Automatic classification of schizophrenia patients using resting-state EEG signals

EEG microstate biomarkers for schizophrenia: a novel approach using deep neural networks

Schizophrenia remains a challenging neuropsychiatric disorder with complex diagnostic processes. Current clinical approaches often rely on subjective assessments, highlighting the critical need for objective, quantitative diagnostic methods. This study aimed to develop a robust classification approach for schizophrenia using EEG microstate analysis and advanced machine learning techniques. We analyzed EEG signals from 14 healthy individuals and 14 patients with schizophrenia during a 15-min resting-state session across 19 EEG channels. A data augmentation strategy expanded the dataset to 56 subjects in each group. The signals were preprocessed and segmented into five frequency bands (delta, theta, alpha, beta, gamma) and five microstates (A, B, C, D, E) using k-means clustering. Five key features were extracted from each microstate: duration, occurrence, standard deviation, coverage, and frequency. A Deep Neural Network (DNN) model, along with other machine learning classifiers, was developed to classify the data. A comprehensive fivefold cross-validation approach evaluated model performance across various EEG channels, frequency bands, and feature combinations. Significant alterations in microstate transition probabilities were observed, particularly in higher frequency bands. The gamma band showed the most pronounced differences, with a notable disruption in D → A transitions (absolute difference = 0.100). The Random Forest classifier achieved the highest accuracy of 99.94% ± 0.12%, utilizing theta band features from the F8 frontal channel. The deep neural network model demonstrated robust performance with 98.31% ± 0.68% accuracy, primarily in the occipital region. Feature size 2 consistently provided optimal classification across most models. Our study introduces a novel, high-precision EEG microstate analysis approach for schizophrenia diagnosis, offering an objective diagnostic tool with potential applications in neuropsychiatric disorders. The findings reveal critical insights into neural dynamics associated with schizophrenia, demonstrating the potential for transforming clinical diagnostic practices through advanced machine learning and neurophysiological feature extraction.

Moving toward precision and personalized treatment strategies in psychiatry

Precision psychiatry aims to improve routine clinical practice by integrating biological, clinical, and environmental data. Many studies have been performed in different areas of research on major depressive disorder, bipolar disorder, and schizophrenia. Neuroimaging and electroencephalography findings have identified potential circuit-level abnormalities predictive of treatment response. Protein biomarkers, including IL-2, S100B, and NfL, and the kynurenine pathway illustrate the role of immune and metabolic dysregulation. Circadian rhythm disturbances and the gut microbiome have also emerged as critical transdiagnostic contributors to psychiatric symptomatology and outcomes. Moreover, advances in genomic research and polygenic scores support the perspective of personalized risk stratification and medication selection. While challenges remain, such as data replication issues, prediction model accuracy, and scalability, the progress so far achieved underscores the potential of precision psychiatry in improving diagnostic accuracy and treatment effectiveness.

Schizophrenia detection using distributed activation function-based statistical attentional bidirectional-long short-term memory

Schizophrenia detection involves identifying the schizophrenia by analyzing specific patterns in Electroencephalogram (EEG) signals, which reflect brain activity associated with symptoms, like hallucinations and cognitive impairments. Existing models face challenges due to the complex and variable nature of EEG data, which may struggle to accurately capture critical temporal dependencies and relevant features. Traditional approaches often lack adaptability, limiting their ability to differentiate schizophrenia patterns from other brain activities. Hence, a Distributed Activation function-based statistical Attention Bi-LSTM (DA-SA-BiLSTM) is proposed for schizophrenia detection, which enhances the precision and interpretability of EEG signal analysis. This model effectively manages the temporal dependencies for the detection as it incorporates past and future data context to improve decision-making. By dynamically weighting features based on their relevance, the model emphasizes critical segments and reduces noise, increasing predictive accuracy. Using different activation functions in various layers, the DA-AB-LSTM is allowed to adapt to specific characteristics of the EEG data, strengthening its flexibility and pattern recognition abilities. Furthermore, this model refines relationships between features, facilitating precise class probability distribution for schizophrenia classification. In particular, the DA-SA-BiLSTM model outperforms the existing models with 95.9 % accuracy, the lowest mean square error (MSE) of 5.86, 95.84 % sensitivity, and 95.97 % specificity.

