Top-Down Disconnectivity in Schizophrenia During P300 Tasks

Disease-specific resting-state EEG network variations in schizophrenia revealed by the contrastive machine learning

Given a multitude of genetic and environmental factors, when investigating the variability in schizophrenia (SCZ) and the first-degree relatives (R-SCZ), latent disease-specific variation is usually hidden. To reliably investigate the mechanism underlying the brain deficits from the aspect of functional networks, we newly iterated a framework of contrastive variational autoencoders (cVAEs) applied in the contrasts among three groups, to disentangle the latent resting-state network patterns specified for the SCZ and R-SCZ. We demonstrated that the comparison in reconstructed resting-state networks among SCZ, R-SCZ, and healthy controls (HC) revealed network distortions of the inner-frontal hypoconnectivity and frontal-occipital hyperconnectivity, while the original ones illustrated no differences. And only the classification by adopting the reconstructed network metrics achieved satisfying performances, as the highest accuracy of 96.80% ± 2.87%, along with the precision of 95.05% ± 4.28%, recall of 98.18% ± 3.83%, and F1-score of 96.51% ± 2.83%, was obtained. These findings consistently verified the validity of the newly proposed framework for the contrasts among the three groups and provided related resting-state network evidence for illustrating the pathological mechanism underlying the brain deficits in SCZ, as well as facilitating the diagnosis of SCZ.

Discrimination of auditory verbal hallucination in schizophrenia based on EEG brain networks

Auditory verbal hallucinations (AVH) are a core positive symptom of schizophrenia and are regarded as a consequence of the functional breakdown in the related sensory process. Yet, the potential mechanism of AVH is still lacking. In the present study, we explored the difference between AVHs (n = 23) and non-AVHs (n = 19) in schizophrenia and healthy controls (n = 29) by using multidimensional electroencephalograms data during an auditory oddball task. Compared to healthy controls, both AVH and non-AVH groups showed reduced P300 amplitudes. Additionally, the results from brain networks analysis revealed that AVH patients showed reduced left frontal to posterior parietal/temporal connectivity compared to non-AVH patients. Moreover, using the fused network properties of both delta and theta bands as features for in-depth learning made it possible to identify the AVH from non-AVH patients at an accuracy of 80.95%. The left frontal-parietal/temporal networks seen in the auditory oddball paradigm might be underlying biomarkers of AVH in schizophrenia. This study demonstrated for the first time the functional breakdown of the auditory processing pathway in the AVH patients, leading to a better understanding of the atypical brain network of the AVH patients.

Antipsychotics-induced improvement of cool executive function in individuals living with schizophrenia

Cool executive dysfunction is a crucial feature in people living with schizophrenia which is related to cognition impairment and the severity of the clinical symptoms. Based on electroencephalogram (EEG), our current study explored the change of brain network under the cool executive tasks in individuals living with schizophrenia before and after atypical antipsychotic treatment (before_TR vs. after_TR). 21 patients with schizophrenia and 24 healthy controls completed the cool executive tasks, involving the Tower of Hanoi Task (THT) and Trail-Marking Test A-B (TMT A-B). The results of this study uncovered that the reaction time of the after_TR group was much shorter than that of the before_TR group in the TMT-A and TMT-B. And the after_TR group showed fewer error numbers in the TMT-B than those of the before_TR group. Concerning the functional network, stronger DMN-like linkages were found in the before_TR group compared to the control group. Finally, we adopted a multiple linear regression model based on the change network properties to predict the patient's PANSS change ratio. Together, the findings deepened our understanding of cool executive function in individuals living with schizophrenia and might provide physiological information to reliably predict the clinical efficacy of schizophrenia after atypical antipsychotic treatment.

