Temporal Connectivity Research Articles

Conducting stock market index prediction via the localized spatial–temporal convolutional network

The stock index movement prediction is a fundamental research issue in financial investment. The high-noise and dynamic of stock data make this problem challenging. Efficiently modeling the underlying spatial–temporal correlations between indices is a potential study area for raising the prediction performance. Existing methods usually use separate modules to capture spatial and temporal correlations, which lose sight of local spatial–temporal correlation. In this paper, we propose a brand-new prediction model named the localized graph convolutional network (LoGCN) for stock index forecasting. This model can represent the intricate local spatial–temporal connections via a well-designed convolution mechanism. First, the localized graph construction method is proposed to model the local spatial–temporal correlations. Then, the localized graph convolutional module is presented to fuse the impact of different indices. Finally, the fully connected network is put forward to transform the features into the expected index trends. 42 Chinese stock market indices were selected to conduct extensive experiments. Three evaluation metrics including the increase rate regression, further trends classification, and stock market back-testing were adopted to the experimental comparison. The experiments show that our method is 4.2%, 3.1%, and 40% better than conventional methods under these three metrics.

Effects of post-acute COVID-19 syndrome on the functional brain networks of non-hospitalized individuals.

The long-term impact of COVID-19 on brain function remains poorly understood, despite growing concern surrounding post-acute COVID-19 syndrome (PACS). The goal of this cross-sectional, observational study was to determine whether there are significant alterations in resting brain function among non-hospitalized individuals with PACS, compared to symptomatic individuals with non-COVID infection. Data were collected for 51 individuals who tested positive for COVID-19 (mean age 41±12 yrs., 34 female) and 15 controls who had cold and flu-like symptoms but tested negative for COVID-19 (mean age 41±14 yrs., 9 female), with both groups assessed an average of 4-5 months after COVID testing. None of the participants had prior neurologic, psychiatric, or cardiovascular illness. Resting brain function was assessed via functional magnetic resonance imaging (fMRI), and self-reported symptoms were recorded. Individuals with COVID-19 had lower temporal and subcortical functional connectivity relative to controls. A greater number of ongoing post-COVID symptoms was also associated with altered functional connectivity between temporal, parietal, occipital and subcortical regions. These results provide preliminary evidence that patterns of functional connectivity distinguish PACS from non-COVID infection and correlate with the severity of clinical outcome, providing novel insights into this highly prevalent disorder.

Global spatio-temporal synergistic topology learning for skeleton-based action recognition

Compared to RGB video-based action recognition, skeleton-based action recognition algorithm has attracted much more attention due to being more lightweight, better generalization and robustness. The extraction of temporal and spatial features is a crucial factor for skeleton-based action recognition. However, existing feature extraction methods suffer from two limitations: (1) the isolated extraction of temporal and spatial feature cannot capture temporal feature connections among non-adjacent joints and (2) convolution-limited perceptual fields cannot capture global temporal features of joints effectively. In this work, we propose a global spatio-temporal synergistic feature learning module (GSTL), which generates global spatio-temporal synergistic topology of joints by spatio-temporal feature fusion. By further combining the GSTL with a temporal modeling unit, we develop a powerful global spatio-temporal synergistic topology learning network (GSTLN), and it achieves competitive performance with fewer parameters on three challenge datasets: NTU RGB + D, NTU RGB + D 120, and NW-UCLA.

Altered Postcentral Connectivity after Sleep Deprivation Correlates to Impaired Risk Perception: A Resting-State Functional Magnetic Resonance Imaging Study.