A Machine-Learning-Based Analysis of Resting State Electroencephalogram Signals to Identify Latent Schizotypal and Bipolar Development in Healthy University Students

Background: Early and accurate diagnosis is crucial for effective prevention and treatment of severe mental illnesses, such as schizophrenia and bipolar disorder. However, identifying these conditions in their early stages remains a significant challenge. Our goal was to develop a method capable of detecting latent disease liability in healthy volunteers. Methods: Using questionnaires examining affective temperament and schizotypal traits among voluntary, healthy university students (N = 710), we created three groups. These were a group characterized by an emphasis on positive schizotypal traits (N = 20), a group showing cyclothymic temperament traits (N = 17), and a control group showing no susceptibility in either direction (N = 21). We performed a resting-state EEG examination as part of a complex psychological, electrophysiological, psychophysiological, and laboratory battery, and we developed feature-selection machine-learning methods to differentiate the low-risk groups. Results: Both low-risk groups could be reliably (with 90% accuracy) separated from the control group. Conclusions: Models applied to the data allowed us to differentiate between healthy university students with latent schizotypal or bipolar tendencies. Our research may improve the sensitivity and specificity of risk-state identification, leading to more effective and safer secondary prevention strategies for individuals in the prodromal phases of these disorders.

Common and differential EEG microstate of major depressive disorder patients with and without response to rTMS treatment

OBJECTIVE

Repetitive transcranial magnetic stimulation (rTMS) has recently emerged as a novel treatment option for patients with major depressive disorder (MDD), but clinical observations reveal variability in patient's responses to rTMS. Therefore, it is clinically significant to investigate the baseline neuroimaging differences between patients with (Responder) and without (NonResponder) response to rTMS treatment and predict rTMS treatment outcomes based on baseline neuroimaging data.

METHOD

Baseline resting-state EEG data and Beck Depression Inventory (BDI) were collected from 74 rTMS Responder, 43 NonResponder, and 47 matched healthy controls (HC). EEG microstate analysis was applied to analyze common and differential microstate characteristics of Responder and NonResponder. In addition, the microstate temporal parameters were sent to four machine learning models to classify Responder from NonResponder.

RESULT

There exists some common and differential EEG microstate characteristics for Responder and NonResponder. Specifically, compared to the HC group, both Responder and NonResponder exhibited a significant increase in the occurrence of microstate A. Only Responder showed an increase in the coverage of microstate A, occurrence of microstate D, transition probability (TP) from A to D, D to A, and C to A, and a decrease in the duration of microstates B and E, TP from A to B and C to B compared to HC. Only NonResponder exhibited a significant decrease in the duration of microstate D, TP from C to D, and an increase in the occurrence of microstate E, TP from C to E compared to HC. The primary differences between the Responder and NonResponder are that Responder had higher parameters for microstate D, TP from other microstates to D, and lower parameters for microstate E, TP from other microstates to E compared to NonResponder. Baseline parameters of microstate D showed significant correlation with Beck Depression Inventory (BDI) reduction rate. Additionally, these microstate features were sent to four machine learning models to predict rTMS treatment response and classification results indicate that an excellent predicting performance (accuracy = 97.35 %, precision = 96.31 %, recall = 100 %, F1 score = 98.06 %) was obtained when using AdaBoost model. These results suggest that baseline resting-state EEG microstate parameters could serve as robust indicators for predicting the effectiveness of rTMS treatment.

CONCLUSION

This study reveals significant baseline EEG microstate differences between rTMS Responder, NonResponder, and healthy controls. Microstates D and E in baseline EEG can serve as potential biomarkers for predicting rTMS treatment outcomes in MDD patients. These findings may aid in identifying patients likely to respond to rTMS, optimizing treatment plans and reducing trial-and-error approaches in therapy selection.

