用分层Transformer模型精准预测危重症患者血糖，提升低血糖预警能力。
Enhancing Glucose Level Prediction of ICU Patients through Hierarchical Modeling of Irregular Time-Series
- 采用分层Transformer架构，自动融合检验、用药、生命体征等多源不规则数据。
- 在eICU数据库上，对低血糖的检出率提升7.2个百分点，显著优于现有方法。
- 模型可灵活扩展新数据源，适合临床决策支持系统部署。
准确预测重症监护室（ICU）患者的血糖水平至关重要，因为低血糖（BG < 70 mg/dL）和高血糖（BG > 180 mg/dL）均与发病率和死亡率升高相关。本研究提出一种基于机器学习的验证性框架——多源不规则时间序列Transformer（MITST），用于预测ICU患者血糖水平。与依赖人工特征工程或仅使用有限电子健康记录（EHR）数据的方法不同，MITST无需预定义聚合方式，即可整合实验室检查结果、药物信息和生命体征等多种临床数据。模型采用分层Transformer架构，捕捉单一时序点内特征间交互、跨时序的时间依赖性以及多数据源间的语义关系。在包含200,859例住院记录的eICU数据库上评估，相较于最先进的随机森林基线，MITST在平均AUROC上提升1.7个百分点（p < 0.001），AUPRC提升1.8个百分点。尤为重要的是，针对罕见但致命的低血糖事件，其敏感性提高7.2个百分点，可能使数百名患者提前获救。MITST结构灵活，可无缝集成新数据源而无需重训练，增强其在临床决策支持中的适应性。尽管本研究聚焦于血糖预测，但亦证明其在院内死亡率预测任务中具有泛化能力，展现了在ICU环境中处理复杂多源不规则时间序列数据的广泛应用潜力。
原文摘要 · Abstract (English)
Accurately predicting blood glucose (BG) levels of ICU patients is critical, as both hypoglycemia (BG < 70 mg/dL) and hyperglycemia (BG > 180 mg/dL) are associated with increased morbidity and mortality. This study presents a proof-of-concept machine learning framework, the Multi-source Irregular Time-Series Transformer (MITST), designed to predict BG levels in ICU patients. In contrast to existing methods that rely heavily on manual feature engineering or utilize limited Electronic Health Record (EHR) data sources, MITST integrates diverse clinical data--including laboratory results, medications, and vital signs without predefined aggregation. The model leverages a hierarchical Transformer architecture, designed to capture interactions among features within individual timestamps, temporal dependencies across different timestamps, and semantic relationships across multiple data sources. Evaluated using the extensive eICU database (200,859 ICU stays across 208 hospitals), MITST achieves a statistically significant ( p < 0.001 ) average improvement of 1.7 percentage points (pp) in AUROC and 1.8 pp in AUPRC over a state-of-the-art random forest baseline. Crucially, for hypoglycemia--a rare but life-threatening condition--MITST increases sensitivity by 7.2 pp, potentially enabling hundreds of earlier interventions across ICU populations. The flexible architecture of MITST allows seamless integration of new data sources without retraining the entire model, enhancing its adaptability for clinical decision support. While this study focuses on predicting BG levels, we also demonstrate MITST's ability to generalize to a distinct clinical task (in-hospital mortality prediction), highlighting its potential for broader applicability in ICU settings. MITST thus offers a robust and extensible solution for analyzing complex, multi-source, irregular time-series data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。