Previous studies revealed that sleep deprivation (SD) impairs risk perception and leads to poor decision-making efficiency. However, how risk perception is related to brain regions' communication after SD has not been elucidated. In this study, we investigated the neuropsychological mechanisms of SD-impaired risk perception. Nineteen healthy male adults were recruited and underwent resting-state functional magnetic resonance imaging during a state of rested wakefulness and after nearly 36 h of total SD. They then completed the balloon analog risk task, which was used to measure the risk perception ability of risky decision-making. Regional homogeneity (ReHo) and voxel-wise functional connectivity were used to investigate neurobiological changes caused by SD. Correlation analysis was used to investigate the relationship between changes in ReHo, function, and risk perception. At the behavioral level, risk perception decreased after 36 h of SD. At the neural level, SD induced a significant increase in ReHo in the right postcentral gyrus and was positively correlated with risk perception changes. The functional connectivity between the right postcentral gyrus, left medial temporal gyrus, and right inferior temporal gyrus was enhanced. Critically, increased right postcentral gyrus and right inferior temporal gyrus connectivity positively correlated with changes in risk perception. SD impairs the risk perception associated with altered postcentral connectivity. The brain requires more energy to process and integrate sensory and perceptual information after SD, which may be one possible reason for decreased risk perception ability after SD.

Integration of time and space in historical prose

The article comprehensively analyzes that time and space are a set of mobile concepts. In historical novels, the essence of the connection between space and time is highlighted. A deep analysis of the specifics of the originality of the relationship of space and time in historical works has been carried out. Since the very nature of the work is formed into a historical event, the relationship between space and time is self-organized here. In describing and depicting the historical situation in the established chronology, the author proposes a peculiar model. For example, in the historiography of Genghis Khan, a broad commentary on the era is given. The author goes beyond the time and space outlined by him, describes the period before the birth of Genghis Khan, analyzes and completes the details, comparing the time in the story with the period of major events. At the same time, all types of models of space and time are intertwined in the work. Since the historical novel is built mainly on truthful data, documentary, consistent materials, the originality of the spatial, temporal connection is emphasized here. The article seeks concreteness, consistency, convergence of the author between artistic time and real time, differentiation of dynamic events, establishment of relations of the past, present and future.       Keywords: space, time, relativistic concept, habitat, parent settlement &nbsp

A Generalized Density-Based Algorithm for the Spatiotemporal Tracking of Drought Events

Abstract Drought events evolve simultaneously in space and time; hence, a proper characterization of an event requires the tracking of its full spatiotemporal evolution. Here we present a generalized algorithm for the tracking of drought events based on a three-dimensional application of the DBSCAN (density-based spatial clustering of applications with noise) clustering approach. The need for a generalized and flexible algorithm is dictated by the absence of a unanimous consensus on the definition of a drought event, which often depends on the target of the study. The proposed methodology introduces a set of six parameters that control both the spatial and the temporal connectivity between cells under drought conditions, also accounting for the local intensity of the drought itself. The capability of the algorithm to adapt to different drought definitions is tested successfully over a study case in Australia in the period 2017–20 using a set of standardized precipitation index (SPI) data derived from the ERA5 precipitation reanalysis. Insights on the possible range of variability of the model parameters, as well as on their effects on the delineation of drought events, are provided for the case of meteorological droughts in order to incentivize further applications of the methodology.

High levels of childhood trauma associated with changes in hippocampal functional activity and connectivity in young adults during novelty salience

Childhood trauma (CT) has been linked to increased risk for psychosis. Moreover, CT has been linked to psychosis phenotypes such as impaired cognitive and sensory functions involved in the detection of novel sensory stimuli. Our objective was to investigate if CT was associated with changes in hippocampal and superior temporal gyrus functional activation and connectivity during a novelty detection task. Fifty-eight young adults were assigned to High-CT (n = 28) and Low-CT (n = 24) groups based on their scores on the childhood trauma questionnaire (CTQ) and underwent functional Magnetic Resonance Imaging during an auditory oddball task (AOT). Relative to the Low CT group, High CT participants showed reduced functional activation in the left hippocampus during the unpredictable tone condition of the AOT. Furthermore, in the High CT group, psychophysiological interaction analysis revealed hypoconnectivity between the hippocampus and temporal and medial regions. The present study indicates both altered hippocampal activation and hippocampal-temporal-prefrontal connectivity during novelty detection in individuals that experienced CT, similarly to that reported in psychosis risk populations. Early stressful experiences and environments may alter hippocampal function during salient events, mediating the relationship between childhood trauma and psychosis risk.