A comparative study of wavelet families for schizophrenia detection

Schizophrenia (SZ) is a chronic mental disorder, affecting approximately 1% of the global population, it is believed to result from various environmental factors, with psychological factors potentially influencing its onset and progression. Discrete wavelet transform (DWT)-based approaches are effective in SZ detection. In this report, we aim to investigate the effect of wavelet and decomposition levels in SZ detection. In our study, we analyzed the early detection of SZ using DWT across various decomposition levels, ranging from 1 to 5, with different mother wavelets. The electroencephalogram (EEG) signals are processed using DWT, which decomposes them into multiple frequency bands, yielding approximation and detail coefficients at each level. Statistical features are then extracted from these coefficients. The computed feature vector is then fed into a classifier to distinguish between SZ and healthy controls (HC). Our approach achieves the highest classification accuracy of 100% on a publicly available dataset, outperforming existing state-of-the-art methods.

EEG-based classification of Alzheimer's disease and frontotemporal dementia: a comprehensive analysis of discriminative features

Alzheimer's disease (AD) and frontotemporal dementia (FTD) are two main types of dementia. These diseases have similar symptoms, and they both may be considered as AD. Early detection of dementia and differential diagnosis between AD and FTD can lead to more effective management of the disease and contributes to the advancement of knowledge and potential treatments. In this approach, several features were extracted from electroencephalogram (EEG) signals of 36 subjects diagnosed with AD, 23 FTD subjects, and 29 healthy controls (HC). Mann-Whitney U-test and t-test methods were employed for the selection of the best discriminative features. The Fp1 channel for FTD patients exhibited the most significant differences compared to AD. In addition, connectivity features in the delta and alpha subbands indicated promising discrimination among these two groups. Moreover, for dementia diagnosis (AD + FTD vs. HC), central brain regions including Cz and Pz channels proved to be determining for the extracted features. Finally, four machine learning (ML) algorithms were utilized for the classification purpose. For differentiating between AD and FTD, and dementia diagnosis, an accuracy of 87.8% and 93.5% were achieved respectively, using the tenfold cross-validation technique and employing support vector machines (SVM) as the classifier.

Multiresolution feature fusion for smart diagnosis of schizophrenia in adolescents using EEG signals

Numerous studies on early detection of schizophrenia (SZ) have utilized all available channels or employed set of a few time domain or frequency domain features, while a limited number of features may not be sufficient enough to perform diagnosis efficiently. To encounter these problems, an automated diagnosis model is proposed for the efficient diagnosis of schizophrenia symptomatic adolescent subjects from electroencephalogram (EEG) signals via machine intelligence. A publicly accessible EEG dataset featuring 16-channels EEG obtained from 84 adolescents (45 SZ symptomatic and 39 healthy control) is used to demonstrate the work. Initially, the signals are decomposed into sub-bands using two multi-resolution signal analysis methods: Empirical Wavelet Transform and Empirical mode decomposition. 75 unique features from each sub-bands are extracted and the few selective prominent features are applied to machine learning classifiers for optimal sub-band selection. Subsequently, a hybrid model is proposed, combining convolutional neural network (CNN) and ensemble bagged tree, incorporating both deep learning and handcrafted features to perform SZ diagnosis. This innovative model achieved superior classification performance compared to existing methods, offering a promising approach for SZ diagnosis. Furthermore, the study explores the impact of different brain regions and combined regional data in SZ diagnosis comprehensively. Hence, this computer-assisted decision-making model minimizes the limitations of prior studies by providing a more robust and efficient diagnostic system for schizophrenia.

Detection of Schizophrenia from EEG Signals using Selected Statistical Moments of MFC Coefficients and Ensemble Learning

Schizophrenia is a mental disorder characterized by neurophysiological dysfunctions that result in disturbances in thinking, perception, and behavior. Early identification of schizophrenia can help prevent potential complications and facilitate effective treatment and management of the condition. This paper proposes a computer aided diagnosis system for the early detection of schizophrenia using 19-channel Electroencephalography (EEG) signals from 28 subjects, leveraging statistical moments of Mel-frequency Cepstral Coefficients (MFCC) and ensemble learning. Initially, the EEG signals are passed through a high-pass filter to mitigate noise and remove extraneous data. The feature extraction technique is then employed to extract MFC coefficients from the filtered EEG signals. The dimensionality of these coefficients is reduced by computing their statistical moments, which include the mean, standard deviation, skewness, kurtosis, and energy. Subsequently, the Support Vector Machine based Recursive Feature Elimination (SVM-RFE) is applied to identify pertinent features from the statistical moments of the MFC coefficients. These SVM-RFE-based selected features serve as input for three base classifiers: Support Vector Machine, k-Nearest Neighbors, and Logistic Regression. Additionally, an ensemble learning approach, which combines the predictions of the three classifiers through majority voting, is introduced to enhance schizophrenia detection performance and generalize the results of the proposed approach. The study's findings demonstrate that the ensemble model, combined with SVM-RFE-based selected statistical moments of MFCC, achieves encouraging detection performance, highlighting the potential of machine learning techniques in advancing the diagnostic process of schizophrenia.

