Language model-assisted label refinement for accurate sepsis detection from electronic health records
· 2026-09-09 · 原文
DOI：10.64898/2026.09.08.26362428v1?rss=1
Sepsis is a leading cause of hospital mortality, yet timely recognition is hampered by nonspecific presentations and label noise in code-based case definitions. We developed STRIDE, a machine-learning framework for sepsis detection across seven hospitals with a scalable approach to label quality. We refined a pragmatic operational definition using a large language model applied to discharge summaries, with an independent physician-adjudicated cohort as the gold standard. We compared 8-, 24-, and 48-hour observation windows and benchmarked against SOFA, SIRS, and Epic, assessing calibration and discrimination. Among 356,610 encounters, the 8-hour model achieved an AUC of 0.960 in derivation and 0.878 in physician-adjudicated validation, matching or outperforming longer-window models. STRIDE
讲义
讲义·推断 依据「原文」自动生成的结构化摘要（推断），非原文表述；以原文为准。
1. 人话版
Sepsis is a leading cause of hospital mortality, yet timely recognition is hampered by nonspecific presentations and label noise in code-based case definitions.
We developed STRIDE, a machine-learning framework for sepsis detection across seven hospitals with a scalable approach to label quality.
2. 领域脉络
We refined a pragmatic operational definition using a large language model applied to discharge summaries, with an independent physician-adjudicated cohort as the gold standard.
3. 机制拆解
摘要未展开方法细节——精读时重点看方法/模型部分。
4. 证据与数字
We compared 8-, 24-, and 48-hour observation windows and benchmarked against SOFA, SIRS, and Epic, assessing calibration and discrimination.
Among 356,610 encounters, the 8-hour model achieved an AUC of 0.960 in derivation and 0.878 in physician-adjudicated validation, matching or outperforming longer-window models.
5. 反例与边界
摘要未声明局限与反例——这是需要警惕的信号，精读时先问边界。
6. 跨领域连接与意外收获
思考本文机制能否迁移到你正在跟进的问题。
7. 可复用方法
把本文机制与你手头项目对照，找一个两周内能验证的最小实验。
8. 术语表
精读时把不熟的术语记入此处，作为下次回忆的锚点。