A hybrid deep neural network for classification of schizophrenia using EEG Data

Sun, Jie; Cao, Rui; Zhou, Mengni; Hussain, Waqar; Wang, Bin; Xue, Jiayue; Xiang, Jie

doi:10.1038/s41598-021-83350-6

Cited by 105 publications

(54 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data on schizophrenic patients with deep learning were also classified by Sun et al [30]. Spectral-based CNN analyzes of schizophrenic patients were also performed in the study conducted by Sing et al [31].…”

Section: Discussionmentioning

confidence: 99%

Wavelet Based and Statistical EEG Analysis in Patients with Schizophrenia

Yılmaz¹

2021

View full text Add to dashboard Cite

Schizophrenia, which is considered a serious mental disorder and a psychological illness, is quite common in society today. Schizophrenia manifests itself with disordered thought development, hallucinations, and different behaviours and reactions. In this study, EEG data were collected and analyzed on a total of 84 subjects diagnosed with normal and schizophrenia. EEG data used as a diagnostic tool with low-resolution level has been used to distinguish between schizophrenic and normal individuals. First of all, statistical methods were used in the analyzes, and also frequency properties of the data were extracted by Wavelet analysis. As a result of the analysis, statistical findings include characteristics that distinguish between diagnosed schizophrenia and normal individuals. In addition, the findings obtained as a result of the Wavelet analysis were determined to distinguish between normal and schizophrenic individuals. While the mean used in statistical analysis takes the value 1.6 for normal individuals, it takes the value 2.9 for individuals diagnosed with schizophrenia. Also, in the results of Continuous Wavelet (CW) Analysis, very important findings were obtained in terms of detection in scale 16 and 64 bands.

show abstract

Section: Discussionmentioning

confidence: 99%

Wavelet Based and Statistical EEG Analysis in Patients with Schizophrenia

Yılmaz¹

2021

View full text Add to dashboard Cite

show abstract

“…CNNs have been used in problems such as speech recognition, image classification, recommender systems, and text classification. More recently, CNNs have been shown to classify EEG brain signals for autism [ 46 ], epilepsy [ 46 , 47 , 48 , 49 ], seizure detection in children [ 50 ], schizophrenia [ 51 ], brain–computer interface (BCI) [ 52 ], alcoholism predisposition [ 21 , 37 ], drowsiness detection [ 36 , 53 ], and neurodegeneration and physiological aging [ 54 ] into normal and pathological groups of young and old people.…”

Section: Methodsmentioning

confidence: 99%

Deep Convolutional Neural Network Regularization for Alcoholism Detection Using EEG Signals

Mukhtar

Qaisar

Zaguia

2021

Sensors

View full text Add to dashboard Cite

Alcoholism is attributed to regular or excessive drinking of alcohol and leads to the disturbance of the neuronal system in the human brain. This results in certain malfunctioning of neurons that can be detected by an electroencephalogram (EEG) using several electrodes on a human skull at appropriate positions. It is of great interest to be able to classify an EEG activity as that of a normal person or an alcoholic person using data from the minimum possible electrodes (or channels). Due to the complex nature of EEG signals, accurate classification of alcoholism using only a small dataset is a challenging task. Artificial neural networks, specifically convolutional neural networks (CNNs), provide efficient and accurate results in various pattern-based classification problems. In this work, we apply CNN on raw EEG data and demonstrate how we achieved 98% average accuracy by optimizing a baseline CNN model and outperforming its results in a range of performance evaluation metrics on the University of California at Irvine Machine Learning (UCI-ML) EEG dataset. This article explains the stepwise improvement of the baseline model using the dropout, batch normalization, and kernel regularization techniques and provides a comparison of the two models that can be beneficial for aspiring practitioners who aim to develop similar classification models in CNN. A performance comparison is also provided with other approaches using the same dataset.

show abstract

“…To overcome this phenomenon, future studies should use a high density EEG system ( 64 electrodes or 128 electrodes). There are different spectral features that can be used to classify the severity of SAD, including FFT, wavelet transform, power spectral density, and fuzzy entropy [74]. Future works are encouraged to use fused modality to categorize the severity of SAD (e.g., combining EEG with fNIRS).…”

Section: B Performance Analysis Of Classification Of 3-class Sad and Hc Using Deep Learning Modelsmentioning

confidence: 99%

Severity Assessment of Social Anxiety Disorder Using Deep Learning Models on Brain Effective Connectivity

et al. 2021

View full text Add to dashboard Cite

Neuroimaging investigations have proven that social anxiety disorder (SAD) is associated with aberrations in the connectivity of human brain functions.The assessment of the effective connectivity (EC) of the brain and its impact on the detection and medication of neurodegenerative pathophysiology is hence a crucial concern that needs to be addressed. Nevertheless, there are no clinically certain diagnostic biomarkers that can be linked to SAD. Therefore, investigating neural connectivity biomarkers of SAD based on deep learning models (DL) has a promising approach with its recent underlined potential results. In this study, an electroencephalography (EEG)-based detection model for SAD is constructed through directed causal influences combined with a deep convolutional neural network (CNN) and the long shortterm memory (LSTM). The EEG data were classified by applying three different DL models, namely, CNN, LSTM, and CNN+LSTM to discriminate the severity of SAD (severe, moderate, mild) and healthy controls (HC) at different frequency bands (delta, theta, alpha, low beta, and high beta) in the default mode network (DMN) under resting-state condition. The DL model uses the EC features as input, which are derived from the cortical correlation within different EEG rhythms for certain cortical areas that are more susceptible to SAD. Experimental results revealed that the proposed model (CNN+LSTM) outperforms the other models in SAD recognition. For our dataset, the highest recognition accuracies of 92.86%, 92.86%, 96.43%, and 89.29%, specificities of 95.24%, 95.24%, 100%, and 90.91%, and sensitivities of 85.71%, 85.71%, 87.50%, and 83.33% were achieved by using CNN+LSTM model for severe, moderate, mild, and HC, respectively. The fundamental contribution of this analysis is the characterization of neural brain features using different DL models to categorize the severity of SAD, which can represent a potential biomarker for SAD.INDEX TERMS Effective connectivity network, convolutional neural networks (CNNs), social anxiety disorder (SAD), default mode network (DMN), deep learning models, partial directed coherence (PDC), Electroencephalogram (EEG), human brain mapping.

show abstract

A hybrid deep neural network for classification of schizophrenia using EEG Data

Cited by 105 publications

References 50 publications

Wavelet Based and Statistical EEG Analysis in Patients with Schizophrenia

Wavelet Based and Statistical EEG Analysis in Patients with Schizophrenia

Deep Convolutional Neural Network Regularization for Alcoholism Detection Using EEG Signals

Severity Assessment of Social Anxiety Disorder Using Deep Learning Models on Brain Effective Connectivity

Contact Info

Product

Resources

About