Mumtaz Wajid, Vuong Pham Lam, Xia Likun, Malik Aamir Saeed, Rashid Rusdi Bin Abd
Center for Intelligent Signal and Imaging Research (CISIR), Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, 32610 Bandar Seri Iskandar, Perak Malaysia.
Beijing Institute of Technology, Beijing, 100081 China.
Cogn Neurodyn. 2017 Apr;11(2):161-171. doi: 10.1007/s11571-016-9416-y. Epub 2016 Oct 24.
Screening alcohol use disorder (AUD) patients has been challenging due to the subjectivity involved in the process. Hence, robust and objective methods are needed to automate the screening of AUD patients. In this paper, a machine learning method is proposed that utilized resting-state electroencephalography (EEG)-derived features as input data to classify the AUD patients and healthy controls and to perform automatic screening of AUD patients. In this context, the EEG data were recorded during 5 min of eyes closed and 5 min of eyes open conditions. For this purpose, 30 AUD patients and 15 aged-matched healthy controls were recruited. After preprocessing the EEG data, EEG features such as inter-hemispheric coherences and spectral power for EEG delta, theta, alpha, beta and gamma bands were computed involving 19 scalp locations. The selection of most discriminant features was performed with a rank-based feature selection method assigning a weight value to each feature according to a criterion, i.e., receiver operating characteristics curve. For example, a feature with large weight was considered more relevant to the target labels than a feature with less weight. Therefore, a reduced set of most discriminant features was identified and further be utilized during classification of AUD patients and healthy controls. As results, the inter-hemispheric coherences between the brain regions were found significantly different between the study groups and provided high classification efficiency ( = 80.8, = 82.5, = 80, - = 0.78). In addition, the power computed in different EEG bands were found significant and provided an overall classification efficiency as ( = 86.6, = 95, = 82.5, - = 0.88). Further, the integration of these EEG feature resulted into even higher results ( = 89.3 %, = 88.5 %, = 91 %, - = 0.90). Based on the results, it is concluded that the EEG data (integration of the theta, beta, and gamma power and inter-hemispheric coherence) could be utilized as objective markers to screen the AUD patients and healthy controls.
由于酒精使用障碍（AUD）患者筛查过程中涉及主观性，因此具有挑战性。因此，需要强大而客观的方法来实现AUD患者筛查的自动化。本文提出了一种机器学习方法，该方法利用静息态脑电图（EEG）衍生特征作为输入数据，对AUD患者和健康对照进行分类，并对AUD患者进行自动筛查。在此背景下，在闭眼5分钟和睁眼5分钟的条件下记录EEG数据。为此，招募了30名AUD患者和15名年龄匹配的健康对照。在对EEG数据进行预处理后，计算了涉及19个头皮位置的EEG特征，如半球间相干性以及EEGδ、θ、α、β和γ频段的频谱功率。使用基于秩的特征选择方法进行最具判别力特征的选择，该方法根据一个标准（即受试者工作特征曲线）为每个特征分配一个权重值。例如，权重较大的特征被认为比权重较小的特征与目标标签更相关。因此，确定了一组减少的最具判别力特征，并在AUD患者和健康对照的分类过程中进一步使用。结果发现，研究组之间脑区之间的半球间相干性存在显著差异，并提供了较高的分类效率（=80.8，=82.5，=80，-=0.78）。此外，发现在不同EEG频段计算的功率具有显著性，并提供了总体分类效率为（=86.6，=95，=82.5，-=0.88）。此外，这些EEG特征的整合产生了更高的结果（=89.3%，=
