Luján Miguel Ángel, Mateo Sotos Jorge, Torres Ana, Santos José L, Quevedo Oscar, Borja Alejandro L
Departamento de Ingeniería Eléctrica, Automática y Comunicaciones, Universidad de Castilla-La Mancha, Electrónica, 02071 Albacete, Spain.
Instituto de Tecnología, Construcción y Telecomunicaciones, Universidad de Castilla-La Mancha, 16071 Cuenca, Spain.
J Med Biol Eng. 2022;42(6):853-859. doi: 10.1007/s40846-022-00758-9. Epub 2022 Nov 11.
In this paper, a new automated procedure based on deep learning methods for schizophrenia diagnosis is presented.
To this aim, electroencephalogram signals obtained using a 32-channel helmet are prominently used to analyze high temporal resolution information from the brain. By these means, the data collected is employed to evaluate the class likelihoods using a neuronal network based on radial basis functions and a fuzzy means algorithm.
The results obtained with real datasets validate the high accuracy of the proposed classification method. Thus, effectively characterizing the changes in EEG signals acquired from schizophrenia patients and healthy volunteers. More specifically, values of accuracy better than 93% has been obtained in the present research. Additionally, a comparative study with other approaches based on well-knows machine learning methods shows that the proposed method provides better results than recently proposed algorithms in schizophrenia detection.
The proposed method can be used as a diagnostic tool in the detection of the schizophrenia, helping for early diagnosis and treatment.
本文提出了一种基于深度学习方法的用于精神分裂症诊断的新自动化程序。
为此，使用32通道头盔获取的脑电图信号被显著用于分析来自大脑的高时间分辨率信息。通过这些手段，收集到的数据被用于使用基于径向基函数的神经网络和模糊均值算法来评估类别似然性。
使用真实数据集获得的结果验证了所提出分类方法的高精度。因此，有效地表征了从精神分裂症患者和健康志愿者获取的脑电图信号的变化。更具体地说，在本研究中获得了优于93%的准确率值。此外，与基于知名机器学习方法的其他方法的比较研究表明，所提出的方法在精神分裂症检测中比最近提出的算法提供了更好的结果。
所提出的方法可作为精神分裂症检测中的诊断工具，有助于早期诊断和治疗。
