Macroscopic Cluster Organizations Change the Complexity of Neural Activity

Spike timing-dependent plasticity under imbalanced excitation and inhibition reduces the complexity of neural activity

Excitatory and inhibitory neurons are fundamental components of the brain, and healthy neural circuits are well balanced between excitation and inhibition (E/I balance). However, it is not clear how an E/I imbalance affects the self-organization of the network structure and function in general. In this study, we examined how locally altered E/I balance affects neural dynamics such as the connectivity by activity-dependent formation, the complexity (multiscale entropy) of neural activity, and information transmission. In our simulation, a spiking neural network model was used with the spike-timing dependent plasticity rule to explore the above neural dynamics. We controlled the number of inhibitory neurons and the inhibitory synaptic weights in a single neuron group out of multiple neuron groups. The results showed that a locally increased E/I ratio strengthens excitatory connections, reduces the complexity of neural activity, and decreases information transmission between neuron groups in response to an external input. Finally, we argued the relationship between our results and excessive connections and low complexity of brain activity in the neuropsychiatric brain disorders.

Detecting autism from picture book narratives using deep neural utterance embeddings

BACKGROUND

Deficits in the ability to use language in social contexts, including storytelling skills, are observed across the autism spectrum. Development in machine-learning approaches may contribute to clinical psychology and psychiatry, given its potential to support decisions concerning the diagnosis and treatment of psychiatric conditions and disorders.

AIMS

To evaluate the usefulness of deep neural networks for detecting autism spectrum disorder (ASD) from textual utterances, specifically from narrations produced by individuals with ASD.

METHODS & PROCEDURES

We examined two text encoders: Embeddings from Language Models (ELMo) and Universal Sentence Encoder (USE), and three classification algorithms: XGBoost, support vector machines, and dense neural network layer. We aimed to classify 25 participants with ASD and 25 participants with typical development (TD) based on their narrations produced during the Autism Diagnostic Observation Schedule, Second Edition (ADOS-2) picture book task. The results of computational approaches were compared with the results of standardized testing and classifications made by two psychiatrists (raters). The raters were asked to read utterances produced by a participant (without an examiner's statements and additional information) and assign a participant to one of the two groups: ASD or with typical development (TD).

OUTCOMES & RESULTS

The computer-based models had higher sensitivity, specificity, positive predictive values and negative predictive values than the raters, and lower than the two standardized instruments: ADOS-2 and Social Communication Questionnaire (SCQ).

CONCLUSIONS & IMPLICATIONS

Our findings lay the groundwork for future studies involving deep neural network-based text representation models as tools for augmenting the ASD diagnosis or screening. Both ELMo and USE text encoders provided promising specificities, sensitivities, positive predictive values and negative predictive values. Our results indicate the usefulness of page-level embeddings for utterance representation in ADOS-2 picture book task.

WHAT THIS PAPER ADDS

What is already known on this subject Deficits in the use of language in social contexts, and narrative ability in particular, are observed across the autism spectrum. Most research on narrative skills has applied hand-coding methods. Hitherto, machine-learning methods were used mostly for image recognition problems and data from screening questionnaires for ASD classification. Detection of mental and developmental disorders from textual input is an emerging field for machine and deep-learning methods. What this paper adds to existing knowledge This study explored the ability of several types of deep neural network-based text representation models to detect ASD. Both ELMo and USE provided the most promising values of specificity, sensitivity, positive predictive values and negative predictive values. What are the potential or actual clinical implications of this work? Competitive accuracy, repeatability, speed and ease of operation are all advantages of computerized methods. They allow for objective and quantitative assessment of narrative ability and complex language skills. Deep neural network-based text representation models could in the future support clinicians and augment the decision-making process related to ASD diagnosis, screening and intervention planning.

Single and Cross-Disorder Detection for Autism and Schizophrenia

Detection of mental disorders from textual input is an emerging field for applied machine and deep learning methods. Here, we explore the limits of automated detection of autism spectrum disorder (ASD) and schizophrenia (SCZ). We compared the performance of: (1) dedicated diagnostic tools that involve collecting textual data, (2) automated methods applied to the data gathered by these tools, and (3) psychiatrists. Our article tests the effectiveness of several baseline approaches, such as bag of words and dictionary-based vectors, followed by a machine learning model. We employed two more refined Sentic text representations using affective features and concept-level analysis on texts. Further, we applied selected state-of-the-art deep learning methods for text representation and inference, as well as experimented with transfer and zero-shot learning. Finally, we also explored few-shot methods dedicated to low data size scenarios, which is a typical problem for the clinical setting. The best breed of automated methods outperformed human raters (psychiatrists). Cross-dataset approaches turned out to be useful (only from SCZ to ASD) despite different data types. The few-shot learning methods revealed promising results on the SCZ dataset. However, more effort is needed to explore the approaches to efficiently training models, given the very limited amounts of labeled clinical data. Psychiatry is one of the few medical fields in which the diagnosis of most disorders is based on the subjective assessment of a psychiatrist. Therefore, the introduction of objective tools supporting diagnostics seems to be pivotal. This paper is a step in this direction.