A deep residual model for characterization of 5D spatiotemporal network dynamics reveals widespread spatiodynamic changes in schizophrenia.

Schizophrenia is a severe brain disorder with serious symptoms including delusions, disorganized speech, and hallucinations that can have a long-term detrimental impact on different aspects of a patient's life. It is still unclear what the main cause of schizophrenia is, but a combination of altered brain connectivity and structure may play a role. Neuroimaging data has been useful in characterizing schizophrenia, but there has been very little work focused on voxel-wise changes in multiple brain networks over time, despite evidence that functional networks exhibit complex spatiotemporal changes over time within individual subjects. Recent studies have primarily focused on static (average) features of functional data or on temporal variations between fixed networks; however, such approaches are not able to capture multiple overlapping networks which change at the voxel level. In this work, we employ a deep residual convolutional neural network (CNN) model to extract 53 different spatiotemporal networks each of which captures dynamism within various domains including subcortical, cerebellar, visual, sensori-motor, auditory, cognitive control, and default mode. We apply this approach to study spatiotemporal brain dynamism at the voxel level within multiple functional networks extracted from a large functional magnetic resonance imaging (fMRI) dataset of individuals with schizophrenia (N = 708) and controls (N = 510). Our analysis reveals widespread group level differences across multiple networks and spatiotemporal features including voxel-wise variability, magnitude, and temporal functional network connectivity in widespread regions expected to be impacted by the disorder. We compare with typical average spatial amplitude and show highly structured and neuroanatomically relevant results are missed if one does not consider the voxel-wise spatial dynamics. Importantly, our approach can summarize static, temporal dynamic, spatial dynamic, and spatiotemporal dynamics features, thus proving a powerful approach to unify and compare these various perspectives. In sum, we show the proposed approach highlights the importance of accounting for both temporal and spatial dynamism in whole brain neuroimaging data generally, shows a high-level of sensitivity to schizophrenia highlighting global but spatially unique dynamics showing group differences, and may be especially important in studies focused on the development of brain-based biomarkers.

Increased Hippocampal-Inferior Temporal Gyrus White Matter Connectivity following Donepezil Treatment in Patients with Early Alzheimer's Disease: A Diffusion Tensor Probabilistic Tractography Study.

The incidence of Alzheimer's disease (AD) has been increasing each year, and a defective hippocampus has been primarily associated with an early stage of AD. However, the effect of donepezil treatment on hippocampus-related networks is unknown. Thus, in the current study, we evaluated the hippocampal white matter (WM) connectivity in patients with early-stage AD before and after donepezil treatment using probabilistic tractography, and we further determined the WM integrity and changes in brain volume. Ten patients with early-stage AD (mean age = 72.4 ± 7.9 years; seven females and three males) and nine healthy controls (HC; mean age = 70.7 ± 3.5 years; six females and three males) underwent a magnetic resonance (MR) examination. After performing the first MR examination, the patients received donepezil treatment for 6 months. The brain volumes and diffusion tensor imaging scalars of 11 regions of interest (the superior/middle/inferior frontal gyrus, the superior/middle/inferior temporal gyrus, the amygdala, the caudate nucleus, the hippocampus, the putamen, and the thalamus) were measured using MR imaging and DTI, respectively. Seed-based structural connectivity analyses were focused on the hippocampus. The patients with early AD had a lower hippocampal volume and WM connectivity with the superior frontal gyrus and higher mean diffusivity (MD) and radial diffusivity (RD) in the amygdala than HC (p < 0.05, Bonferroni-corrected). However, brain areas with a higher (or lower) brain volume and WM connectivity were not observed in the HC compared with the patients with early AD. After six months of donepezil treatment, the patients with early AD showed increased hippocampal-inferior temporal gyrus (ITG) WM connectivity (p < 0.05, Bonferroni-corrected).

