Dewi Sari Rahmawati Kusuma, Li Yu-Chuan Jack, Lin Ming-Ching
Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, New Taipei City, Taiwan.
Department of Neurosurgery, Wan Fang Hospital, Taipei Medical University, New Taipei City, Taiwan.
Stud Health Technol Inform. 2025 Aug 7;329:1870-1871. doi: 10.3233/SHTI251256.
Brain response to command can be detected using task-based EEG. Insufficient evidence of brain response and prognosis remain happen in brain infarction. This preliminary study aimed to explore brain response in task-based electroencephalography (EEG) and the 6-month responsiveness in brain infarction. Interestingly, we detected brain response in 58.59% of clinically responsive patients and 6.25% of unresponsive patients. The presence of brain response in clinically unresponsive patient indicates brain activation despite the absence of responsiveness in Glasgow Coma Scale (GCS) assessment. This descriptive and comparison analysis highlights the utility of EEG-based machine learning to identify brain response in brain infarction patients, providing insights for further investigation related to brain injury prognosis, rehabilitation strategy, and management.
使用基于任务的脑电图（EEG）可以检测大脑对指令的反应。在脑梗死中，大脑反应和预后的证据仍然不足。这项初步研究旨在探索基于任务的脑电图（EEG）中的大脑反应以及脑梗死患者6个月后的反应性。有趣的是，我们在58.59%的临床有反应的患者和6.25%的无反应的患者中检测到了大脑反应。临床无反应患者中大脑反应的存在表明，尽管格拉斯哥昏迷量表（GCS）评估无反应，但大脑仍被激活。这种描述性和比较性分析突出了基于脑电图的机器学习在识别脑梗死患者大脑反应方面的效用，为进一步研究脑损伤预后、康复策略和管理提供了见解。
