Shaobin Huang

Objective: Clinical studies indicated a link between DTI imaging characteristics and epilepsy, but the causality of this connection had not been established. Therefore, we employed the Mendelian randomization analysis method to determine the causal relationship between DTI imaging characteristics and epilepsy.Method: We used Mendelian randomization analysis to identify the causal relationship between brain structure and the risk of epilepsy. GWAS data of DTI phenotypes, focal epilepsy, and genetic generalized epilepsy (GGE) were utilized in the analysis.Results: Our study found that DTI imaging phenotypes had a causal risk relationship with epilepsy. These phenotypes had a statistical impact on the risk of epilepsy seizures. There were differences in DTI phenotype causality between GGE and focal epilepsy, which were associated with the clinical phenotype differences of the two types of epilepsy.Significance: Our study demonstrated that the diagnosis of subtypes could be assisted by comparing the differences in DTI phenotypes of specific brain regions. This meant that by studying the changes in brain regions before the onset of epilepsy, we might be able to intervene in epilepsy at an earlier stage.Plain Language Summary: Our study used Mendelian randomization to explore the causal relationship between brain structure, as seen in DTI imaging, and epilepsy. We found that specific DTI phenotypes are linked to an increased risk of epilepsy seizures, with notable differences between genetic generalized epilepsy and focal epilepsy. This suggested that analyzing DTI phenotypes could help in diagnosing and potentially intervening in epilepsy earlier by finding brain changes before seizures begin.

Objectives: Currently, a multitude of machine learning techniques are available for the diagnosis of hypertrophic cardiomyopathy (HCM) and dilated cardiomyopathy (DCM) by utilizing electrocardiography (ECG) data. However, these methods rely on digital versions of ECG data, while in practice, numerous ECG data still exist in paper form. As a result, the accuracy of the existing machine learning diagnostic models is suboptimal in practical scenarios. In order to enhance the accuracy of machine learning models for diagnosing cardiomyopathy, we propose a multimodal machine learning model capable of diagnosing both HCM and DCM. Methods: Our study employed an artificial neural network (ANN) for feature extraction from both the echocardiogram report form and biochemical examination data. Furthermore, a convolutional neural network (CNN) was utilized for feature extraction from the electrocardiogram (ECG). The resulting extracted features were subsequently integrated and inputted into a multilayer perceptron (MLP) for diagnostic classification. Results: Our multimodal fusion model achieved a precision of 89.87%, recall of 91.20%, F1 score of 89.13%, and precision of 89.72%. Conclusions: Compared to existing machine learning models, our proposed multimodal fusion model has achieved superior results in various performance metrics. We believe that our method is effective.

Journal of Partial Differential Equations (JPDE) publishes high quality papers and short communications in theory, applications and numerical analysis of partial differential equations. Papers addressing new theoretical techniques, novel ideas, and new analysis tools are suitable topics for the journal. JPDE is a peer-reviewed international journal which is founded by Peking University, Institute of Applied Physics and Computational Mathematics, and Zhengzhou University, with an editorial office based in Zhengzhou, China.

We study the initial boundary value problem of linear homogeneous wave equation with dynamic boundary condition. We aim to prove the finite time blow-up of the solution at critical energy level or high energy level with the nonlinear damping term on boundary in control systems.

The accuracy of fuzzy time series prediction method depends on the accuracy of the discourse division and fuzzy relation extraction. Aiming at the main problems in the model, this paper put forward a kind of fuzzy time series prediction method based on spectral clustering using spectral clustering dividing time series discourse and calculate the corresponding fuzzy sets to construct fuzzy time series; At the same time using second-order Markov probability model constructing fuzzy relation in fuzzy time series, and then predict the subsequent numerical. Compared with the traditional fuzzy time series prediction method, this method can improve the accuracy.