Machine Learning Techniques for the Diagnosis of Schizophrenia Based on Event-Related Potentials

Antecedent

The event-related potential (ERP) components P300 and mismatch negativity (MMN) have been linked to cognitive deficits in patients with schizophrenia. The diagnosis of schizophrenia could be improved by applying machine learning procedures to these objective neurophysiological biomarkers. Several studies have attempted to achieve this goal, but no study has examined Multiple Kernel Learning (MKL) classifiers. This algorithm finds optimally a combination of kernel functions, integrating them in a meaningful manner, and thus could improve diagnosis.

Objective

This study aimed to examine the efficacy of the MKL classifier and the Boruta feature selection method for schizophrenia patients (SZ) and healthy controls (HC) single-subject classification.

Methods

A cohort of 54 SZ and 54 HC participants were studied. Three sets of features related to ERP signals were calculated as follows: peak related features, peak to peak related features, and signal related features. The Boruta algorithm was used to evaluate the impact of feature selection on classification performance. An MKL algorithm was applied to address schizophrenia detection.

Results

A classification accuracy of 83% using the whole dataset, and 86% after applying Boruta feature selection was obtained. The variables that contributed most to the classification were mainly related to the latency and amplitude of the auditory P300 paradigm.

Conclusion

This study showed that MKL can be useful in distinguishing between schizophrenic patients and controls when using ERP measures. Moreover, the use of the Boruta algorithm provides an improvement in classification accuracy and computational cost.

Altered temporal variability in brain functional connectivity identified by fuzzy entropy underlines schizophrenia deficits

Investigation of the temporal variability of resting-state brain networks informs our understanding of how neural connectivity aggregates and disassociates over time, further shedding light on the aberrant neural interactions that underlie symptomatology and psychosis development. In the current work, an electroencephalogram-based sliding window analysis was utilized for the first time to measure the nonlinear complexity of dynamic resting-state brain networks of schizophrenia (SZ) patients by applying fuzzy entropy. The results of this study demonstrated the attenuated temporal variability among multiple electrodes that were distributed in the frontal and right parietal lobes for SZ patients when compared with healthy controls (HCs). Meanwhile, a concomitant strengthening of the posterior and peripheral flexible connections that may be attributed to the excessive alertness or sensitivity of SZ patients to the external environment was also revealed. These temporal fluctuation distortions combined reflect an abnormality in the coordination of functional network switching in SZ, which is further the source of worse task performance (i.e., P300 amplitude) and the negative relationship between individual complexity metrics and P300 amplitude. Notably, when using the network metrics as features, multiple linear regressions of P300 amplitudes were also exactly achieved for both the SZ and HC groups. These findings shed light on the pathophysiological mechanisms of SZ from a temporal variability perspective and provide potential biomarkers for quantifying SZ's progressive neurophysiological deterioration.

A survey of brain network analysis by electroencephalographic signals

Brain network analysis is one efficient tool in exploring human brain diseases and can differentiate the alterations from comparative networks. The alterations account for time, mental states, tasks, individuals, and so forth. Furthermore, the changes determine the segregation and integration of functional networks that lead to network reorganization (or reconfiguration) to extend the neuroplasticity of the brain. Exploring related brain networks should be of interest that may provide roadmaps for brain research and clinical diagnosis. Recent electroencephalogram (EEG) studies have revealed the secrets of the brain networks and diseases (or disorders) within and between subjects and have provided instructive and promising suggestions and methods. This review summarized the corresponding algorithms that had been used to construct functional or effective networks on the scalp and cerebral cortex. We reviewed EEG network analysis that unveils more cognitive functions and neural disorders of the human and then explored the relationship between brain science and artificial intelligence which may fuel each other to accelerate their advances, and also discussed some innovations and future challenges in the end.

