Background: Epilepsy is a neurological disorder that is usually detected by electroencephalogram (EEG) signals. Since manual examination of epilepsy seizures is a laborious and time-consuming process, lots of automatic epilepsy detection algorithms have been proposed. However, most of the available classification algorithms for epilepsy EEG signals adopted a single feature extraction, in turn to result in low classification accuracy. Although a small account of studies have carried out feature fusion, the computational efficiency is reduced due to too many features, because there are also some poor features that interfere with the classification results. Methods: In order to solve the above problems, an automatic recognition method of epilepsy EEG signals based on feature fusion and selection is proposed in this paper. Firstly, the Approximate Entropy (ApEn), Fuzzy Entropy (FuzzyEn), Sample Entropy (SampEn), and Standard Deviation (STD) mixed features of the subband obtained by the Discrete Wavelet Transform (DWT) decomposition of EEG signals are extracted. Secondly, the random forest algorithm is used for feature selection. Finally, the Convolutional Neural Network (CNN) is used to classify epilepsy EEG signals. Results: The empirical evaluation of the presented algorithm is performed on the benchmark Bonn EEG datasets and New Delhi datasets. In the interictal and ictal classification tasks of Bonn datasets, the proposed model achieves an accuracy of 99.9%, a sensitivity of 100%, a precision of 99.81%, and a specificity of 99.8%. For the interictal-ictal case of New Delhi datasets, the proposed model achieves a classification accuracy of 100%, a sensitivity of 100%, a specificity of 100%, and a precision of 100%. Conclusion: The proposed model can effectively realize the high-precision automatic detection and classification of epilepsy EEG signals. This model can provide high-precision automatic detection capability for clinical epilepsy EEG detection. We hope to provide positive implications for the prediction of seizure EEG.

The diagnosis and treatment of epilepsy continue to face numerous challenges, highlighting the urgent need for the development of rapid, accurate, and non-invasive methods for seizure detection. In recent years, advancements in the analysis of electroencephalogram (EEG) signals have garnered widespread attention, particularly in the area of seizure recognition. A novel hybrid deep learning approach that combines feature fusion for efficient seizure detection is proposed in this study. First, the Discrete Wavelet Transform (DWT) is applied to perform a five-level decomposition of the raw EEG signals, from which time–frequency and nonlinear features are extracted from the decomposed sub-bands. To eliminate redundant features, Support Vector Machine-Recursive Feature Elimination (SVM-RFE) is employed to select the most distinctive features for fusion. Finally, seizure states are classified using Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-Bi-LSTM). The method was rigorously validated on the Bonn and New Delhi datasets. In the binary classification tasks, both the D-E group (Bonn dataset) and the Interictal-Ictal group (New Delhi dataset) achieved 100% accuracy, 100% sensitivity, 100% specificity, 100% precision, and 100% F1-score. In the three-class classification task A-D-E on the Bonn dataset, the model performed excellently, achieving 96.19% accuracy, 95.08% sensitivity, 97.34% specificity, 97.49% precision, and 96.18% F1-score. In addition, the proposed method was further validated on the larger and more clinically relevant CHB-MIT dataset, achieving average metrics of 98.43% accuracy, 97.84% sensitivity, 99.21% specificity, 99.14% precision, and an F1 score of 98.39%. Compared to existing literature, our method outperformed several recent studies in similar classification tasks, underscoring the effectiveness and advancement of the approach presented in this research. The findings indicate that the proposed method demonstrates a high level of effectiveness in detecting seizures, which is a crucial aspect of managing epilepsy. By improving the accuracy of seizure detection, this method has the potential to significantly enhance the process of diagnosing and treating individuals affected by epilepsy. This advancement could lead to more tailored treatment plans, timely interventions, and ultimately, better quality of life for patients.

This review elucidates the pivotal role of pyroptosis, triggered by gut microbiota, in the development of multiple sclerosis (MS), emphasizing its significance within the gut-brain axis. Our comprehensive analysis of recent literature reveals how dysbiosis in the gut microbiota of MS patients—characterized by reduced microbial diversity and shifts in bacterial populations—profoundly impacts immune regulation and the integrity of the central nervous system (CNS). Pyroptosis, an inflammatory form of programmed cell death, significantly exacerbates MS by promoting the release of inflammatory cytokines and causing substantial damage to CNS tissues. The gut microbiota facilitates this detrimental process through metabolites such as short-chain fatty acids and neuroactive compounds, or self-structural products like lipopolysaccharides (LPS), which modulate immune responses and influence neuronal survival. This review highlights the potential of modulating gut microbiota to regulate pyroptosis, thereby suggesting that targeting this pathway could be a promising therapeutic strategy to mitigate inflammatory responses and preserve neuronal integrity in patients with MS.

