机器学习导出的脓毒症集束化治疗
该回顾性队列研究利用MIMIC-IV数据库(训练与内部验证队列)和eICU-CRD数据库(外部验证队列)中的脓毒症/脓毒症休克ICU患者,通过LASSO惩罚机器学习模型从SSC指南中筛选出6项推荐(抗菌药物、平衡晶体液、胰岛素治疗、糖皮质激素、血管加压素、碳酸氢盐治疗)组成集束。共纳入42,735例患者,倾向性评分匹配后,集束组较无集束组28天全因死亡率更低(内部验证OR 0.41 [0.33-0.53],p<0.001;外部验证OR 0.75 [0.60-0.94],p=0.02)。作者结论为该6项推荐组成的集束与死亡率大幅降低相关,需前瞻性评估。
要点
- 在MIMIC-IV训练队列中通过LASSO模型筛选出6项推荐:抗菌药物、平衡晶体液、胰岛素治疗、糖皮质激素、血管加压素、碳酸氢盐治疗。
- 集束组定义为至少接受全部6项推荐,无集束组为至少省略1项推荐。
- 倾向性评分匹配的内部验证队列中,集束组28天全因死亡率低于无集束组(OR 0.41 [0.33-0.53],p<0.001)。
- 倾向性评分匹配的外部验证队列(eICU-CRD)中,集束组28天全因死亡率低于无集束组(OR 0.75 [0.60-0.94],p=0.02)。
- 作者结论:该6项推荐集束与脓毒症/脓毒症休克死亡率大幅降低相关,需前瞻性评估。
适用人群与场景
- 从MIMIC-IV数据库(训练与内部验证队列)和eICU-CRD数据库(外部验证队列)中提取的入住ICU的脓毒症/脓毒症休克患者,共42,735例。
诊断标准与关键阈值
- 集束组:至少接受全部6项推荐(抗菌药物、平衡晶体液、胰岛素治疗、糖皮质激素、血管加压素、碳酸氢盐治疗)的患者。
- 无集束组:至少省略1项上述推荐的患者。
研究设计与关键结果
- 研究类型:回顾性队列研究;数据来源:MIMIC-IV(训练与内部验证队列)和eICU-CRD(外部验证队列);总样本量42,735例。
- 主要终点:28天全因死亡率。
- 通过LASSO惩罚机器学习模型从训练队列中筛选出6项推荐组成集束:抗菌药物、平衡晶体液、胰岛素治疗、糖皮质激素、血管加压素、碳酸氢盐治疗。
- 倾向性评分匹配的内部验证队列:集束组较无集束组28天死亡率更低(OR 0.41 [0.33-0.53],p<0.001)。
- 倾向性评分匹配的外部验证队列:集束组较无集束组28天死亡率更低(OR 0.75 [0.60-0.94],p=0.02)。
证据类型、等级与局限
- 证据类型:回顾性队列研究。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为该6项推荐组成的集束与脓毒症/脓毒症休克死亡率大幅降低相关,需前瞻性评估。
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
PURPOSE: Compliance to the Surviving Sepsis Campaign (SSC) guidelines is limited. This is known to be associated with increased mortality. The aim of this retrospective cohort study was to identify among the SCC guidelines the optimal bundle of recommendations that minimize 28-day mortality.
METHODS: We used a training cohort to identify, using a least absolute shrinkage and selection operator penalized machine learning model, this bundle. Patients with sepsis/septic shock admitted to the intensive care unit (ICU) were extracted from two US databases, the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database (training and internal validation cohorts) and the eICU Collaborative Research Database (eICU-CRD) (external validation cohort). In the validation cohorts, we defined a bundle group that includes patients who were treated with at least all the recommendations selected in our bundle and a no-bundle group that includes patients in whom at least one recommendation from our bundle was omitted.
RESULTS: All-cause 28-day mortality was the primary outcome measure. A total of 42,735 patients were included. Six recommendations (antimicrobials, balanced crystalloid, insulin therapy, corticosteroids, vasopressin, and bicarbonate therapy) were identified from the training cohort to be included in our bundle. In the propensity score-(PS)-matched internal validation cohort, the bundle group was associated with a lower mortality (OR 0.41 [0.33-0.53]; p < 0.001) compared to the no-bundle group. This was confirmed in the PS-matched external validation cohort (OR 0.75 [0.60-0.94]; p 0.02).
CONCLUSION: Our bundle of six recommendations is associated with a dramatic reduction in mortality in sepsis and septic shock. This bundle needs to be evaluated prospectively.
参考来源
- Kalimouttou A, Lerner I, Cheurfa C, et al. Machine-learning-derived sepsis bundle of care. Intensive Care Med. 2022. PMID: 36446854. doi:10.1007/s00134-022-06928-2
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。