Mismatch Negativity and P3a Impairment through Different Phases of Schizophrenia and Their Association with Real-Life Functioning

Impairment in functioning since the onset of psychosis and further deterioration over time is a key aspect of subjects with schizophrenia (SCZ). Mismatch negativity (MMN) and P3a, indices of early attention processing that are often impaired in schizophrenia, might represent optimal electrophysiological candidate biomarkers of illness progression and poor outcome. However, contrasting findings are reported about the relationships between MMN-P3a and functioning. The study aimed to investigate in SCZ the influence of illness duration on MMN-P3a and the relationship of MMN-P3a with functioning. Pitch (p) and duration (d) MMN-P3a were investigated in 117 SCZ and 61 healthy controls (HCs). SCZ were divided into four illness duration groups: ≤ 5, 6 to 13, 14 to 18, and 19 to 32 years. p-MMN and d-MMN amplitude was reduced in SCZ compared to HCs, independently from illness duration, psychopathology, and neurocognitive deficits. p-MMN reduction was associated with lower "Work skills". The p-P3a amplitude was reduced in the SCZ group with longest illness duration compared to HCs. No relationship between P3a and functioning was found. Our results suggested that MMN amplitude reduction might represent a biomarker of poor functioning in SCZ.

Investigating the Relationships of P3b with Negative Symptoms and Neurocognition in Subjects with Chronic Schizophrenia

Neurocognitive deficits and negative symptoms (NS) have a pivotal role in subjects with schizophrenia (SCZ) due to their impact on patients' functioning in everyday life and their influence on goal-directed behavior and decision-making. P3b is considered an optimal electrophysiological candidate biomarker of neurocognitive impairment for its association with the allocation of attentional resources to task-relevant stimuli, an important factor for efficient decision-making, as well as for motivation-related processes. Furthermore, associations between P3b deficits and NS have been reported. The current research aims to fill the lack of studies investigating, in the same subjects, the associations of P3b with multiple cognitive domains and the expressive and motivation-related domains of NS, evaluated with state-of-the-art instruments. One hundred and fourteen SCZ and 63 healthy controls (HCs) were included in the study. P3b amplitude was significantly reduced and P3b latency prolonged in SCZ as compared to HCs. In SCZ, a positive correlation was found between P3b latency and age and between P3b amplitude and the Attention-vigilance domain, while no significant correlations were found between P3b and the two NS domains. Our results indicate that the effortful allocation of attention to task-relevant stimuli, an important component of decision-making, is compromised in SCZ, independently of motivation deficits or other NS.

Advanced Signal Processing Methods for Characterization of Schizophrenia

OBJECTIVE

Schizophrenia is a severe mental disorder associated with nerobiological deficits. Auditory oddball P300 have been found to be one of the most consistent markers of schizophrenia. The goal of this study is to find quantitative features that can objectively distinguish patients with schizophrenia (SCZs) from healthy controls (HCs) based on their recorded auditory odd-ball P300 electroencephalogram (EEG) data.

METHODS

Using EEG dataset, we develop a machine learning (ML) algorithm to distinguish 57 SCZs from 66 HCs. The proposed ML algorithm has three steps. In the first step, a brain source localization (BSL) procedure using the linearly constrained minimum variance (LCMV) beamforming approach is employed on EEG signals to extract source waveforms from 30 specified brain regions. In the second step, a method for estimating effective connectivity, referred to as symbolic transfer entropy (STE), is applied to the source waveforms. In the third step the ML algorithm is applied to the STE connectivity matrix to determine whether a set of features can be found that successfully discriminate SCZ from HC.

RESULTS

The findings revealed that the SCZs have significantly higher effective connectivity compared to HCs and the selected STE features could achieve an accuracy of 92.68%, with a sensitivity of 92.98% and specificity of 92.42%.

CONCLUSION

The findings imply that the extracted features are from the regions that are mainly affected by SCZ and can be used to distinguish SCZs from HCs.

SIGNIFICANCE

The proposed ML algorithm may prove to be a promising tool for the clinical diagnosis of schizophrenia.