ℛSCZ: A Riemannian schizophrenia diagnosis framework based on the multiplexity of EEG-based dynamic functional connectivity patterns

Abnormal electrophysiological (EEG) activity has been largely reported in schizophrenia (SCZ). In the last decade, research has focused to the automatic diagnosis of SCZ via the investigation of an EEG aberrant activity and connectivity linked to this mental disorder. These studies followed various preprocessing steps of EEG activity focusing on frequency-dependent functional connectivity brain network (FCBN) construction disregarding the topological dependency among edges. FCBN belongs to a family of symmetric positive definite (SPD) matrices forming the Riemannian manifold. Due to its unique geometric properties, the whole analysis of FCBN can be performed on the Riemannian geometry of the SPD space. The advantage of the analysis of FCBN on the SPD space is that it takes into account all the pairwise interdependencies as a whole. However, only a few studies have adopted a FCBN analysis on the SPD manifold, while no study exists on the analysis of dynamic FCBN (dFCBN) tailored to SCZ. In the present study, I analyzed two open EEG-SCZ datasets under a Riemannian geometry of SPD matrices for the dFCBN analysis proposing also a multiplexity index that quantifies the associations of multi-frequency brainwave patterns. I adopted a machine learning procedure employing a leave-one-subject-out cross-validation (LOSO-CV) using snapshots of dFCBN from (N-1) subjects to train a battery of classifiers. Each classifier operated in the inter-subject dFCBN distances of sample covariance matrices (SCMs) following a rhythm-dependent decision and a multiplex-dependent one. The proposed ℛSCZ decoder supported both the Riemannian geometry of SPD and the multiplexity index DC reaching an absolute accuracy (100 %) in both datasets in the virtual default mode network (DMN) source space.

Schizophrenia diagnosis based on diverse epoch size resting-state EEG using machine learning

Schizophrenia is a severe mental disorder that impairs a person's mental, social, and emotional faculties gradually. Detection in the early stages with an accurate diagnosis is crucial to remedying the patients. This study proposed a new method to classify schizophrenia disease in the rest state based on neurologic signals achieved from the brain by electroencephalography (EEG). The datasets used consisted of 28 subjects, 14 for each group, which are schizophrenia and healthy control. The data was collected from the scalps with 19 EEG channels using a 250 Hz frequency. Due to the brain signal variation, we have decomposed the EEG signals into five sub-bands using a band-pass filter, ensuring the best signal clarity and eliminating artifacts. This work was performed with several scenarios: First, traditional techniques were applied. Secondly, augmented data (additive white Gaussian noise and stretched signals) were utilized. Additionally, we assessed Minimum Redundancy Maximum Relevance (MRMR) as the features reduction method. All these data scenarios are applied with three different window sizes (epochs): 1, 2, and 5 s, utilizing six algorithms to extract features: Fast Fourier Transform (FFT), Approximate Entropy (ApEn), Log Energy entropy (LogEn), Shannon Entropy (ShnEn), and kurtosis. The L2-normalization method was applied to the derived features, positively affecting the results. In terms of classification, we applied four algorithms: K-nearest neighbor (KNN), support vector machine (SVM), quadratic discriminant analysis (QDA), and ensemble classifier (EC). From all the scenarios, our evaluation showed that SVM had remarkable results in all evaluation metrics with LogEn features utilizing a 1-s window size, impacting the diagnosis of Schizophrenia disease. This indicates that an accurate diagnosis of schizophrenia can be achieved through the right features and classification model selection. Finally, we contrasted our results to recently published works using the same and a different dataset, where our method showed a notable improvement.