Introduction: Parkinson's disease (PD) is a common neurodegenerative disorder. Traditional diagnostic methods, relying on clinical assessment and imaging, are often invasive, costly, and require specialized personnel, posing barriers to early detection. As approximately 90% of PD patients develop vocal impairments, vocal analysis emerges as a promising non-invasive diagnostic tool. However, individual deep learning models are often limited by overfitting and poor generalizability. Methods: This study proposes a PD classification method using spectrogram feature fusion with pre-trained convolutional neural networks (CNNs). Voice recordings were obtained from 61 PD patients and 70 healthy controls (HC) at the First Affiliated Hospital of Henan University of Science and Technology. Preprocessing the raw speech signals yielded 2,476 spectrograms. Three pre-trained models, DenseNet121, MobileNetV3-Large, and ShuffleNetV2, were used for feature extraction. The output of MobileNetV3-Large was adjusted using a 1 × 1 convolutional layer to ensure dimensional alignment before features were fused via summation. Results: Evaluation using 5-fold cross-validation demonstrated that models employing feature fusion consistently outperformed individual models across all metrics. Specifically, the fusion of MobileNetV3-Large and ShuffleNetV2 achieved the highest accuracy of 95.56% and an AUC of 0.99. Comparative experiments with existing state-of-the-art methods confirmed the competitive performance of the proposed approach. Discussion: The fusion of multi-model features more effectively captures subtle pathological signatures in PD speech, overcoming the limitations of single models. This method provides a reliable, low-cost, and non-invasive tool for auxiliary PD diagnosis, with significant potential for clinical application. The code is available at https://github.com/lvrongfu/pjs .

Menstrually-related migraine (MM) is a primary migraine in women of reproductive age. The underlying neural mechanism of MM was still unclear. In this study, we aimed to reveal the case–control differences in network integration and segregation for the morphometric similarity network of MM. Thirty-six patients with MM and 29 healthy females were recruited and underwent MRI scanning. The morphometric features were extracted in each region to construct the single-subject interareal cortical connection using morphometric similarity. The network topology characteristics, in terms of integration and segregation, were analyzed. Our results revealed that, in the absence of morphology differences, disrupted cortical network integration was found in MM patients compared to controls. The patients with MM showed a decreased global efficiency and increased characteristic path length compared to healthy controls. Regional efficiency analysis revealed the decreased efficiency in the left precentral gyrus and bilateral superior temporal gyrus contributed to the decreased network integration. The increased nodal degree centrality in the right pars triangularis was positively associated with the attack frequency in MM. Our results suggested MM would reorganize the morphology in the pain-related brain regions and reduce the parallel information processing capacity of the brain.

Background: The systemic inflammation index (SII), neutrophil-to-lymphocyte ratio (NLR), monocyte-to-lymphocyte ratio (MLR) and platelet-to-lymphocyte ratio (PLR) are inflammatory markers in peripheral blood, which have been proven to be associated with some central nervous system diseases. We aimed to evaluate the association of SII, NLR MLR and PLR with the severity of autoimmune encephalitis (AE) and to compare the predictive value of those biomarkers in the early identification of ICU admission.Methods: This retrospective study was conducted in three medical centers in China. We included 176 patients diagnosed with AE and 200 age and gender-matched healthy controls and correlated their demographic and clinical data. The SII, NLR, MLR and PLR levels were calculated from the blood routine tests. The severity of the patients was evaluated by the Clinical Assessment Scale for Autoimmune Encephalitis (CASE) and the modified Rankin Scale (mRS) at admission, and the patients were divided into two groups according to the ICU admission.Results: The SII, NLR, MLR and PLR were significantly higher in AE patients than that in HCs (<0.001 for all). The SII and NLR were positively correlated with the CASE score (r = 0.243, p = 0.001; r = 0.237, p = 0.002) and the mRS score (r = 0.185, p = 0.014; r = 0.185, p = 0.014) in AE patients. The MLR and PLR were only positively correlated with the CASE score (r = 0.242, p = 0.001; r = 0.158, p = 0.036). The SII and NLR of the ICU group were significantly higher than that of the non-ICU group. The result of receiver operating characteristic (ROC) analysis showed that NLR was the best predictor of ICU admission for AE patients (AUC = 0.701). NLR and MLR had similar predictive ability (AUC = 0.654; AUC = 0.608) and were superior to PLR. The optimal NLR cut-off value for the incidence of ICU was 3.906.Conclusion: Increased SII, NLR, MLR and PLR at admission are positively correlated with the CASE score of AE patients. Among the four indexes, the NLR is the best predictor of ICU admission, which may be helpful for clinicians to monitor disease progression and identify potentially severe patients of AE.