Department of Neurology, Sleep-Wake-Epilepsy-Center, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland.
Department of Clinical Neuroscience, Lausanne University Hospital (CHUV) and University of Lausanne, Lausanne, Switzerland.
Crit Care. 2020 Dec 7;24(1):680. doi: 10.1186/s13054-020-03407-2.
Early prognostication in patients with acute consciousness impairment is a challenging but essential task. Current prognostic guidelines vary with the underlying etiology. In particular, electroencephalography (EEG) is the most important paraclinical examination tool in patients with hypoxic ischemic encephalopathy (HIE), whereas it is not routinely used for outcome prediction in patients with traumatic brain injury (TBI).
Data from 364 critically ill patients with acute consciousness impairment (GCS ≤ 11 or FOUR ≤ 12) of various etiologies and without recent signs of seizures from a prospective randomized trial were retrospectively analyzed. Random forest classifiers were trained using 8 visual EEG features-first alone, then in combination with clinical features-to predict survival at 6 months or favorable functional outcome (defined as cerebral performance category 1-2).
The area under the ROC curve was 0.812 for predicting survival and 0.790 for predicting favorable outcome using EEG features. Adding clinical features did not improve the overall performance of the classifier (for survival: AUC = 0.806, p = 0.926; for favorable outcome: AUC = 0.777, p = 0.844). Survival could be predicted in all etiology groups: the AUC was 0.958 for patients with HIE, 0.955 for patients with TBI and other neurosurgical diagnoses, 0.697 for patients with metabolic, inflammatory or infectious causes for consciousness impairment and 0.695 for patients with stroke. Training the classifier separately on subgroups of patients with a given etiology (and thus using less training data) leads to poorer classification performance.
While prognostication was best for patients with HIE and TBI, our study demonstrates that similar EEG criteria can be used in patients with various causes of consciousness impairment, and that the size of the training set is more important than homogeneity of ACI etiology.
对急性意识障碍患者进行早期预后预测是一项具有挑战性但必不可少的任务。目前的预后指南因潜在病因而异。特别是，脑电图（EEG）是缺氧缺血性脑病（HIE）患者最重要的辅助检查手段，但在创伤性脑损伤（TBI）患者中并不常规用于预后预测。
回顾性分析了一项前瞻性随机试验中 364 例不同病因、无近期癫痫发作迹象的急性意识障碍（GCS≤11 或 FOUR≤12）危重患者的数据。使用 8 种视觉 EEG 特征（首先单独使用，然后与临床特征结合使用）对随机森林分类器进行训练，以预测 6 个月时的生存或良好的功能结局（定义为脑功能分类 1-2）。
使用 EEG 特征预测生存的 ROC 曲线下面积为 0.812，预测良好结局的 AUC 为 0.790。添加临床特征并没有提高分类器的整体性能（对于生存：AUC=0.806，p=0.926；对于良好结局：AUC=0.777，p=0.844）。所有病因组均可以预测生存：HIE 患者的 AUC 为 0.958，TBI 和其他神经外科诊断患者的 AUC 为 0.955，代谢、炎症或感染导致意识障碍患者的 AUC 为 0.697，卒中患者的 AUC 为 0.695。在具有特定病因的患者亚组中分别训练分类器（因此使用较少的训练数据）会导致较差的分类性能。
尽管 HIE 和 TBI 患者的预后预测最佳，但我们的研究表明，类似的 EEG 标准可用于各种病因引起的意识障碍患者，并且训练集的大小比 ACI 病因的同质性更重要。
Zotero 插件