Diagnosis of mental disorders using machine learning: Literature review and bibliometric mapping from 2012 to 2023

Background

Mental disorders (MDs) are becoming a leading burden in non-communicable diseases (NCDs). As per the World Health Organization's 2022 assessment report, there was a steep increase of 25 % in MDs during the COVID-19 pandemic. Early diagnosis of MDs can significantly improve treatment outcome and save disability-adjusted life years (DALYs). In recent times, the application of machine learning (ML) and deep learning (DL)) has shown promising results in the diagnosis of MDs, and the field has witnessed a huge research output in the form of research publications. Therefore, a bibliometric mapping along with a review of recent advancements is required.

Methods

This study presents a bibliometric analysis and review of the research, published over the last 10 years. Literature searches were conducted in the Scopus database for the period from January 1, 2012, to June 9, 2023. The data was filtered and screened to include only relevant and reliable publications. A total of 2811 journal articles were found. The data was exported to a comma-separated value (CSV) format for further analysis. Furthermore, a review of 40 selected studies was performed.

Results

The popularity of ML techniques in diagnosing MDs has been growing, with an annual research growth rate of 17.05 %. The Journal of Affective Disorders published the most documents (n = 97), while Wang Y. (n = 64) has published the most articles. Lotka's law is observed, with a minority of authors contributing the majority of publications. The top affiliating institutes are the West China Hospital of Sichuan University followed by the University of California, with China and the US dominating the top 10 institutes. While China has more publications, papers affiliated with the US receive more citations. Depression and schizophrenia are the primary focuses of ML and deep learning (DL) in mental disease detection. Co-occurrence network analysis reveals that ML is associated with depression, schizophrenia, autism, anxiety, ADHD, obsessive-compulsive disorder, and PTSD. Popular algorithms include support vector machine (SVM) classifier, decision tree classifier, and random forest classifier. Furthermore, DL is linked to neuroimaging techniques such as MRI, fMRI, and EEG, as well as bipolar disorder. Current research trends encompass DL, LSTM, generalized anxiety disorder, feature fusion, and convolutional neural networks.

Optimizing feature subset for schizophrenia detection using multichannel EEG signals and rough set theory

Schizophrenia (SZ) is a mental disorder that causes lifelong disorders based on delusions, cognitive deficits, and hallucinations. By visual assessment, SZ diagnosis is time-consuming and complicated, because brain states are more effectively revealed by electroencephalogram (EEG) signals, which are effectively used in SZ diagnosis. The application of existing deep learning methods in SZ detection is effective in the classification of 2-dimensional images, and these methods require more computational resources. Therefore, dimensionality reduction is necessary for SZ diagnosis using EEG signals. To reduce the dimensionality of the data, an improved CAO (ICAO) dimensionality reduction method is proposed, which integrates horizontal and vertical crossover approaches with AOA. The optimal feature subset is achieved by satisfying the ICAO conditions, and a fitness function is evaluated based on rough sets for improved accuracy in feature selection. Therefore a Crossover-boosted Archimedes optimization algorithm (AOA) with rough sets for Schizophrenia detection (CAORS-SD) was proposed using multichannel EEG signals from both SZ and normal patients. The signals are decomposed using multivariate empirical mode decomposition into multivariate intrinsic mode functions (MIMFs). Entropy metrics such as spectral entropy, permutation entropy, approximate entropy, sample entropy, and SVD entropy are evaluated on the MIMF domain to detect SZ. The processing time of the kernel support vector machine classifier is minimized with fewer features, reducing the risk Fof overfitting. Accuracy, sensitivity, specificity, precision, and F1-score of the CAORS-SD model should be conducted to diagnose SZ. Therefore, the proposed CAORS-SD method achieves the higher performance of accuracy, sensitivity, specificity, precision, and F1-score values of 96.34, 98.95, 96.86, 98.52, and 96.74% respectively. Also, the CAORS-SD method minimizes the error rate and significantly reduces the execution time.