Spatial and temporal controls on the solute behavior of rivers in arid watersheds: The Okavango River, NW Botswana

Solute cycling models for rivers in arid watersheds must identify solute sources and their spatial and temporal connectivity to rivers to assess the processes that control the solute behavior in these rivers. In this study, we collected hourly time series of total dissolved ions (TDI) concentrations, water levels, water temperatures and air temperatures at select stations distributed longitudinally in a river in an arid watershed. Our objectives were to: (1) document the spatial and temporal variations in solute concentrations and (2) determine the processes controlling the spatial and temporal variations in solute concentrations. We conducted this investigation over a two-year period at four stations along the Okavango River flowing through the Okavango Delta (Delta) in the middle Kalahari Desert, Botswana. At the spatial scale, we observed progressive downriver enrichment in TDI concentrations associated with evapotranspiration of river water because of the 5 months river transit across the hot Delta. At a temporal scale, the TDI concentrations increased seasonally from evapoconcentration and sub-seasonally from solute transfer from the watershed to the river. We analyzed sub-seasonal TDI concentration perturbations using the slope (β) of the relationship between TDI concentrations and normalized water level (C-NWL) relationships. We find that at low discharge during flow recession and at the beginning of rising discharge from flooding, the solute enrichment anomalies with β > 0 are related to hydrologic connectivity between the river and solute stores in the river floodplains, hundreds of thousands of salt islands and isolated evapoconcentrated wetland pools. Our findings indicate that hydrologically-driven river connectivity to solute stores in the local watershed and evapotranspiration jointly control the solute behavior at variable spatial and temporal scales in rivers in arid watersheds. We anticipate that our findings will inform solute transport and solute cycling models for rivers in arid watersheds.

Nexuses between Economic Growth and Health Indicators: Evidence from Pakistan

The goal of this article is to look at how various health indices affect Pakistan's economic growth. To achieve this goal, error correction and co-integration methods were used by using time series data from 1990 to 2022. The goal of this research is to examine the short-run and long-term temporal connections between health and per capita GDP growth. In the long-run, there is a significant relationship between per capita GDP and economic health indicators, which are significantly affecting per-capita GDP. According to the results of short run, health indicators have no meaningful influence on per-capita GDP. While indicators of health have a considerable long-run influence in economic growth. It implies that the influence of health indicators can only impact economic growth in the long run. The study's main result suggests financial gain, through growing and raising the stock of healthy human capital, particularly if present stocks are at a low level. Improved health has a two-way interaction with the economic process. This research is to examine the short-run and long-term temporal connections between health and per capita GDP growth, using mistreatment Co-integration and Error Correction. Long-term health and economic process studies would be extremely valuable in determining the achievable magnitudes of the entire cumulative effects of health on economic process. Two key hypotheses would be examined; the first would be that 'health influences economic growth' might be a long-standing temporal development. Second, what role do health output and input factors play in per capita GDP growth?

Altered temporal connectivity and reduced meta-state dynamism in adolescents born very preterm.

Adolescents born very preterm have an increased risk for anxiety, social difficulties and inattentiveness, i.e. the 'preterm behavioural phenotype'. The extreme end of these traits comprises the core diagnostic features of attention and hyperactivity disorders and autism spectrum disorder, which have been reported to show aberrant dynamic resting-state functional network connectivity. This study aimed to compare this dynamism between adolescents born very preterm and controls. A resting-state functional magnetic resonance imaging was performed on 24 adolescents born very preterm (gestational age <32 weeks and/or birth weight ≤1500 g) and 32 controls born full term (≥37 weeks of gestation) at 13 years of age. Group-wise comparisons of dynamic connectivity between the resting-state networks were performed using both hard clustering and meta-state analysis of functional network connectivity. The very preterm group yielded a higher fraction of time spent in the least active connectivity state in hard clustering state functional network connectivity, even though no group differences in pairwise connectivity patterns were discovered. The meta-state analysis showed a decreased fluidity and dynamic range in the very preterm group compared with controls. Our results suggest that the 13-year-old adolescents born very preterm differ from controls in the temporal characteristics of functional connectivity. The findings may reflect the long-lasting effects of prematurity and the clinically acknowledged 'preterm behavioural phenotype'.

