深度学习用于心脏骤停后昏迷的结局预测
这项前瞻性队列研究纳入荷兰五家教学医院医疗ICU的895例心脏骤停后昏迷患者,连续记录心脏骤停后前3天的脑电图。研究训练卷积神经网络(VGG架构),以脑电图片段和结局标签为输入,预测12小时和24小时后的神经功能结局,输出为良好结局的概率。两家医院数据用于训练和内部验证(n=661),其余三家医院数据用于外部验证(n=234)。外部验证集中,12小时预测不良结局的敏感度为58%(95%CI 51-65%),假阳性率0%(CI 0-7%);预测良好结局的敏感度为48%(CI 45-51%),假阳性率5%(CI 0-15%)。作者认为深度学习脑电图信号优于既往任何心脏骤停后昏迷结局预测方法,包括受训脑电图专家的视觉评估。
要点
- 外部验证集中,12小时预测不良结局的敏感度为58%(95%CI 51-65%),假阳性率0%(CI 0-7%)。
- 外部验证集中,12小时预测良好结局的敏感度为48%(CI 45-51%),假阳性率5%(CI 0-15%)。
- 预测不良结局在12小时最准确,优于24小时。
- 深度学习脑电图信号优于既往任何心脏骤停后昏迷结局预测方法,包括受训专家的视觉脑电图评估。
- 该方法有望实现客观、实时的床旁神经预后评估。
适用人群与场景
- 荷兰五家教学医院医疗ICU的连续895例心脏骤停后昏迷患者。
- 连续记录心脏骤停后前3天的脑电图。
- 功能结局在6个月时分类为良好(脑功能分级1-2)或不良(脑功能分级3-5)。
诊断标准与关键阈值
- 功能结局采用脑功能分级:良好为1-2,不良为3-5。
- 预测不良结局的最准确时间点为心脏骤停后12小时。
研究设计与关键结果
- 研究类型:前瞻性队列研究;样本量895例;五家教学医院。
- 干预:无;连续脑电图记录心脏骤停后前3天。
- 训练与内部验证:两家医院数据(n=661),80%用于训练和交叉验证,20%用于独立内部验证。
- 外部验证:其余三家医院数据(n=234)。
- 外部验证集中,12小时预测不良结局的敏感度58%(95%CI 51-65%),假阳性率0%(CI 0-7%)。
- 外部验证集中,12小时预测良好结局的敏感度48%(CI 45-51%),假阳性率5%(CI 0-15%)。
- 预测不良结局在12小时最准确。
证据类型、等级与局限
- 证据类型:前瞻性队列研究。
- 作者结论:深度学习脑电图信号优于既往任何心脏骤停后昏迷结局预测方法,包括受训脑电图专家的视觉评估。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,该方法有望为心脏骤停后昏迷患者的神经预后提供客观、实时的床旁评估。
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
OBJECTIVES: Visual assessment of the electroencephalogram by experienced clinical neurophysiologists allows reliable outcome prediction of approximately half of all comatose patients after cardiac arrest. Deep neural networks hold promise to achieve similar or even better performance, being more objective and consistent.
DESIGN: Prospective cohort study.
SETTING: Medical ICU of five teaching hospitals in the Netherlands.
PATIENTS: Eight-hundred ninety-five consecutive comatose patients after cardiac arrest.
INTERVENTIONS: None.
MEASUREMENTS AND MAIN RESULTS: Continuous electroencephalogram was recorded during the first 3 days after cardiac arrest. Functional outcome at 6 months was classified as good (Cerebral Performance Category 1-2) or poor (Cerebral Performance Category 3-5). We trained a convolutional neural network, with a VGG architecture (introduced by the Oxford Visual Geometry Group), to predict neurologic outcome at 12 and 24 hours after cardiac arrest using electroencephalogram epochs and outcome labels as inputs. Output of the network was the probability of good outcome. Data from two hospitals were used for training and internal validation (n = 661). Eighty percent of these data was used for training and cross-validation, the remaining 20% for independent internal validation. Data from the other three hospitals were used for external validation (n = 234). Prediction of poor outcome was most accurate at 12 hours, with a sensitivity in the external validation set of 58% (95% CI, 51-65%) at false positive rate of 0% (CI, 0-7%). Good outcome could be predicted at 12 hours with a sensitivity of 48% (CI, 45-51%) at a false positive rate of 5% (CI, 0-15%) in the external validation set.
CONCLUSIONS: Deep learning of electroencephalogram signals outperforms any previously reported outcome predictor of coma after cardiac arrest, including visual electroencephalogram assessment by trained electroencephalogram experts. Our approach offers the potential for objective and real time, bedside insight in the neurologic prognosis of comatose patients after cardiac arrest.
参考来源
- Tjepkema-Cloostermans MC, da Silva Lourenço C, Ruijter BJ, et al. Outcome Prediction in Postanoxic Coma With Deep Learning. Crit Care Med. 2019. PMID: 31162190. doi:10.1097/CCM.0000000000003854
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。