脓毒性休克中血管加压素的最佳启动时机:OVISS强化学习研究
本研究利用2012至2023年加州5家医院3608例符合Sepsis-3休克标准的成人患者电子健康记录,通过强化学习构建血管加压素启动规则,并在628例加州数据及3个外部数据集共10217例(227家美国医院)中验证。验证数据显示,模型建议启动血管加压素的患者比例更高(87% vs 31%)、相对休克发生更早(中位4小时 vs 5小时)、去甲肾上腺素剂量更低(0.20 vs 0.37 µg/kg/min)。与临床实际做法不同相比,启动方式与规则相似时住院死亡率校正比值比更低(OR 0.81,95%CI 0.73-0.91),外部验证一致。该模型推荐较平均诊疗模式更频繁、更早使用血管加压素,并与死亡率降低相关。
要点
- 在10217例外部验证患者中,模型建议87%启动血管加压素,而临床实际仅31%启动。
- 模型建议启动时间中位4小时(IQR 1-8),早于临床实际的5小时(IQR 1-14)。
- 模型建议启动时去甲肾上腺素剂量中位0.20 µg/kg/min(IQR 0.08-0.45),低于临床实际的0.37 µg/kg/min(IQR 0.17-0.69)。
- 血管加压素启动方式与规则相似者住院死亡率校正OR为0.81(95%CI 0.73-0.91),外部验证集结果一致。
- 该规则在验证数据中较临床实际做法获得更大的期望奖励(加权重要性抽样差值31,95%CI 15-52)。
适用人群与场景
- 成人重症患者,接受去甲肾上腺素治疗的脓毒性休克患者,符合Sepsis-3休克标准。
- 推导队列来自2012至2023年加州5家医院,共3608例;验证队列包括加州628例及3个外部数据集共10217例(227家美国医院)。
诊断标准与关键阈值
- 脓毒性休克诊断采用Sepsis-3休克标准。
- 推导队列休克发生时SOFA评分中位5分(IQR 3-7,范围0-24,评分越高死亡率越高);验证队列SOFA评分中位6分(IQR 4-9)。
处置流程与药物剂量
- 强化学习模型基于电子健康记录中按小时分组的120小时临床、实验室和治疗变量,生成血管加压素启动规则。
- 模型建议的启动规则为:较临床实践更早(中位4小时 vs 5小时)、更频繁(87% vs 31%)、在较低去甲肾上腺素剂量下(中位0.20 vs 0.37 µg/kg/min)启动血管加压素。
研究设计与关键结果
- 研究类型为强化学习模型推导与验证研究,推导队列3608例,验证队列共10845例(加州628例+外部10217例)。
- 推导队列中男性2075例(57%),年龄中位63岁(IQR 56-70);验证队列男性56%(5743例),年龄中位67岁(IQR 57-75)。
- 验证数据中,模型建议启动血管加压素的比例为87%,临床实际为31%;启动时间中位4小时(IQR 1-8) vs 5小时(IQR 1-14);去甲肾上腺素剂量中位0.20 µg/kg/min(IQR 0.08-0.45) vs 0.37 µg/kg/min(IQR 0.17-0.69)。
- 模型规则在验证数据中较临床实际做法获得更大的期望奖励(加权重要性抽样差值31,95%CI 15-52)。
- 血管加压素启动与规则相似者住院死亡率校正OR为0.81(95%CI 0.73-0.91),外部验证集结果一致。
证据类型、等级与局限
- 证据类型:基于电子健康记录的观察性数据推导与验证研究,采用强化学习、加权重要性抽样和逆概率加权 pooled logistic 回归。
- 局限:原文未报告局限性。
对床旁实践的改变
- 在成人脓毒性休克接受去甲肾上腺素的患者中,血管加压素的使用存在差异;强化学习模型提示较平均诊疗模式更频繁、更早启动血管加压素与住院死亡率降低相关。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「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: Norepinephrine is the first-line vasopressor for patients with septic shock. When and whether a second agent, such as vasopressin, should be added is unknown.
OBJECTIVE: To derive and validate a reinforcement learning model to determine the optimal initiation rule for vasopressin in adult, critically ill patients receiving norepinephrine for septic shock.
DESIGN, SETTING, AND PARTICIPANTS: Reinforcement learning was used to generate the optimal rule for vasopressin initiation to improve short-term and hospital outcomes, using electronic health record data from 3608 patients who met the Sepsis-3 shock criteria at 5 California hospitals from 2012 to 2023. The rule was evaluated in 628 patients from the California dataset and 3 external datasets comprising 10 217 patients from 227 US hospitals, using weighted importance sampling and pooled logistic regression with inverse probability weighting.
EXPOSURES: Clinical, laboratory, and treatment variables grouped hourly for 120 hours in the electronic health record.
MAIN OUTCOME AND MEASURE: The primary outcome was in-hospital mortality.
RESULTS: The derivation cohort (n = 3608) included 2075 men (57%) and had a median (IQR) age of 63 (56-70) years and Sequential Organ Failure Assessment (SOFA) score at shock onset of 5 (3-7 [range, 0-24, with higher scores associated with greater mortality]). The validation cohorts (n = 10 217) were 56% male (n = 5743) with a median (IQR) age of 67 (57-75) years and a SOFA score of 6 (4-9). In validation data, the model suggested vasopressin initiation in more patients (87% vs 31%), earlier relative to shock onset (median [IQR], 4 [1-8] vs 5 [1-14] hours), and at lower norepinephrine doses (median [IQR], 0.20 [0.08-0.45] vs 0.37 [0.17-0.69] µg/kg/min) compared with clinicians' actions. The rule was associated with a larger expected reward in validation data compared with clinician actions (weighted importance sampling difference, 31 [95% CI, 15-52]). The adjusted odds of hospital mortality were lower if vasopressin initiation was similar to the rule compared with different (odds ratio, 0.81 [95% CI, 0.73-0.91]), a finding consistent across external validation sets.
CONCLUSIONS AND RELEVANCE: In adult patients with septic shock receiving norepinephrine, the use of vasopressin was variable. A reinforcement learning model developed and validated in several observational datasets recommended more frequent and earlier use of vasopressin than average care patterns and was associated with reduced mortality.
参考来源
- Kalimouttou A, Kennedy JN, Feng J, et al. Optimal Vasopressin Initiation in Septic Shock: The OVISS Reinforcement Learning Study. JAMA. 2025. PMID: 40098600. doi:10.1001/jama.2025.3046
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。