zhu, Ryan Zhang, Baraa Abed, Tilendra Choudhary, Malvern Madondo, Mehak Arora, Yixuan Yang, Alasdair Gent, Aditya Nagori, Omer T. Inan, Krista L. Haines, Patrick Georgoff, Suresh M. Agarwal, Vijay Krishnamoorthy, Tetsu Ohnuma, Mihai V. Podgoreanu, Michael R. Pinsky, Gilles Clermont, Craig M. Coopersmith, Craig S. Jabaley, Rishikesan Kamaleswaran 发布时间: 2026-08-27 arXiv: 2608.27421

中文摘要

目前使用的脓毒症严重度指数依赖几十年前建立的固定变量和权重，这些被粗略离散化并校准到不再反映当代重症监护的队列。我们进行了一项回顾性双队列研究，纳入马萨诸塞州和乔治亚州两个医院系统共29,116和7,691名符合Sepsis-3标准的成人患者。我们使用72小时治疗窗口内的43个常规记录变量开发了脓毒症指数。与以往研究不同，我们使用死亡率作为治疗级别排序信号而非每个状态的目标，允许信用在非均匀时间步上重新分配。在该排序方案下，非存活者在所有基线SOFA-2分层中比存活者高1.19-1.64分（0-10分制），在乳酸、平均动脉压和肌酐分层中也有类似结果。患者内部指数变化与乳酸变化相关（Spearman rho = 0.39）。跨机构一致性为同机构相关性的70-77%。

原文摘要

Currently used sepsis severity indices rely on fixed variables and weights established decades ago, which are coarsely discretized and calibrated to a cohort that no longer reflects contemporary critical care. No alternative learned directly from patient trajectories is in routine use. We conducted a retrospective two-cohort study on a total of 29,116 and 7,691 adult patients meeting Sepsis-3 criteria from two hospital systems in Massachusetts and Georgie, respectively. We developed a sepsis index using 43 routinely charted variables over a 72-hour treatment window. Unlike previous studies, we use mortality as a treatment-level ranking signal rather than a per-state target, allowing credit to be redistributed non-uniformly across timesteps. Evaluation was done on a permanent 20% test holdo...

#论文 #arXiv #ML #小凯