Discrimination of Tourette Syndrome Based on the Spatial Patterns of the Resting-State EEG Network

Tourette syndrome (TS) is a neuropsychiatric disorder with childhood onset characterized by chronic motor and vocal tics; however, the current diagnosis of TS patients is subjective, as it is mainly assessed based on the parents' description alongside specific evaluations. The early and accurate diagnosis of TS based on its potential symptoms in children would be of benefit in their future therapy, but reliable diagnoses are difficult due to the lack of objective knowledge of the etiology and pathogenesis of TS. In this study, resting-state electroencephalograms were first collected from 36 patients and 21 healthy controls (HCs); the corresponding resting-state functional networks were then constructed, and the potential differences in network topology between the two groups were extracted by using the topology of the spatial pattern of the network (SPN). Compared to the HCs, the TS patients exhibited decreased frontotemporal/occipital/parietal connectivity. When classifying the two groups, compared to the network properties, the derived SPN features achieved a much higher accuracy of 92.31%. The intrinsic long-range connectivity between the frontal and the temporal/occipital/parietal lobes was damaged in the patient group, and this dysfunctional network pattern might serve as a reliable biomarker to differentiate TS patients from HCs as well as to assess the severity of tic symptoms.

Measuring the Non-linear Directed Information Flow in Schizophrenia by Multivariate Transfer Entropy

People living with schizophrenia (SCZ) experience severe brain network deterioration. The brain is constantly fizzling with non-linear causal activities measured by electroencephalogram (EEG) and despite the variety of effective connectivity methods, only few approaches can quantify the direct non-linear causal interactions. To circumvent this problem, we are motivated to quantitatively measure the effective connectivity by multivariate transfer entropy (MTE) which has been demonstrated to be able to capture both linear and non-linear causal relationships effectively. In this work, we propose to construct the EEG effective network by MTE and further compare its performance with the Granger causal analysis (GCA) and Bivariate transfer entropy (BVTE). The simulation results quantitatively show that MTE outperformed GCA and BVTE under varied signal-to-noise conditions, edges recovered, sensitivity, and specificity. Moreover, its applications to the P300 task EEG of healthy controls (HC) and SCZ patients further clearly show the deteriorated network interactions of SCZ, compared to that of the HC. The MTE provides a novel tool to potentially deepen our knowledge of the brain network deterioration of the SCZ.

Different Contexts in the Oddball Paradigm Induce Distinct Brain Networks in Generating the P300

Despite the P300 event-related potential (ERP) differences between distinct stimulus sequences, the effect of stimulus sequence on the brain network is still left unveiled. To uncover the corresponding effect of stimulus sequence, we thus investigated the differences of functional brain networks, when a target (T) or standard (S) stimulus was presented preceding another T as background context. Results of this study demonstrated that, when an S was first presented preceding a T (i.e., ST sequence), the P300 experiencing large amplitude was evoked by the T, along with strong network architecture. In contrast, if a T was presented in advance [i.e., target-to-target (TT) sequence], decreased P300 amplitude and attenuated network efficiency were demonstrated. Additionally, decreased activations in regions, such as inferior frontal gyrus and superior frontal gyrus were also revealed in TT sequence. Particularly, the effect of stimulus sequence on P300 network could be quantitatively measured by brain network properties, the increase in network efficiency corresponded to large P300 amplitude evoked in P300 task.

Transition of brain networks from an interictal to a preictal state preceding a seizure revealed by scalp EEG network analysis

Epilepsy is a neurological disorder in the brain that is characterized by unprovoked seizures. Epileptic seizures are attributed to abnormal synchronous neuronal activity in the brain. To detect the seizure as early as possible, the identification of specific electroencephalogram (EEG) dynamics is of great importance in investigating the transition of brain activity as the epileptic seizure approaches. In this study, we investigated the transition of brain activity from interictal to preictal states preceding a seizure by combining EEG network and clustering analyses together in different frequency bands. The findings of this study demonstrated the best clustering performance of k-medoids in the beta band; in addition, compared to the interictal state, the preictal state experienced increased synchronization of EEG network connectivity, characterized by relatively higher network properties. These findings can provide helpful insight into the mechanism of epilepsy, which can also be used in the prediction of epileptic seizures and subsequent intervention.