Decreased default mode network functional connectivity with visual processing regions as potential biomarkers for delayed neurocognitive recovery: A resting-state fMRI study and machine-learning analysis

Altered effective connectivity of the default mode network in juvenile myoclonic epilepsy

Juvenile myoclonic epilepsy (JME) is associated with brain dysconnectivity in the default mode network (DMN). Most previous studies of patients with JME have assessed static functional connectivity in terms of the temporal correlation of signal intensity among different brain regions. However, more recent studies have shown that the directionality of brain information flow has a more significant regional impact on patients' brains than previously assumed in the present study. Here, we introduced an empirical approach incorporating independent component analysis (ICA) and spectral dynamic causal modeling (spDCM) analysis to study the variation in effective connectivity in DMN in JME patients. We began by collecting resting-state functional magnetic resonance imaging (rs-fMRI) data from 37 patients and 37 matched controls. Then, we selected 8 key nodes within the DMN using ICA; finally, the key nodes were analyzed for effective connectivity using spDCM to explore the information flow and detect patient abnormalities. This study found that compared with normal subjects, patients with JME showed significant changes in the effective connectivity among the precuneus, hippocampus, and lingual gyrus (p < 0.05 with false discovery rate (FDR) correction) with most of the effective connections being strengthened. In addition, previous studies have found that the self-connection of normal subjects' nodes showed strong inhibition, but the self-connection inhibition of the anterior cingulate cortex and lingual gyrus of the patient was decreased in this experiment (p < 0.05 with FDR correction); as the activity in these areas decreased, the nodes connected to them all appeared abnormal. We believe that the changes in the effective connectivity of nodes within the DMN are accompanied by changes in information transmission that lead to changes in brain function and impaired cognitive and executive function in patients with JME. Overall, our findings extended the dysconnectivity hypothesis in JME from static to dynamic causal and demonstrated that aberrant effective connectivity may underlie abnormal brain function in JME patients at early phase of illness, contributing to the understanding of the pathogenesis of JME.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-023-09994-4.

Deep Learning-Based Assessment Model for Real-Time Identification of Visual Learners Using Raw EEG

Automatic identification of visual learning style in real time using raw electroencephalogram (EEG) is challenging. In this work, inspired by the powerful abilities of deep learning techniques, deep learning-based models are proposed to learn high-level feature representation for EEG visual learning identification. Existing computer-aided systems that use electroencephalograms and machine learning can reasonably assess learning styles. Despite their potential, offline processing is often necessary to eliminate artifacts and extract features, making these methods unsuitable for real-time applications. The dataset was chosen with 34 healthy subjects to measure their EEG signals during resting states (eyes open and eyes closed) and while performing learning tasks. The subjects displayed no prior knowledge of the animated educational content presented in video format. The paper presents an analysis of EEG signals measured during a resting state with closed eyes using three deep learning techniques: Long-term, short-term memory (LSTM), Long-term, short-term memory-convolutional neural network (LSTM-CNN), and Long-term, short-term memory-Fully convolutional neural network (LSTM-FCNN). The chosen techniques were based on their suitability for real-time applications with varying data lengths and the need for less computational time. The optimization of hypertuning parameters has enabled the identification of visual learners through the implementation of three techniques. LSTM-CNN technique has the highest average accuracy of 94%, a sensitivity of 80%, a specificity of 92%, and an F1 score of 94% when identifying the visual learning style of the student out of all three techniques. This research has shown that the most effective method is the deep learning-based LSTM-CNN technique, which accurately identifies a student's visual learning style.