Functional differentiations in evolutionary reservoir computing networks

We propose an extended reservoir computer that shows the functional differentiation of neurons. The reservoir computer is developed to enable changing of the internal reservoir using evolutionary dynamics, and we call it an evolutionary reservoir computer. To develop neuronal units to show specificity, depending on the input information, the internal dynamics should be controlled to produce contracting dynamics after expanding dynamics. Expanding dynamics magnifies the difference of input information, while contracting dynamics contributes to forming clusters of input information, thereby producing multiple attractors. The simultaneous appearance of both dynamics indicates the existence of chaos. In contrast, the sequential appearance of these dynamics during finite time intervals may induce functional differentiations. In this paper, we show how specific neuronal units are yielded in the evolutionary reservoir computer.

Spatiotemporal complexity patterns of resting-state bioelectrical activity explain fluid intelligence: Sex matters

Neural complexity is thought to be associated with efficient information processing but the exact nature of this relation remains unclear. Here, the relationship of fluid intelligence (gf) with the resting-state EEG (rsEEG) complexity over different timescales and different electrodes was investigated. A 6-min rsEEG blocks of eyes open were analyzed. The results of 119 subjects (57 men, mean age = 22.85 ± 2.84 years) were examined using multivariate multiscale sample entropy (mMSE) that quantifies changes in information richness of rsEEG in multiple data channels at fine and coarse timescales. gf factor was extracted from six intelligence tests. Partial least square regression analysis revealed that mainly predictors of the rsEEG complexity at coarse timescales in the frontoparietal network (FPN) and the temporo-parietal complexities at fine timescales were relevant to higher gf. Sex differently affected the relationship between fluid intelligence and EEG complexity at rest. In men, gf was mainly positively related to the complexity at coarse timescales in the FPN. Furthermore, at fine and coarse timescales positive relations in the parietal region were revealed. In women, positive relations with gf were mostly observed for the overall and the coarse complexity in the FPN, whereas negative associations with gf were found for the complexity at fine timescales in the parietal and centro-temporal region. These outcomes indicate that two separate time pathways (corresponding to fine and coarse timescales) used to characterize rsEEG complexity (expressed by mMSE features) are beneficial for effective information processing.

Classification Methods Based on Complexity and Synchronization of Electroencephalography Signals in Alzheimer's Disease

Electroencephalography (EEG) has long been studied as a potential diagnostic method for Alzheimer's disease (AD). The pathological progression of AD leads to cortical disconnection. These disconnections may manifest as functional connectivity alterations, measured by the degree of synchronization between different brain regions, and alterations in complex behaviors produced by the interaction among wide-spread brain regions. Recently, machine learning methods, such as clustering algorithms and classification methods, have been adopted to detect disease-related changes in functional connectivity and classify the features of these changes. Although complexity of EEG signals can also reflect AD-related changes, few machine learning studies have focused on the changes in complexity. Therefore, in this study, we compared the ability of EEG signals to detect characteristics of AD using different machine learning approaches one focused on functional connectivity and the other focused on signal complexity. We examined functional connectivity, estimated by phase lag index (PLI) in EEG signals in healthy older participants [healthy control (HC)] and patients with AD. We estimated signal complexity using multi-scale entropy. Utilizing a support vector machine, we compared the identification accuracy of AD based on functional connectivity at each frequency band and complexity component. Additionally, we evaluated the relationship between synchronization and complexity. The identification accuracy of functional connectivity of the alpha, beta, and gamma bands was significantly high (AUC 1.0), and the identification accuracy of complexity was sufficiently high (AUC 0.81). Moreover, the relationship between functional connectivity and complexity exhibited various temporal-scale-and-regional-specific dependency in both HC participants and patients with AD. In conclusion, the combination of functional connectivity and complexity might reflect complex pathological process of AD. Applying a combination of both machine learning methods to neurophysiological data may provide a novel understanding of the neural network processes in both healthy brains and pathological conditions.

Temporal-specific complexity of spiking patterns in spontaneous activity induced by a dual complex network structure

Temporal fluctuation of neural activity in the brain has an important function in optimal information processing. Spontaneous activity is a source of such fluctuation. The distribution of excitatory postsynaptic potentials (EPSPs) between cortical pyramidal neurons can follow a log-normal distribution. Recent studies have shown that networks connected by weak synapses exhibit characteristics of a random network, whereas networks connected by strong synapses have small-world characteristics of small path lengths and large cluster coefficients. To investigate the relationship between temporal complexity spontaneous activity and structural network duality in synaptic connections, we executed a simulation study using the leaky integrate-and-fire spiking neural network with log-normal synaptic weight distribution for the EPSPs and duality of synaptic connectivity, depending on synaptic weight. We conducted multiscale entropy analysis of the temporal spiking activity. Our simulation demonstrated that, when strong synaptic connections approach a small-world network, specific spiking patterns arise during irregular spatio-temporal spiking activity, and the complexity at the large temporal scale (i.e., slow frequency) is enhanced. Moreover, we confirmed through a surrogate data analysis that slow temporal dynamics reflect a deterministic process in the spiking neural networks. This modelling approach may improve the understanding of the spatio-temporal complex neural activity in the brain.