Investigation of Machine Learning and Deep Learning Approaches for Detection of Mild Traumatic Brain Injury from Human Sleep Electroencephalogram.
Investigation of Machine Learning and Deep Learning Approaches for Detection of Mild Traumatic Brain Injury from Human Sleep Electroencephalogram.
复制标题
从人类睡眠脑电图中检测轻度创伤性脑损伤的机器学习和深度学习方法的研究。
DOI：
10.1109/embc46164.2021.9630423
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Cao,Hung
中科院分区：
文献类型：
--
作者：
Vishwanath,Manoj;Jafarlou,Salar;Shin,Ikhwan;Dutt,Nikil;Rahmani,AmirM;Jones,CarolynE;Lim,MirandaM;Cao,Hung
创伤性脑损伤（TBI）是一个非常普遍且严重的公共卫生问题。大多数 TBI 病例性质较轻，但有些人可能会出现后续持续性残疾。持续性脑震荡后症状患者的病理生理原因很可能是多因素的，其潜在机制尚不清楚，但很明显，睡眠障碍在持续性残疾患者中表现突出。睡眠脑电图 (EEG) 为了解高度刻板的行为状态期间的神经元活动提供了一个直接窗口，并且代表了一种有前景的 TBI 诊断和预后定量测量方法。随着机器学习、深度卷积神经网络领域的不断发展以及更好架构的发展，这些方法有望解决推荐系统和/或健康监测系统中个性化医疗的一些长期根深蒂固的挑战。特别是，用于识别神经系统疾病的推定脑电图生物标志物的高级脑电图分析可能与轻度 TBI 的预测高度相关，轻度 TBI 是一种具有广泛受影响表型和残疾水平的异质性疾病。在这项工作中，我们研究了各种机器学习技术和深度神经网络架构在一组人类受试者身上的使用情况，这些受试者的睡眠脑电图记录来自夜间、实验室内诊断性多导睡眠图 (PSG)。探索了 TBI 与非 TBI 对照受试者分类的最佳方案。当使用少量受试者（10 名 mTBI 受试者和 9 名年龄和性别匹配的对照）使用适当的参数时，结果令人鼓舞，随机抽样安排的准确度为 95%，独立验证安排的准确度为 70%。因此，我们相信，通过额外的数据和进一步的研究，我们将能够建立一个通用模型来准确检测 TBI，不仅可以通过有人值守的实验室内 PSG 记录，还可以在实际场景中，例如从日常生活中的简单可穿戴设备获得的脑电图数据。
Traumatic Brain Injury (TBI) is a highly prevalent and serious public health concern. Most cases of TBI are mild in nature, yet some individuals may develop following-up persistent disability. The pathophysiologic causes for those with persistent postconcussive symptoms are most likely multifactorial and the underlying mechanism is not well understood, although it is clear that sleep disturbances feature prominently in those with persistent disability. The sleep electroencephalogram (EEG) provides a direct window into neuronal activity during an otherwise highly stereotyped behavioral state, and represents a promising quantitative measure for TBI diagnosis and prognosis. With the ever-evolving domain of machine learning, deep convolutional neural networks, and the development of better architectures, these approaches hold promise to solve some of the long entrenched challenges of personalized medicine for uses in recommendation systems and/or in health monitoring systems. In particular, advanced EEG analysis to identify putative EEG biomarkers of neurological disease could be highly relevant in the prognostication of mild TBI, an otherwise heterogeneous disorder with a wide range of affected phenotypes and disability levels. In this work, we investigate the use of various machine learning techniques and deep neural network architectures on a cohort of human subjects with sleep EEG recordings from overnight, in-lab, diagnostic polysomnography (PSG). An optimal scheme is explored for the classification of TBI versus non-TBI control subjects. The results were promising with an accuracy of ∼95% in random sampling arrangement and ∼70% in independent validation arrangement when appropriate parameters were used using a small number of subjects (10 mTBI subjects and 9 age- and sex-matched controls). We are thus confident that, with additional data and further studies, we would be able to build a generalized model to detect TBI accurately, not only via attended, in-lab PSG recordings, but also in practical scenarios such as EEG data obtained from simple wearables in daily life.