Spectral Multiplexing of Fluorescent Endoscopy for Simultaneous Imaging with Multiple Fluorophores and Multiple Fields of View

Complex clinical procedures and small-animal research procedures can benefit from dual-site imaging provided by multiple endoscopic devices. Here, an endoscopic system is proposed which enables multiple fluorescence microendoscopes to be spectrally multiplexed on a single microscope base, enabling light sources and optical relays to be shared between endoscopes. The presented system is characterized for resolution using USAF-1951 resolution test charts and for modulation transfer function using the slanted edge method. Imaging is demonstrated both directly and with microendoscopes attached. Imaging of phantoms was demonstrated by targeting USAF charts and fiber tissues dyed for FITC and Texas Red fluorescence. Afterwards, simultaneous liver and kidney imaging was demonstrated in mice expressing mitochondrial Dendra2 and injected with Texas Red-dextran. The results indicate that the system achieves high channel isolation and submicron and subcellular resolution, with resolution limited by the endoscopic probe and by physiological movement during endoscopic imaging. Multi-channel microendoscopy provides a potentially low-cost means of simultaneous multiple endoscopic imaging during biological experiments, resulting in reduced animal harm and potentially increasing insight into temporal connections between connected biological systems.

Brain instability in dynamic functional connectivity in schizophrenia

Schizophrenia is a severe psychiatric disorder associated with altered connectivity of brain functional networks (BFNs). Researchers have observed a profound disruption in prefrontal-temporal interactions, damage to hub regions in brain networks and modified topological organization of BFNs in schizophrenia (SCZ) individuals. Assessment of BFNs with dynamic approaches allow the characterization of new functional structures, such as topological stability patterns and temporal connectivity, which are not accessible through static methods. In this perspective, the present study investigated the physiological processes of brain connectivity in SCZ. A resting-state EEG dataset of 14 SCZ individuals and 14 healthy controls (HC) was obtained at a sampling rate of 250Hz. Dynamic BFNs were constructed using time-varying graphs combined with the motifs' synchronization method and the indexes were evaluated in different scales: global averages, by hemispheres, by regions, and by electrodes for both groups. The SCZ group exhibited lower temporal connectivity, lesser hub probability, and fewer number of edges in right and left temporal lobes over time, besides increased temporal connectivity in the central-parietal region. Neither differences for the full synchronization time of BFNs were observed, nor for intra- and inter-hemispheric connections between groups. These results indicate that SCZ BFNs exhibit a dynamic fluctuation pattern with abrupt increases in connectivity over time for the regions studied. This elucidates an attempted interaction of the temporal area with other regions (frontal, central-parietal, and occipital) that is not sufficient to maintain a connectivity pattern in schizophrenia individuals similar to that of healthy subjects. Our results suggest that changes in interaction of dynamic BFNs connections in SCZ can be better approached by dynamic analyses that enable a thorough glance at brain changes over time.