Investigating the interpretability of schizophrenia EEG mechanism through a 3DCNN-based hidden layer features aggregation framework

BACKGROUND AND OBJECTIVE

Electroencephalogram (EEG) signals record brain activity, with growing interest in quantifying neural activity through complexity analysis as a potential biological marker for schizophrenia. Presently, EEG complexity analysis primarily relies on manual feature extraction, which is subjective and yields varied findings in studies involving schizophrenia and healthy controls.

METHODS

This study aims to leverage deep learning methods for enhanced EEG complexity exploration, aiding early schizophrenia screening and diagnosis. Our proposed approach utilizes a three-dimensional Convolutional Neural Network (3DCNN) to extract enhanced data features for early schizophrenia identification and subsequent complexity analysis. Leveraging the spatiotemporal capabilities of 3DCNN, we extract advanced latent features and employ knowledge distillation to reintegrate these features into the original channels, creating feature-enhanced data.

RESULTS

We employ a 10-fold cross-validation strategy, achieving the average accuracies of 99.46% and 98.06% in subject-dependent experiments on Dataset 1(14SZ and 14HC) and Dataset 2 (45SZ and 39HC). The average accuracy for subject-independent is 96.04% and 92.67% on both datasets. Feature extraction and classification are conducted on both the re-aggregated data and the original data. Our results demonstrate that re-aggregated data exhibit superior classification performance and a more stable training process after feature extraction. In the complexity analysis of re-aggregated data, we observe lower entropy features in schizophrenic patients compared to healthy controls, with more pronounced differences in the temporal and frontal lobes. Analyzing Katz's Fractal Dimension (KFD) across three sub-bands of lobe channels reveals the lowest α band KFD value in schizophrenia patients.

CONCLUSIONS

This emphasizes the ability of our method to enhance the discrimination and interpretability in schizophrenia detection and analysis. Our approach enhances the potential for EEG-based schizophrenia diagnosis by leveraging deep learning, offering superior discrimination capabilities and richer interpretive insights.

A systematic review of EEG based automated schizophrenia classification through machine learning and deep learning

The electroencephalogram (EEG) serves as an essential tool in exploring brain activity and holds particular importance in the field of mental health research. This review paper examines the application of artificial intelligence (AI), encompassing machine learning (ML) and deep learning (DL), for classifying schizophrenia (SCZ) through EEG. It includes a thorough literature review that addresses the difficulties, methodologies, and discoveries in this field. ML approaches utilize conventional models like Support Vector Machines and Decision Trees, which are interpretable and effective with smaller data sets. In contrast, DL techniques, which use neural networks such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs), are more adaptable to intricate EEG patterns but require significant data and computational power. Both ML and DL face challenges concerning data quality and ethical issues. This paper underscores the importance of integrating various techniques to enhance schizophrenia diagnosis and highlights AI's potential role in this process. It also acknowledges the necessity for collaborative and ethically informed approaches in the automated classification of SCZ using AI.

Automatic recognition of schizophrenia from brain-network features using graph convolutional neural network

Schizophrenia is a severe mental illness that imposes considerable economic burden on families and society. However, its clinical diagnosis primarily relies on scales and doctors' clinical experience and lacks an objective and accurate diagnostic approach. In recent years, graph convolutional neural networks (GCN) have been used to assist in psychiatric diagnosis owing to their ability to learn spatial-association information. Therefore, this study proposes a schizophrenia automatic recognition model based on graph convolutional neural network. Herein, the resting-state electroencephalography (EEG) data of 103 first-episode schizophrenia patients and 92 normal controls (NCs) were obtained. The automatic recognition model was trained with a nodal feature matrix that comprised the time and frequency-domain features of the EEG signals and local features of the brain network. The most significant regions that contributed to the model classification were identified, and the correlation between the node topological features of each significant region and clinical evaluation metrics was explored. Experiments were conducted to evaluate the performance of the model using 10-fold cross-validation. The best performance in the theta frequency band with a 6 s epoch length and phase-locked value. The recognition accuracy was 90.01%. The most significant region for identifying with first-episode schizophrenia patients and NCs was located in the parietal lobe. The results of this study verify the applicability of the proposed novel method for the identification and diagnosis of schizophrenia.

