文献速递复苏、休克与脓毒症心脑血管急症

联合心室颤动与除颤波形预测除颤结局:一项回顾性临床研究

Predicting defibrillation outcomes by combining ventricular fibrillation and defibrillation waveforms: a retrospective clinical study.
PubMed 文献 · Resuscitation · 2025-11-19
一句话结论回顾性心脏骤停队列显示,联合室颤与除颤波形的深度学习模型预测除颤结局的AUC高于振幅谱面积(AMSA)。

该回顾性临床研究纳入发生室颤并接受除颤的患者,经除颤器记录心电波形,基于报告能量和经胸阻抗建模除颤波形,并将未受损的除颤前室颤波形与建模除颤波形用卷积神经网络联合。数据按4:1随机分为训练集和测试集。以每次电击后室颤终止、恢复有组织心律、恢复潜在灌注心律为除颤结局。联合波形预测三项结局的AUC均显著高于AMSA,其中AMSA 4.6–15.0 mVHz的电击改善最明显。

要点

  • 联合室颤与除颤波形预测室颤终止的AUC为0.627,高于AMSA的0.578(p=0.010)。
  • 联合波形预测恢复有组织心律的AUC为0.854,高于AMSA的0.804(p<0.001)。
  • 联合波形预测恢复潜在灌注心律的AUC为0.873,高于AMSA的0.836(p=0.004)。
  • AMSA 4.6–15.0 mVHz的电击中,联合波形使室颤终止、恢复有组织心律、恢复潜在灌注心律的AUC分别提高9.0、7.3、5.1个点。
  • 建模除颤波形与实测波形的相关误差范围为-1.10%至1.31%。

适用人群与场景

  • 回顾性心脏骤停队列中发生室颤并接受除颤的患者。

研究设计与关键结果

  • 研究类型为回顾性临床研究,数据按4:1随机分为训练集和测试集。
  • 以每次电击后室颤终止、恢复有组织心律、恢复潜在灌注心律为除颤结局。
  • 建模除颤波形与实测波形的相关误差范围为-1.10%至1.31%。
  • 联合室颤与除颤波形预测室颤终止的AUC为0.627,AMSA为0.578,差异有统计学意义(p=0.010)。
  • 联合波形预测恢复有组织心律的AUC为0.854,AMSA为0.804,差异有统计学意义(p<0.001)。
  • 联合波形预测恢复潜在灌注心律的AUC为0.873,AMSA为0.836,差异有统计学意义(p=0.004)。
  • AMSA 4.6–15.0 mVHz的电击中,联合波形使室颤终止、恢复有组织心律、恢复潜在灌注心律的AUC分别提高9.0、7.3、5.1个点。

证据类型、等级与局限

  • 证据类型:回顾性临床研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,联合室颤与除颤波形的深度学习方法可提高除颤结局预测准确性,且不受除颤成功定义标准影响。

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」「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

AIM: To validate whether combining ventricular fibrillation (VF) and defibrillation (DF) waveforms could improve the prediction accuracy of DF outcomes in a retrospective cardiac arrest cohort.

METHODS: Electrocardiographic waveforms were recorded via defibrillators for patients who experienced VF and DF. DF waveforms were modeled on the basis of reported energy and transthoracic impedance and assessed by related errors between modeled and delivered waveforms. The uncorrupted preshock VF waveform and the modeled DF waveform were combined using a convolutional neural network. The data were randomized into training and testing sets at a ratio of 4:1. The termination of ventricular fibrillation (TOVF), return of organized rhythm (ROOR), and return of potentially perfusing rhythm (RPPR) after each shock were used as DF outcomes. The performance was evaluated by comparing the area under the receiver operating characteristic curve (AUC) with that of the amplitude spectrum area (AMSA).

RESULTS: Related errors for the modeled DF waveform ranged from -1.10 % to 1.31 %. Compared with those of AMSA, AUC values were significantly greater for TOVF (0.627 vs. 0.578; p = 0.010), ROOR (0.854 vs. 0.804; p < 0.001), and RPPR (0.873 vs. 0.836; p = 0.004) when VF and DF waveforms were combined. The most notable improvement occurred in shocks with AMSA values ranging from 4.6 to 15.0 mVHz, which demonstrated AUC increases of 9.0, 7.3, and 5.1 points for TOVF, ROOR, and RPPR, respectively.

CONCLUSIONS: The combination of VF and DF waveforms using a deep learning-based approach significantly improved the prediction accuracy of DF outcomes regardless of the criteria used to define DF success.

来源:Resuscitation,查看原文。版权归原作者所有。

参考来源

  1. Wei L, Gong Y, Wang J, et al. Predicting defibrillation outcomes by combining ventricular fibrillation and defibrillation waveforms: a retrospective clinical study. Resuscitation. 2025. PMID: 41270994. doi:10.1016/j.resuscitation.2025.110906

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。