The Role of The Hippocampus in Conditionally Reflective Activity and The Formation of The Functional State of The Crust of The Large Hemisphere

The studies were carried out on dogs, which were stereotactically implanted with depth electrodes in the ventral and dorsal parts of the hippocampus. We studied the effect of stimulation of these structures with an electric current of high (60 pulses/sec) and low (4 pulses/sec) frequencies on conditional reflex activity and the formation of the functional state of the cerebral cortex. It was revealed that stimulation of different structures of the hippocampus has a different effect on the tone of cortex cells. The nature of this influence depends on the frequency of the electric current, which was used to stimulate. Formulation of the problem. Analysis of recent research and publications. There are a number of scientific papers devoted to the study of the role of the hippocampus in the regulation of various body functions (Giuliana, Caronia, Jennifer, Wilcoxon, et all., 2010; Purvis, EM, O'Donnelly, JC et all, 2020). Some authors believe that the hippocampus is a poly-functional structure: the center of visceral functions and sense of smell, memory, and learning, the regulator of emotions and motivations, it is used for orientation reflexes and attention, sensory analysis (Chaychenko, G.M., 1984; Wiskott L, Rasch MJ, Kempermann G. Wiskott L, Rasch MJ, Kempermann G. et all. 2006). But today there is not enough reliable data on the role of this structure in conditioned reflex activity under conditions of electrical stimulation of various structures of the hippocampus. It was found that when the hippocampus is stimulated by a weak electric current during the formation of conditioned reflexes, the fixation time of the reflex is significantly reduced, ie the processes of memorization and learning are accelerated (Gray, J.A., 1983; Diana, X Yu, Maria, C Marchetto, Fred, H Gage, 2014; Nader, K, Krysiak A, Beroun, A, et all., 2019; Whitfield, JF, Chakravarthy, BR., 2009). The mechanism of temporal connections has been shown to play an important role in regulating cortical tone. If the question of the formation of the functional state of the cortex of the large hemispheres during the formation of conditioned reflexes is more or less studied, then the question of the dependence of this phenomenon on the properties of the inhibitory process is insufficiently studied (William, D Jones, Sarah, M Guadiana, Elizabeth, A Grove, 2019). In addition, the role of various subcortical structures and, in particular, the hippocampus in the regulation of the tone of the cortex of the large hemispheres has not been clarified to date. The purpose to establish features of the formation of a functional condition of the bark of large hemispheres in the conditions of electric stimulation of various structures of a hippocampus

Intra-annual sediment dynamic assessment in the Wei River Basin, China, using the AIC functional-structural connectivity index

Hydrological and sediment dynamics have changed considerably on the Chinese Loess Plateau during the last six decades due to large scale land use changes and numerous water regulation actions. Understanding the mechanism of sediment transport change and its effects is of great importance to food and environmental security. Numerical approaches are useful to map and assess spatio-temporal patterns in sediment dynamics. This study evaluates monthly and annual sediment connectivity in the Wei River Basin (134,800 km2) at the basin and sub-basin scales using the aggregated index of sediment connectivity (AIC). For the first time, this index is applied on this relatively large regional scale. The two objectives were to (1) evaluate the performance of the AIC at the regional scale, addressing substantial differences among areas, and (2) analyze how each AIC sub-factor co-determines the monthly sediment and connectivity patterns. Results show that AIC has strong or moderate positive correlation with sediment yield from 15 out of 23 stations in the Wei and Jing sub-basin. The Jing sub-basin has the highest sediment connectivity due to degraded vegetation, while the Beiluo sub-basin has the lowest sediment connectivity on average due to better ecological restoration. Within the year, sediment connectivity is highest in April and lowest in January, due to the rainfall regime and intra-annual land cover variations. Among the AIC factors, the rainfall factor has the highest effect on sediment connectivity, implying that functional connectivity (graded by rainfall and soil cover) determines sediment dynamics more than structural connectivity (mainly determined by topography and soil permeability). This study provides one of the first large-scale estimates of spatial and temporal sediment connectivity from hillslopes to river stream and including large reservoirs, which can be further employed to implement regional ecological construction works and environmental catchment management.

