Classifying Schizotypy Using an Audiovisual Emotion Perception Test and Scalp Electroencephalography

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.

Emotional anticipation for dynamic emotional faces is not modulated by schizotypal traits: A Representational Momentum study

Schizotypy, a personality structure that resembles schizophrenia symptoms, is often associated with abnormal facial emotion perception. Based on the prevailing sense of threat in psychotic experiences, and the immediate perceptual history of seeing others' facial expressions, individuals with high schizotypal traits may exhibit a heightened tendency to anticipate anger. To test this, we used insights from Representational Momentum (RM), a perceptual phenomenon in which the endpoint of a dynamic event is systematically displaced forward, into the immediate future. Angry-to-ambiguous and happy-to-ambiguous avatar faces were presented, each followed by a probe with the same (ambiguous) expression as the endpoint, or one slightly changed to express greater happiness/anger. Participants judged if the probe was "equal" to the endpoint and rated how confident they were. The sample was divided into high (N = 46) and low (N = 49) schizotypal traits using the Schizotypal Personality Questionnaire (SPQ). First, a forward bias was found in happy-to-ambiguous faces, suggesting emotional anticipation solely for dynamic faces changing towards a potential threat (anger). This may reflect an adaptative mechanism, as it is safer to anticipate any hostility from a conspecific than the opposite. Second, contrary to our hypothesis, high schizotypal traits did not heighten RM for happy-to-ambiguous faces, nor did they lead to overconfidence in biased judgements. This may suggest a typical pattern of emotional anticipation in non-clinical schizotypy, but caution is needed due to the use of self-report questionnaires, university students, and a modest sample size. Future studies should also investigate if the same holds for clinical manifestations of schizophrenia.

Prominent genetic variants and epigenetic changes in post-traumatic stress disorder among combat veterans

Post-traumatic stress disorder (PTSD) is one of the most widespread and disabling psychiatric disorders among combat veterans. Substantial interindividual variability in susceptibility to PTSD suggests the presence of different risk factors for this disorder. Twin and family studies confirm genetic factors as important risk factors for PTSD. In addition to genetic factors, epigenetic factors, especially DNA methylation, can be considered as a potential mechanism in changing the risk of PTSD. So far, many genetic and epigenetic association studies have been conducted in relation to PTSD. In genetic studies, many single nucleotide polymorphisms have been identified as PTSD risk factors. Meanwhile, the variations in catecholamines-related genes, serotonin transporter and receptors, brain-derived neurotrophic factor, inflammatory factors, and apolipoprotein E are the most prominent candidates. CpG methylation in the upstream regions of many genes is also considered a PTSD risk factor. Accurate identification of genetic and epigenetic changes associated with PTSD can lead to the presentation of suitable biomarkers for susceptible individuals to this disorder. This study aimed to delineate prominent genetic variations and epigenetic changes associated with post-traumatic stress disorder in military veterans who have experienced combat, focusing on genetic and epigenetic association studies.

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.

Assisting schizophrenia diagnosis using clinical electroencephalography and interpretable graph neural networks: a real-world and cross-site study

Schizophrenia (SCZ) is a chronic and serious mental disorder with a high mortality rate. At present, there is a lack of objective, cost-effective and widely disseminated diagnosis tools to address this mental health crisis globally. Clinical electroencephalogram (EEG) is a noninvasive technique to measure brain activity with high temporal resolution, and accumulating evidence demonstrates that clinical EEG is capable of capturing abnormal SCZ neuropathology. Although EEG-based automated diagnostic tools have obtained impressive performance on individual datasets, the transportability of potential EEG biomarkers in cross-site real-world application is still an open question. To address the challenges of small sample sizes and population heterogeneity, we develop an advanced interpretable deep learning model using multimodal clinical EEG features and demographic information as inputs to graph neural networks, and further propose different transfer learning strategies to adapt to different clinical scenarios. Taking the disease discrimination of health control (HC) and SCZ with 1030 participants as a use case, our model is trained on a small clinical dataset (N = 188, Chinese) and enhanced using a large-scale public dataset (N = 508, American) of adult participants. Cross-site validation from an independent dataset of adult participants (N = 157, Chinese) produced stable performance, with AUCs of 0.793-0.852 and accuracies of 0.786-0.858 for different SCZ prevalence, respectively. In addition, cross-site validation from another dataset of adolescent boys (N = 84, Russian) yielded an AUC of 0.702 and an accuracy of 0.690. Moreover, feature visualization further revealed that the ranking of feature importance varied significantly among different datasets, and that EEG theta and alpha band power appeared to be the most significant and translational biomarkers of SCZ pathology. Overall, our promising results demonstrate the feasibility of SCZ discrimination using EEG biomarkers in multiple clinical settings.

