低血压暴露持续时间指数的开发与验证:用于重症患者死亡风险预测
本研究为回顾性研究,使用Salzburg重症监护数据库,纳入11,059例接受连续有创动脉监测的ICU入院患者,基于逐分钟血压数据构建热图,分析血压阈值(52-120 mmHg)与暴露时长(5分钟至5小时)和死亡率的关系,并开发HEDI以整合多MAP阈值的累积低血压负担。非幸存者HEDI显著高于幸存者(0.47 [-0.20, 1.43] vs -0.15 [-0.41, 0.27],p < 0.001)。HEDI预测能力随入住时间增加,AUC从24小时的0.624升至72小时的0.700;Extra Trees分类器测试AUC为0.843,HEDI位列顶级预测特征。内部交叉验证和eICU数据库外部验证均证实模型稳健性,包括使用与不使用血管升压药的患者。
要点
- 非幸存者HEDI显著高于幸存者:0.47 [-0.20, 1.43] vs -0.15 [-0.41, 0.27],p < 0.001。
- HEDI预测ICU死亡的AUC从入住24小时的0.624升至72小时的0.700。
- Extra Trees分类器测试AUC达0.843,HEDI位列顶级预测特征。
- 内部交叉验证和eICU外部验证均证实HEDI在不同人群中具有预后价值,包括使用与不使用血管升压药的患者。
- HEDI通过整合多个MAP阈值(52-120 mmHg)和暴露时长(5分钟至5小时)的累积低血压负担进行量化。
适用人群与场景
- 使用Salzburg重症监护数据库的ICU入院患者,共11,059例,均接受连续有创动脉监测。
- 外部验证使用eICU数据库,评估HEDI在不同人群中的一致性,包括使用与不使用血管升压药的患者。
诊断标准与关键阈值
- HEDI整合多个MAP阈值(52-120 mmHg)和暴露时长(5分钟至5小时)的累积低血压负担进行量化。
研究设计与关键结果
- 回顾性研究,使用Salzburg重症监护数据库,纳入11,059例接受连续有创动脉监测的ICU入院患者。
- 非幸存者HEDI显著高于幸存者:0.47 [-0.20, 1.43] vs -0.15 [-0.41, 0.27],p < 0.001。
- HEDI预测能力随入住时间增加,AUC从24小时的0.624升至72小时的0.700。
- Extra Trees分类器测试AUC为0.843,HEDI位列顶级预测特征。
- 内部交叉验证和eICU数据库外部验证均证实模型稳健性,HEDI在包括使用与不使用血管升压药的不同患者人群中具有预后价值。
证据类型、等级与局限
- 证据类型:回顾性研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 原文未据此给出推荐。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
BACKGROUND: Blood pressure management is crucial in critical care, but relationships between pressure patterns and outcomes remain incompletely understood. We analyzed minute-by-minute blood pressure data to develop and validate a novel index quantifying hypotensive exposure burden.
METHODS: In this retrospective study using the Salzburg Intensive Care Database, 11,059 ICU admissions with continuous invasive arterial monitoring were analyzed. Heatmaps were constructed from high-resolution hemodynamic data to visualize relationships between blood pressure thresholds (52-120 mmHg), exposure durations (5 min-5 h), and mortality. The Hypotensive Exposure Duration Index (HEDI) was developed to quantify cumulative hypotensive burden by integrating exposure across multiple MAP thresholds. HEDI's prognostic value was evaluated through nine machine learning algorithms. External validation using the eICU database assessed HEDI's consistency across different populations.
RESULTS: Non-survivors showed significantly higher HEDI compared to survivors (0.47 [-0.20, 1.43] vs. -0.15 [-0.41, 0.27], p < 0.001). HEDI demonstrated increasing predictive capability, with AUC values rising from 0.624 at 24 h to 0.700 at 72 h post-admission. The Extra Trees classifier achieved exceptional performance (test AUC: 0.843), with HEDI ranking among the top predictive features. Both internal cross-validation and external validation confirmed the model's robustness, demonstrating HEDI's prognostic value across different patient populations, including both patients with and without vasopressor use.
CONCLUSIONS: HEDI effectively quantifies cumulative hypotensive burden in critically ill patients, demonstrating significant predictive ability for ICU mortality validated across diverse populations.
参考来源
- Ding XY, Xu HP, Zhang JR, et al. Development and validation of the Hypotensive Exposure Duration Index for mortality risk prediction in critically ill patients. J Intensive Care. 2025. PMID: 41331450. doi:10.1186/s40560-025-00834-7
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。