Default mode network and medial temporal lobe functional connectivity changes with Alzheimer’s disease severity and cognitive impairment in individuals with Down syndrome

AbstractBackgroundBy age 40, virtually all people with Down syndrome (DS) have sufficient beta‐amyloid and tau pathologies present to meet the criteria for pathological Alzheimer's disease (AD). Determining the timing and location of neurobiological changes caused by AD is critically important for effective intervention within this high‐risk population and more broadly in the general population, but little is known about the brain changes associated with clinical onset of AD in DS. Previous studies in sporadic AD suggest that functional connectivity of the default mode network (DMN) and medial temporal lobe (MTL) is vulnerable to AD pathology‐related impairment.MethodSeventy‐five individuals with DS (mean age 49.9±6.6, 36% women) from a subset of the Alzheimer’s Biomarkers Consortium ‐ Down Syndrome study underwent MRI, including an MPRAGE scan and a resting state functional scan. Participants completed a battery of neuropsychological tests and were assigned a consensus diagnosis for the presence or absence of mild cognitive impairment (MCI‐DS) or AD dementia. Forty‐eight participants were classified as cognitively stable (CS) (mean age 48±6.1, 42% women), 16 participants had MCI‐DS (mean age 50.8±4.2, 19% women), and 11 participants had dementia (mean age 57.2±6.6, 36% women).ResultParticipants with dementia had lower functional connectivity between the posterior DMN and the MTL relative to the CS and MCI‐DS groups. MCI‐DS participants had greater functional connectivity within the MTL relative to the CS group. Functional connectivity differences in these networks tracked with memory performance as well.ConclusionChanges in DMN and MTL functional connectivity are related to the progression of clinical symptoms of AD‐DS and may reflect synaptic changes stemming from AD pathology.

Improving automated diagnosis of epilepsy from EEGs beyond IEDs

Objective. Clinical diagnosis of epilepsy relies partially on identifying interictal epileptiform discharges (IEDs) in scalp electroencephalograms (EEGs). This process is expert-biased, tedious, and can delay the diagnosis procedure. Beyond automatically detecting IEDs, there are far fewer studies on automated methods to differentiate epileptic EEGs (potentially without IEDs) from normal EEGs. In addition, the diagnosis of epilepsy based on a single EEG tends to be low. Consequently, there is a strong need for automated systems for EEG interpretation. Traditionally, epilepsy diagnosis relies heavily on IEDs. However, since not all epileptic EEGs exhibit IEDs, it is essential to explore IED-independent EEG measures for epilepsy diagnosis. The main objective is to develop an automated system for detecting epileptic EEGs, both with or without IEDs. In order to detect epileptic EEGs without IEDs, it is crucial to include EEG features in the algorithm that are not directly related to IEDs. Approach. In this study, we explore the background characteristics of interictal EEG for automated and more reliable diagnosis of epilepsy. Specifically, we investigate features based on univariate temporal measures (UTMs), spectral, wavelet, Stockwell, connectivity, and graph metrics of EEGs, besides patient-related information (age and vigilance state). The evaluation is performed on a sizeable cohort of routine scalp EEGs (685 epileptic EEGs and 1229 normal EEGs) from five centers across Singapore, USA, and India. Main results. In comparison with the current literature, we obtained an improved Leave-One-Subject-Out (LOSO) cross-validation (CV) area under the curve (AUC) of 0.871 (Balanced Accuracy (BAC) of 80.9%) with a combination of three features (IED rate, and Daubechies and Morlet wavelets) for the classification of EEGs with IEDs vs. normal EEGs. The IED-independent feature UTM achieved a LOSO CV AUC of 0.809 (BAC of 74.4%). The inclusion of IED-independent features also helps to improve the EEG-level classification of epileptic EEGs with and without IEDs vs. normal EEGs, achieving an AUC of 0.822 (BAC of 77.6%) compared to 0.688 (BAC of 59.6%) for classification only based on the IED rate. Specifically, the addition of IED-independent features improved the BAC by 21% in detecting epileptic EEGs that do not contain IEDs. Significance. These results pave the way towards automated detection of epilepsy. We are one of the first to analyze epileptic EEGs without IEDs, thereby opening up an underexplored option in epilepsy diagnosis.

