脓毒症合并急性肾损伤患者的个体化液体管理:因果机器学习方法
本研究为回顾性研究,纳入ICU入科48小时内发生AKI的脓毒症患者,开发因果机器学习框架估计限制性液体(AKI后24小时内<500 mL)的个体化治疗效应。模型在MIMIC-IV开发,在Salzburg Intensive Care数据库外部验证,主要终点为24小时早期AKI逆转。因果森林模型识别异质性治疗效应的能力优于随机森林(外部验证AUTOC 0.15 vs -0.02)。外部验证队列1931例中模型推荐68.9%患者接受限制性液体,该组早期AKI逆转率53.9% vs 33.2%(p<0.001),持续AKI逆转率34.2% vs 18.0%(p<0.001),MAKE30更低(17.1% vs 34.6%,p=0.003)。作者认为该数据驱动方法值得前瞻性临床试验评估。
要点
- 外部验证队列1931例脓毒症合并AKI患者中,因果森林模型推荐68.9%接受限制性液体(AKI后24小时内<500 mL)。
- 被推荐且实际接受限制性液体的患者早期AKI逆转率53.9% vs 33.2%(p<0.001),持续AKI逆转率34.2% vs 18.0%(p<0.001)。
- 被推荐且接受限制性液体者MAKE30发生率17.1% vs 34.6%(p=0.003),调整分析结果一致。
- 因果森林模型识别异质性治疗效应的能力优于随机森林,外部验证AUTOC 0.15 vs -0.02。
- 作者认为该框架为个体化液体管理提供了数据驱动方法,值得前瞻性临床试验评估。
适用人群与场景
- 脓毒症患者,且在ICU入科48小时内发生急性肾损伤(AKI)。
- 研究在MIMIC-IV开发模型,在Salzburg Intensive Care数据库进行外部验证。
诊断标准与关键阈值
- 限制性液体定义为AKI发生后24小时内静脉液体<500 mL。
- 主要终点为24小时早期AKI逆转;次要终点包括持续AKI逆转和30天主要不良肾脏事件(MAKE30)。
研究设计与关键结果
- 研究类型:回顾性研究,在MIMIC-IV开发因果机器学习模型,在Salzburg Intensive Care数据库外部验证。
- 外部验证队列1931例,因果森林模型识别异质性治疗效应的AUTOC为0.15,随机森林为-0.02。
- 模型推荐68.9%的患者接受限制性液体;该组中实际接受限制性液体者早期AKI逆转率53.9% vs 33.2%(p<0.001),持续AKI逆转率34.2% vs 18.0%(p<0.001),MAKE30发生率17.1% vs 34.6%(p=0.003)。
- 调整分析结果与主分析一致。
证据类型、等级与局限
- 证据类型:回顾性研究,开发并外部验证因果机器学习框架。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为因果机器学习框架优于随机森林模型,可用于识别脓毒症合并AKI患者中可能从限制性液体治疗中获益的个体。
- 作者认为该数据驱动方法为个体化液体管理提供了新途径,值得前瞻性临床试验评估。
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
IMPORTANCE: IV fluids are the cornerstone for management of acute kidney injury (AKI) after sepsis but can cause fluid overload. A restrictive fluid strategy may benefit some patients; however, identifying them is challenging. Novel causal machine learning (ML) techniques can estimate heterogenous treatment effects (HTEs) of IV fluids among these patients.
OBJECTIVES: To develop and validate a causal-ML framework to identify patients who benefit from restrictive fluids (< 500 mL fluids within 24 hr after AKI).
DESIGN SETTING AND PARTICIPANTS: We conducted a retrospective study among patients with sepsis who developed acute kidney injury (AKI) within 48 hours of ICU admission. We developed a causal-ML approach to estimate individualized treatment effects and guide fluid therapy. We developed the model in Medical Information Mart for Intensive Care IV and externally validated it in Salzburg Intensive Care database.
MAIN OUTCOMES AND MEASURES: Our primary outcome was early AKI reversal at 24 hours. Secondary outcomes included sustained AKI reversal and major adverse kidney events by 30 days (MAKE30). Model performance to identify HTE of restrictive IV fluids was assessed using the area under the targeting operator characteristic curve (AUTOC), which quantifies how well a model captures HTE, and compared with a random forest model.
RESULTS: Causal forest model outperformed random forest in identifying HTE of restrictive IV fluids with AUTOC 0.15 vs. -0.02 in external validation cohort. Among 1931 patients in external validation cohort, the model recommended restrictive fluids for 68.9%. Among these, patients who received restrictive fluids demonstrated significantly higher rates of early AKI reversal (53.9% vs. 33.2%, p < 0.001), sustained AKI reversal (34.2% vs. 18.0%, p < 0.001), and lower rates of MAKE30 (17.1% vs. 34.6%, p = 0.003). Results were consistent in the adjusted analysis.
CONCLUSIONS AND RELEVANCE: Causal-ML framework outperformed random forest model in identifying patients with AKI and sepsis who benefit from restrictive fluid therapy. This provides a data-driven approach for personalized fluid management and merits prospective evaluation in clinical trials.
参考来源
- Oh W, Takkavatakarn K, Al-Taie Z, et al. Personalized Fluid Management in Patients With Sepsis and Acute Kidney Injury: A Causal Machine Learning Approach. Crit Care Explor. 2025. PMID: 41357343. doi:10.1097/CCE.0000000000001354
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。