Graph-based analysis of EEG for schizotypy classification applying flicker Ganzfeld stimulation

Ganzfeld conditions induce alterations in brain function and pseudo-hallucinatory experiences, particularly in people with high positive schizotypy. The current study uses graph-based parameters to investigate and classify brain networks under Ganzfeld conditions as a function of positive schizotypy. Participants from the general population (14 high schizotypy (HS), 29 low schizotypy (LS)) had an electroencephalography assessment during Ganzfeld conditions, with varying visual activation (8 frequencies of random light flicker) and soundscape-induced mood (neutral, serenity, and anxiety). Weighted functional networks were computed in six frequency sub-bands (delta, theta, alpha-low, alpha-high, beta, and gamma) as a function of light-flicker frequency and mood. The brain network was analyzed using graph theory parameters, including clustering coefficient (CC), strength, and global efficiency (GE). It was found that the LS groups had higher CC and strength than the HS groups, especially in bilateral temporal and frontotemporal brain regions. Moreover, some decreases in CC and strength measures were found in LS groups among occipital and parieto-occipital brain regions. LS groups also had significantly higher GE in all Ganzfeld conditions compared to the HS groups. The random under-sampling boosting (RUSBoost) algorithm achieved the best classification performance with an accuracy of 95.34%, specificity of 96.55%, and sensitivity of 92.85% during an anxiety-induction Ganzfeld condition. This is the first exploration of the relationship between brain functional state changes under Ganzfeld conditions in individuals who vary in positive schizotypy. The accuracy of graph-based parameters in classifying brain states as a function of schizotypy is shown, particularly for brain activity during anxiety induction, and should be investigated in psychosis.

Tensor factorization approach for ERP-based assessment of schizotypy in a novel auditory oddball task on perceived family stress

Objective. Schizotypy, a potential phenotype for schizophrenia, is a personality trait that depicts psychosis-like signs in the normal range of psychosis continuum. Family communication may affect the social functioning of people with schizotypy. Greater family stress, such as irritability, criticism and less praise, is perceived at a higher level of schizotypy. This study aims to determine the differences between people with high and low levels of schizotypy using electroencephalography (EEG) during criticism, praise and neutral comments. EEGs were recorded from 29 participants in the general community who varied from low schizotypy to high schizotypy (HS) during a novel emotional auditory oddball task.Approach. We consider the difference in event-related potential parameters, namely the amplitude and latency of P300 subcomponents (P3a and P3b), between pairs of target words (standard, positive, negative and neutral). A model based on tensor factorization is then proposed to detect these components from the EEG using the CANDECOMP/PARAFAC decomposition technique. Finally, we employ the mutual information estimation method to select influential features for classification.Main results.The highest classification accuracy, sensitivity, and specificity of 93.1%, 94.73%, and 90% are obtained via leave-one-out cross validation.Significance. This is the first attempt to investigate the identification of individuals with psychometrically-defined HS from brain responses that are specifically associated with perceiving family stress and schizotypy. By measuring these brain responses to social stress, we achieve the goal of improving the accuracy in detection of early episodes of psychosis.

Classification of Low and High Schizotypy Levels via Evaluation of Brain Connectivity

Schizotypy is a latent cluster of personality traits that denote a vulnerability for schizophrenia or a type of spectrum disorder. The aim of the study is to investigate parametric effective brain connectivity features for classifying high versus low schizotypy (LS) status. Electroencephalography (EEG) signals are recorded from 13 high schizotypy (HS) and 11 LS participants during an emotional auditory odd-ball task. The brain connectivity signals for machine learning are taken after the settlement of event-related potentials. A multivariate autoregressive (MVAR)-based connectivity measure is estimated from the EEG signals using the directed transfer functions (DTFs) method. The values of DTF power in five standard frequency bands are used as features. The support vector machines (SVMs) revealed significant differences between HS and LS. The accuracy, specificity, and sensitivity of the results using SVM are as high as 89.21%, 90.3%, and 88.2%, respectively. Our results demonstrate that the effective brain connectivity in prefrontal/parietal and prefrontal/frontal brain regions considerably changes according to schizotypal status. These findings prove that the brain connectivity indices offer valuable biomarkers for detecting schizotypal personality. Further monitoring of the changes in DTF following the diagnosis of schizotypy may lead to the early identification of schizophrenia and other spectrum disorders.

Predicting subclinical psychotic-like experiences on a continuum using machine learning

Previous studies applying machine learning methods to psychosis have primarily been concerned with the binary classification of chronic schizophrenia patients and healthy controls. The aim of this study was to use electroencephalographic (EEG) data and pattern recognition to predict subclinical psychotic-like experiences on a continuum between these two extremes in otherwise healthy people. We applied two different approaches to an auditory oddball regularity learning task obtained from N = 73 participants: A feature extraction and selection routine incorporating behavioural measures, event-related potential components and effective connectivity parameters; Regularisation of spatiotemporal maps of event-related potentials. Using the latter approach, optimal performance was achieved using the response to frequent, predictable sounds. Features within the P50 and P200 time windows had the greatest contribution toward lower Prodromal Questionnaire (PQ) scores and the N100 time window contributed most to higher PQ scores. As a proof-of-concept, these findings demonstrate that EEG data alone are predictive of individual psychotic-like experiences in healthy people. Our findings are in keeping with the mounting evidence for altered sensory responses in schizophrenia, as well as the notion that psychosis may exist on a continuum expanding into the non-clinical population.

