文献速递复苏、休克与脓毒症心脑血管急症

通过5分钟社会救援圈实施提升中国院外心脏骤停生存率

Enhancing out-of-hospital cardiac arrest survival in China through the 5-minute social rescue circle implementation.
PubMed 文献 · Resuscitation · 2025-06-30
一句话结论深圳宝安5分钟社会救援圈实施期间,旁观者CPR率从12.32%升至27.27%,AED使用率从1.96%升至4.64%,30天生存率从2.27%升至6.51%。

该研究整合深圳市宝安区2019年3月至2024年9月的3586例院外心脏骤停(OHCA)病例、332507名接受CPR培训的居民和4707台AED部署数据,开发基于微信的5分钟社会救援圈(5MSRC)系统,将视频指导CPR与紧急调度整合。利用地理空间追踪、机器学习和SHAP分析识别与自主循环恢复(ROSC)及30天生存改善相关的关键因素。结果显示,疫情期间恢复阶段(2020—2024年)旁观者CPR率、AED使用率和30天生存率均显著改善。社区层面因素(近期CPR培训率、AED邻近度、快速响应系统)驱动院前ROSC,而医院内干预(如经皮冠状动脉介入治疗)对30天生存愈发重要。

要点

  • 在3586例OHCA中,3.88%实现院前ROSC,3.82%存活超过30天。
  • 公共场所发生的OHCA结局显著优于住宅场所:ROSC为66.2% vs 33.8%,30天生存为68.6% vs 31.4%(均p<0.001)。
  • 2020—2024年疫情期间恢复阶段,旁观者CPR率从12.32%升至27.27%,AED使用率从1.96%升至4.64%,30天生存率从2.27%升至6.51%(均p<0.05)。
  • 机器学习模型对院前ROSC预测性能优异(最佳ROC-AUC 0.92,95%CI 0.91-0.93),对30天生存预测良好(最佳ROC-AUC 0.97,95%CI 0.96-0.98)。
  • 社区层面因素(如6个月内的近期CPR培训率、AED邻近度、快速响应系统)驱动院前ROSC,医院内干预(如经皮冠状动脉介入治疗)对30天生存愈发重要。

适用人群与场景

  • 深圳市宝安区2019年3月至2024年9月发生的3586例院外心脏骤停(OHCA)病例。
  • 该区332507名接受CPR培训的居民及4707台AED部署覆盖的社区场景。

处置流程与药物剂量

  • 开发基于微信的5分钟社会救援圈(5MSRC)系统,将视频指导CPR与紧急调度整合。

研究设计与关键结果

  • 研究类型为患者为中心的整合数据分析,整合宝安区3586例OHCA病例、332507名CPR培训居民和4707台AED部署三套数据集。
  • 3586例OHCA中,3.88%实现院前ROSC,3.82%存活超过30天。
  • 公共场所OHCA结局优于住宅场所:ROSC 66.2% vs 33.8%,30天生存68.6% vs 31.4%(均p<0.001)。
  • 2020—2024年旁观者CPR率从12.32%升至27.27%,AED使用率从1.96%升至4.64%,30天生存率从2.27%升至6.51%(均p<0.05)。
  • 机器学习模型预测院前ROSC的最佳ROC-AUC为0.92(95%CI 0.91-0.93),预测30天生存的最佳ROC-AUC为0.97(95%CI 0.96-0.98)。
  • 特征重要性分析显示,社区层面因素(近期CPR培训率如6个月、AED邻近度、快速响应系统)驱动院前ROSC,医院内干预(如经皮冠状动脉介入治疗)对30天生存愈发重要。

证据类型、等级与局限

  • 证据类型:基于整合数据集的分析研究,采用地理空间追踪、机器学习和SHAP分析。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,社区准备(频繁CPR培训、AED可及性)与高级医院救治之间的协同对优化OHCA结局至关重要。
  • 作者认为,高性能预测模型展示了机器学习在识别心脏骤停全程救治中战略干预点的潜力。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「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: Out-of-hospital cardiac arrest (OHCA) survival in China remains critically low due to limited bystander cardiopulmonary resuscitation (CPR) training, insufficient automated external defibrillator (AED) deployment, and delayed community rescue responses. This study quantitatively assessed the impact of the intervention and the 5-minute social rescue circle (5MSRC) on OHCA outcomes in Baoan District, Shenzhen, China.

METHODS: We employed a patient-centered approach to integrate three datasets from Baoan, Shenzhen from March 2019 to September 2024: (a) 3586 OHCA cases; (b) 332,507 CPR-trained residents; (c) 4,707 AED deployments. A WeChat-based 5MSRC system was developed to integrate video-guided CPR with emergency dispatch. Using the integrated dataset, we applied geospatial tracking, machine learning, and SHapley Additive exPlanations (SHAP) analysis to identify key factors associated with improvedreturn of spontaneous circulation (ROSC) and 30-day survival.

RESULTS: Among 3586 OHCA cases, 3.88 % achieved prehospital ROSC and 3.82 % survived after 30 days. Arrests in public locations showed significantly better outcomes than residential settings (ROSC: 66.2 % vs 33.8 %; 30-day survival: 68.6 % vs 31.4 %, both p < 0.001). During post-pandemic recovery (2020-2024), OHCA outcomes demonstrated significant improvement: bystander CPR rates increased from 12.32 % to 27.27 %, AED application rose from 1.96 % to 4.64 %, and 30-day survival improved from 2.27 % to 6.51 % (all p < 0.05). The machine learning models achieved excellent predictive performance for prehospital ROSC (best ROC-AUC: 0.92, 95 % CI 0.91-0.93) and good performance for 30-day survival (best ROC-AUC: 0.97, 95 % CI 0.96-0.98), demonstrating robust predictive capability for both acute and longer-term outcomes. Feature importance analysis revealed that community-level factors-particularly recent CPR training rates (e.g., 6-month), AED proximity, and rapid response systems-drove prehospital ROSC, while hospital-based interventions (e.g., percutaneous coronary intervention) became increasingly important for 30-day survival.

CONCLUSIONS: These findings underscore the critical synergy between community preparedness (frequent CPR training, AED accessibility) and advanced hospital care in optimizing OHCA outcomes. The high-performing prediction models demonstrate the potential of machine learning to identify strategic intervention points across the continuum of cardiac arrest care.

来源:Resuscitation,查看原文。版权归原作者所有。

参考来源

  1. Zhang W, Wu L, He X, et al. Enhancing out-of-hospital cardiac arrest survival in China through the 5-minute social rescue circle implementation. Resuscitation. 2025. PMID: 40602480. doi:10.1016/j.resuscitation.2025.110694

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。