Khare Smith K, Bajaj Varun
Electronics and Communication Discipline, Indian Institute of Information Technology Design and Manufacturing, Jabalpur, MP, 482005, India.
Electronics and Communication Discipline, Indian Institute of Information Technology Design and Manufacturing, Jabalpur, MP, 482005, India.
Comput Biol Med. 2022 Feb;141:105028. doi: 10.1016/j.compbiomed.2021.105028. Epub 2021 Nov 17.
Schizophrenia (SCZ) is a serious neurological condition in which people suffer with distorted perception of reality. SCZ may result in a combination of delusions, hallucinations, disordered thinking, and behavior. This causes permanent disability and hampers routine functioning. Trained neurologists use interviewing and visual inspection techniques for the detection and diagnosis of SCZ. These techniques are manual, time-consuming, subjective, and error-prone. Therefore, there is a need to develop an automatic model for SCZ classification. The aim of this study is to develop an automated SCZ classification model using electroencephalogram (EEG) signals. The EEG signals can capture the changes in neural dynamics of human cognition during SCZ.
Based on the nature of the SCZ condition, the EEG signals must be examined. For accurate interpretation of EEG signals during SCZ, an automated model integrating a robust variational mode decomposition (RVMD) and an optimized extreme learning machine (OELM) classifier is developed. Traditional VMD suffers from noisy mode generation, mode duplication, under segmentation, and mode discarding. These problems are suppressed in RVMD by automating the selection of quadratic penalty factor (α) and a number of modes (L). The hyperparameters (HPM) of the OELM classifier are automatically selected to ensure maximum accuracy for each mode without overfitting or underfitting. For the selection of α and L in RVMD and HPM in the OELM classifier, a whale optimization algorithm is used. The root mean square error is minimized for RVMD and classification accuracy of each mode is maximized for the OELM classifier. The EEG signals of three conditions performing basic sensory tasks have been analyzed to detect SCZ.
The Kruskal Wallis test is used to select different features extracted from the modes produced by RVMD. An OELM classifier is tested using a ten-fold cross-validation technique. An accuracy, precision, specificity, F-1 measure, sensitivity, and Cohen's Kappa of 92.93%, 93.94%, 91.06% 94.07%, 97.15%, and 85.32% are obtained.
The third mode's chaotic features helped to capture the significant changes that occurred during the SCZ state. The findings of the RVMD-OELM-based hybrid decision support system can help neuro-experts for the accurate identification of SCZ in real-time scenarios.
精神分裂症（SCZ）是一种严重的神经系统疾病，患者会出现对现实的扭曲认知。SCZ可能导致妄想、幻觉、思维紊乱和行为异常等多种症状，会造成永久性残疾并妨碍日常功能。训练有素的神经科医生通过访谈和视觉检查技术来检测和诊断SCZ。这些技术是人工操作的，耗时、主观且容易出错。因此，需要开发一种用于SCZ分类的自动模型。本研究的目的是利用脑电图（EEG）信号开发一种自动的SCZ分类模型。EEG信号可以捕捉SCZ期间人类认知神经动力学的变化。
基于SCZ病症的性质，必须对EEG信号进行检查。为了在SCZ期间准确解释EEG信号，开发了一种集成了稳健变分模态分解（RVMD）和优化极限学习机（OELM）分类器的自动模型。传统的VMD存在噪声模态生成、模态复制、分割不足和模态丢弃等问题。在RVMD中，通过自动选择二次惩罚因子（α）和模态数量（L）来抑制这些问题。自动选择OELM分类器的超参数（HPM），以确保每种模态都具有最高的准确性，且不会出现过拟合或欠拟合。对于RVMD中α和L的选择以及OELM分类器中HPM的选择，使用了鲸鱼优化算法。使RVMD的均方根误差最小化，并使OELM分类器对每种模态的分类准确率最大化。分析了执行基本感觉任务的三种状态下的EEG信号以检测SCZ。
使用Kruskal Wallis检验来选择从RVMD产生的模态中提取的不同特征。使用十折交叉验证技术对OELM分类器进行测试。获得的准确率、精确率、特异性、F1分数、灵敏度和科恩卡帕系数分别为92.93%、93.94%、91.06%、94.07%、97.15%和85.32%。
第三种模态的混沌特征有助于捕捉SCZ状态期间发生的显著变化。基于RVMD - OELM的混合决策支持系统的研究结果可以帮助神经专家在实际场景中准确实时识别SCZ。
