文献速递心脑血管急症重症综合管理与镇静镇痛

连续卷积神经网络:极早期脑电图对缺氧后昏迷神经功能不良结局最具预测价值

A continuous convolutional neural network: very early EEG most predictive for poor neurological outcome in postanoxic coma.
PubMed 文献 · Resuscitation · 2025-12-24
一句话结论连续卷积神经网络模型分析心脏骤停后缺氧性昏迷患者的脑电图,在骤停后8小时预测不良神经结局的AUC达0.93,且4电极与9电极配置性能差异可忽略。

该研究使用连续卷积神经网络(CNN)模型,对366例心脏骤停后缺氧性昏迷患者从记录开始至骤停后72小时的每小时5分钟脑电图片段进行训练,主要结局为6个月内最佳脑功能分级(CPC 1-2为良好,3-5为不良)。9电极累积CNN模型在所有可用小时上的AUC为82%,0%假阳性率下灵敏度71%;预测性能在骤停后14小时前最高,8小时达峰值(AUC=0.93,0%假阳性率下灵敏度0.81)。9电极与4电极模型在各时间点的性能差异可忽略。作者认为CNN似乎对缺氧后昏迷患者的不良神经结局预测有价值,尤其对极早期(骤停后6-14小时)脑电图,且减少电极配置与全导联同样足够。

要点

  • 9电极累积CNN模型在所有可用小时上预测不良神经结局的AUC为82%,0%假阳性率下灵敏度71%。
  • 预测性能在心脏骤停后14小时前最高,峰值在8小时(AUC=0.93,0%假阳性率下灵敏度0.81)。
  • 9电极与4电极模型在各时间点的性能差异可忽略,减少电极配置与全导联同样足够。
  • 模型基于每小时5分钟脑电图片段,从记录开始至骤停后72小时,结局为6个月内CPC评分。
  • 作者认为CNN似乎对缺氧后昏迷患者的不良神经结局预测有价值,尤其对极早期(6-14小时)脑电图。

适用人群与场景

  • 366例心脏骤停后缺氧性昏迷患者,从脑电图记录开始至骤停后72小时。
  • 主要结局为心脏骤停后6个月内最佳脑功能分级(CPC),良好为CPC 1-2,不良为CPC 3-5。

诊断标准与关键阈值

  • 脑功能分级(CPC)评分:良好结局为CPC 1-2,不良结局为CPC 3-5。
  • 预测基于所有可用小时预测值的平均值,分别独立和累积计算。

研究设计与关键结果

  • 研究为CNN模型训练与验证,使用366例患者每小时5分钟脑电图片段,从记录开始至骤停后72小时。
  • 9电极累积CNN模型在所有可用小时上AUC为82%,0%假阳性率下灵敏度71%。
  • 最高预测性能在骤停后14小时前,峰值在8小时:AUC=0.93,0%假阳性率下灵敏度0.81。
  • 9电极与4电极模型在各时间点的性能差异可忽略。

证据类型、等级与局限

  • 证据类型:卷积神经网络模型研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为CNN似乎对缺氧后昏迷患者的不良神经结局预测有价值,尤其对极早期(骤停后6-14小时)脑电图。
  • 作者认为减少电极配置(4电极)与全导联(9电极)同样足够。
  • 作者提出未来研究可探索捕捉脑电图信号中细微的时间依赖性以用于预后判断。

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

OBJECTIVE: Our first objective was to characterize the predictive power of electroencephalography (EEG) over time after cardiac arrest (CA) using a continuous, convolutional neural network (CNN). Our second objective was to investigate the performance difference between a 9 and a 4-electrode-model in predicting poor neurological outcome.

METHODS: We trained a CNN model using hourly 5-min EEG epochs from 366 postanoxic coma patients from the start of recording up to 72 h after CA. Primary outcome was best Cerebral Performance Category (CPC) within 6 months after CA, classified as good (CPC score 1-2) or poor (CPC score 3-5). Prediction was based on the average of predictions over all available hours, both independently and cumulatively. We report (1) model discrimination of poor neurological outcome up to 72 h after CA and (2) model performance difference between a 9 and 4-electrode configuration.

RESULTS: The 9-electrode cumulative CNN model reached an area under the receiver operating characteristic curve (AUC) of 82 % and a sensitivity of 71 % at 0 % false-positive rate (FPR) over all available hours. Highest predictive performance was observed before 14 h after CA, peaking at 8 h (AUC = 0.93, sensitivity at 0 % FPR = 0.81). Performance differences over hours were negligible between the 9 and 4-electrode model.

CONCLUSION: The CNN seems valuable for poor neurological outcome prediction in postanoxic coma patients, especially for very early (6-14 h after CA) EEG. A reduced electrode configuration is equally sufficient as the full set. Future studies could explore capturing nuanced temporal dependencies in EEG signals for prognostication.

来源:Resuscitation,查看原文。版权归原作者所有。

参考来源

  1. Hodžić I, Doelkahar B, Horn J, et al. A continuous convolutional neural network: very early EEG most predictive for poor neurological outcome in postanoxic coma. Resuscitation. 2025. PMID: 41453650. doi:10.1016/j.resuscitation.2025.110943

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。