Weighted ordinal connection based functional network classification for schizophrenia disease detection using EEG signal

A brain connectivity network (BCN) is an advanced approach to examining brain functionality in various conditions. However, the predictability of the BCN is affected by the connectivity measure used for the network construction. Various connectivity measures available in the literature differ according to the domain of their working data. The application of random connectivity measures might result in an inefficient BCN that ultimately hampers its predictability. Therefore, selecting an appropriate functional connectivity metric is crucial in clinical as well as cognitive neuroscience. In parallel to this, an effective network identifier plays a vital role in distinguishing different brain states. Hence, the objective of this paper is two-fold, which includes identifying suitable connectivity measures and proposing an efficient network identifier. For this, the weighted BCN (WBCN) is constructed using multiple connectivity measures like correlation coefficient (r), coherence (COH), phase-locking value (PLV), and mutual information (MI) from electroencephalogram (EEG) signals. The most recent technique for feature extraction, i.e., weighted ordinal connections, has been applied to EEG-based BCN. EEG signals data has been taken from the schizophrenia disease database. Further, several classification algorithms such as k-nearest neighbours (KNN), support vector machine (SVM) with linear, radial basis function and polynomial kernels, random forest (RF), and 1D convolutional neural network (CNN1D) are used to classify the brain states based on extracted features. In classification, 90% accuracy is achieved by the CNN1D classifier with WBCN based on the coherence connectivity measure. The study also provides a structural analysis of the BCN.

Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals

Stress has an impact, not only on a person's physical health, but also on the ability to perform at the workplace in daily life. The well-established relation between psychological stress and its pathogeneses highlights the need for detecting psychological stress early, in order to prevent disease advancement and to save human lives. Electroencephalography (EEG) signal recording tools are widely used to collect these psychological signals/brain rhythms in the form of electric waves. The aim of the current research was to apply automatic feature extraction to decomposed multichannel EEG recordings, in order to efficiently detect psychological stress. The traditional deep learning techniques, namely the convolution neural network (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU) and recurrent neural network (RNN) models, have been frequently used for stress detection. A hybrid combination of these techniques may provide improved performance, and can handle long-term dependencies in non-linear brain signals. Therefore, this study proposed an integration of deep learning models, called DWT-based CNN, BiLSTM, and two layers of a GRU network, to extract features and classify stress levels. Discrete wavelet transform (DWT) analysis was used to remove the non-linearity and non-stationarity from multi-channel (14 channel) EEG recordings, and to decompose them into different frequency bands. The decomposed signals were utilized for automatic feature extraction using the CNN, and the stress levels were classified using BiLSTM and two layers of GRU. This study compared five combinations of the CNN, LSTM, BiLSTM, GRU and RNN models with the proposed model. The proposed hybrid model performed better in classification accuracy compared to the other models. Therefore, hybrid combinations are appropriate for the clinical intervention and prevention of mental and physical problems.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

A Survey on EEG Signal Processing Techniques and Machine Learning: Applications to the Neurofeedback of Autobiographical Memory Deficits in Schizophrenia

In this paper, a general overview regarding neural recording, classical signal processing techniques and machine learning classification algorithms applied to monitor brain activity is presented. Currently, several approaches classified as electrical, magnetic, neuroimaging recordings and brain stimulations are available to obtain neural activity of the human brain. Among them, non-invasive methods like electroencephalography (EEG) are commonly employed, as they can provide a high degree of temporal resolution (on the order of milliseconds) and acceptable space resolution. In addition, it is simple, quick, and does not create any physical harm or stress to patients. Concerning signal processing, once the neural signals are acquired, different procedures can be applied for feature extraction. In particular, brain signals are normally processed in time, frequency, and/or space domains. The features extracted are then used for signal classification depending on its characteristics such us the mean, variance or band power. The role of machine learning in this regard has become of key importance during the last years due to its high capacity to analyze complex amounts of data. The algorithms employed are generally classified in supervised, unsupervised and reinforcement techniques. A deep review of the most used machine learning algorithms and the advantages/drawbacks of most used methods is presented. Finally, a study of these procedures utilized in a very specific and novel research field of electroencephalography, i.e., autobiographical memory deficits in schizophrenia, is outlined.