A mild cognitive impairment diagnostic model based on IAAFT and BiLSTM

The early diagnosis of mild cognitive impairment (MCI) is a essential prevention of further development of MCI into Alzheimer's disease (AD). Electroencephalogram (EEG) has many advantages compared to other methods in the analysis of AD in an early stage, but there are some limitations of EEG such as small size of datasets caused by difficulty in clinical data collection and too many other interfering signals are contained. Recent years, deep learning (DL) have overcome these limitations relatively. In this study, a novel model which aims to classify MCI and healthy control (HC) was constructed based on iterative amplitude adjusted Fourier transform (IAAFT) and bidirectional long short-term memory (BiLSTM). IAAFT is used to overcome the problems caused by small datasets; sample entropy (SampEn) feature extraction is used to further reduce computational time and obtain better classification results; BiLSTM for better capture of EEG temporal connections. The performance of the model was evaluated on a clinical dataset containing 10 MCI and 10 HC. Compared with the traditional EEG classification method, the result shows that BiLSTM is more suitable for the EEG classification task, and the classification accuracy is significantly improved by data augmentation. After performing 10-fold cross-validation and 10-fold data augmentation, the model achieved a maximum classification accuracy of 97.20 ± 1.74 %. The results indicate that the model can be used to diagnose MCI patients with the EEG small datasets. Meanwhile, The data augmentation used in this study has a high reference value for other resting-state EEG classification tasks.

Degree centrality and functional connections in presbycusis with and without cognitive impairments.

Presbycusis is a major public issue that affecting elderly adults. However, the neural substrates between normal cognition and cognitive deficits in these patients need to be illustrated. 47 patients with presbycusis and 33 well-matched healthy controls were recruited in present study. Each subject underwent pure-tone audiometry (PTA), MRI scanning and cognition evaluations, then we found 22 patients with cognitive deficits and 25 patients with common cognition. We analyzed the Degree centrality (DC) characteristics among three groups, and try to recognize key nodes which contribute significantly. Subsequent functional connectivity analysis was applied using the key nodes as seeds. Compared with controls, presbycusis without cognitive impairments showed deceased DC in superior temporal gyrus (STG), inferior frontal gyrus (IFG) and supramarginal gyrus (SMG). Additionally, presbycusis with cognitive impairments showed enhanced DC in fusiform gurus (FFG), cerebellum and para-hippocampal gyrus (PHG), while weakened DC in SMG, middle frontal gyrus (IFG) and inferior Parietal lobule (IPL). Compared with normal cognition, increased DC value of cerebellum and STG, as well as decreased DC value of IPL in presbycusis with cognitive impairments were observed. We noticed that SMG may play an important role. Then the left and right SMG were used as seeds in functional connections analysis. With the seed set at left SMG, presbycusis without cognitive impairments showed decreases connections with cerebellum, temporal pole (TP), superior temporal gyrus (STG) and median cingulate cortex (MCC). Presbycusis with cognitive impairments showed weakened connectivity with cerebellum, IFG, IPL and superior frontal gyrus (SFG). The right SMG showed decrease connections with cerebellum, middle temporal gyrus (MTG), STG and increase connection with middle frontal gyrus (MFG) in presbycusis without cognitive impairments. While the right SMG showed enhanced connections with left TP, caudate, anterior cingulate cortex (ACC), angular, SFG and weakened connectivity with right SFG presbycusis with cognitive impairments. In comparison with normal cognition and impaired cognition, MFG, IFG, PHG, rolandic operculum and cerebellum were involved. These findings enriched our understanding of the neural mechanisms underlying cognitive impairments associated with presbycusis and may serve as a potential imaging biomarker for investigating and predicting cognitive difficulties.