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

Schizophrenia is a serious mental illness that causes great harm to patients, so timely and accurate detection is essential. This study aimed to identify a better feature to represent electroencephalography (EEG) signals and improve the classification accuracy of patients with schizophrenia and healthy controls by using EEG signals. Our research method involves two steps. First, the EEG time series is preprocessed, and the extracted time-domain and frequency-domain features are transformed into a sequence of red-green-blue (RGB) images that carry spatial information. Second, we construct hybrid deep neural networks (DNNs) that combine convolution neural networks and long short-term memory to address RGB images to classify schizophrenic patients and healthy controls. The results show that the fuzzy entropy (FuzzyEn) feature is more significant than the fast Fourier transform (FFT) feature in brain topography. The deep learning (DL) method that we propose achieves an average accuracy of 99.22% with FuzzyEn and an average accuracy of 96.34% with FFT. These results show that the best effect is to extract fuzzy features as input features from EEG time series and then use a hybrid DNN for classification. Compared with the most advanced methods in this field, significant improvements have been achieved.

Effects of an Audiovisual Emotion Perception Training for Schizophrenia: A Preliminary Study

Individuals with schizophrenia show a reduced ability to integrate facial and vocal information in emotion perception. Although emotion perception has been a target for treatment, no study has yet examined the effect of multimodal training on emotion perception in schizophrenia. In the present study, we developed an audiovisual emotion perception training and test in which a voice and a face were simultaneously presented, and subjects were asked to judge whether the emotions of the voice and the face matched. The voices were either angry or happy, and the faces were morphed on a continuum ranging from angry to happy. Sixteen patients with schizophrenia participated in six training sessions and three test sessions (i.e., pre-training, post-training, and generalization). Eighteen healthy controls participated only in pre-training test session. Prior to training, the patients with schizophrenia performed significantly worse than did the controls in the recognition of anger; however, following the training, the patients showed a significant improvement in recognizing anger, which was maintained and generalized to a new set of stimuli. The patients also improved the recognition of happiness following the training, but this effect was not maintained or generalized. These results provide preliminary evidence that a multimodal, audiovisual training may yield improvements in anger perception for patients with schizophrenia.

Multivariate patterns of EEG microstate parameters and their role in the discrimination of patients with schizophrenia from healthy controls

Quasi-stable electrical fields in the EEG, called microstates carry information on the dynamics of large scale brain networks. Using machine learning techniques, we explored whether abnormalities in microstates can be used to classify patients with schizophrenia and healthy controls. We applied multivariate pattern analysis of microstate features to create a specified feature set to represent microstate characteristics. Machine learning approaches using these features for classification of patients with schizophrenia were compared with prior EEG based machine learning studies. Our microstate segmentation in both patients with schizophrenia and healthy controls yielded topographies that were similar to the normative database established earlier by Koenig et al. Our machine learning model was based on large sample size, low number of features and state-of-art K-fold cross-validation technique. The multivariate analysis revealed three patterns of correlated features, which yielded an AUC of 0.84 for the group separation (accuracy: 82.7%, sensitivity/specificity: 83.5%/85.3%). Microstate segmentation of resting state EEG results in informative features to discriminate patients with schizophrenia from healthy individuals. Moreover, alteration in microstate measures may represent disturbed activity of networks in patients with schizophrenia.

Perspectives on Machine Learning for Classification of Schizotypy Using fMRI Data

Functional magnetic resonance imaging is capable of estimating functional activation and connectivity in the human brain, and lately there has been increased interest in the use of these functional modalities combined with machine learning for identification of psychiatric traits. While these methods bear great potential for early diagnosis and better understanding of disease processes, there are wide ranges of processing choices and pitfalls that may severely hamper interpretation and generalization performance unless carefully considered. In this perspective article, we aim to motivate the use of machine learning schizotypy research. To this end, we describe common data processing steps while commenting on best practices and procedures. First, we introduce the important role of schizotypy to motivate the importance of reliable classification, and summarize existing machine learning literature on schizotypy. Then, we describe procedures for extraction of features based on fMRI data, including statistical parametric mapping, parcellation, complex network analysis, and decomposition methods, as well as classification with a special focus on support vector classification and deep learning. We provide more detailed descriptions and software as supplementary material. Finally, we present current challenges in machine learning for classification of schizotypy and comment on future trends and perspectives.