A Dynamic Window Method Based on Reinforcement Learning for SSVEP Recognition.

Steady-state visual evoked potential (SSVEP) is one of the most used brain-computer interface (BCI) paradigms. Conventional methods analyze SSVEPs at a fixed window length. Compared with these methods, dynamic window methods can achieve a higher information transfer rate (ITR) by selecting an appropriate window length. These methods dynamically evaluate the credibility of the result by linear discriminant analysis (LDA) or Bayesian estimation and extend the window length until credible results are obtained. However, the hypotheses introduced by LDA and Bayesian estimation may not align with the collected real-world SSVEPs, which leads to an inappropriate window length. To address the issue, we propose a novel dynamic window method based on reinforcement learning (RL). The proposed method optimizes the decision of whether to extend the window length based on the impact of decisions on the ITR, without additional hypotheses. The decision model can automatically learn a strategy that maximizes the ITR through trial and error. In addition, compared with traditional methods that manually extract features, the proposed method uses neural networks to automatically extract features for the dynamic selection of window length. Therefore, the proposed method can more accurately decide whether to extend the window length and select an appropriate window length. To verify the performance, we compared the novel method with other dynamic window methods on two public SSVEP datasets. The experimental results demonstrate that the novel method achieves the highest performance by using RL.

Numerical simulation of upper airway heat transfer in children with mandibular retrognathia during inspiratory process.

Introduction: The human upper airway regulates temperature, but its heating capacity remains unclear when the ambient temperature is low and the airway structure is abnormal. Therefore, the purpose of this study was to evaluate the heat transfer characteristics of the upper airway in patients with mandibular retrognathia, and to quantitatively evaluate the influence of ambient temperature on the temperature field of the upper airway, which could provide a valuable reference for the prediction, diagnosis and treatment of respiratory tract related diseases. Methods: Two typical ambient temperatures of -10 °C and 20 °C were selected to numerically simulate the air flow and heat transfer synchronization in the upper airway model of mandibular retrognathia under quiet breathing and heavy breathing. Results and discussion: The results showed that the inspired air could not be sufficiently heated after flowing through the upper airway and main trachea in the two breathing states under low temperature conditions, and the inferior bronchus was more stimulated under the state of heavy breathing. In addition, the vortex flow structure in the upper airway can enhance the convective heat transfer effect in the corresponding area.

A Self-Interpretable Deep Learning Model for Seizure Prediction Using a Multi-Scale Prototypical Part Network.

The epileptic seizure prediction (ESP) method aims to timely forecast the occurrence of seizures, which is crucial to improving patients' quality of life. Many deep learning-based methods have been developed to tackle this issue and achieve significant progress in recent years. However, the "black-box" nature of deep learning models makes the clinician mistrust the prediction results, severely limiting its clinical application. For this purpose, in this study, we propose a self-interpretable deep learning model for patient-specific epileptic seizure prediction: Multi-Scale Prototypical Part Network (MSPPNet). This model attempts to measure the similarity between the inputs and prototypes (learned during training) as evidence to make final predictions, which could provide a transparent reasoning process and decision basis (e.g., significant prototypes for inputs and corresponding similarity score). Furthermore, we assign different sizes to the prototypes in latent space to capture the multi-scale features of EEG signals. To the best of our knowledge, this is the first study that develops a self-interpretable deep learning model for seizure prediction, other than the existing post hoc interpretation studies. Our proposed model is evaluated on two public epileptic EEG datasets (CHB-MIT: 16 patients with a total of 85 seizures, Kaggle: 5 dogs with a total of 42 seizures), with a sensitivity of 93.8% and a false prediction rate of 0.054/h in the CHB-MIT dataset and a sensitivity of 88.6% and a false prediction rate of 0.146/h in the Kaggle dataset, achieving the current state-of-the-art performance with self-interpretable evidence.

Traffic Condition Classification Model Based on Traffic-Net.

The classification and detection of traffic status plays a vital role in the urban smart transportation system. The classification and mastery of the traffic status at different time periods and sections will help the traffic management department to optimize road management and implement rescue in real time. Travelers can follow the traffic conditions. We choose the best route to effectively improve travel efficiency and safety. However, due to factors such as weather, time of day, lighting, and sample labeling costs, the existing classification methods are insufficient in real time and detection accuracy to meet application requirements. In order to solve this problem, this article aims to effectively transfer and apply the pretrained model learned on large-scale image data sets to small-sample road traffic data sets. By sharing common visual features, model weight parameter migration, and fine-tuning, the road is finally optimized. Traffic conditions classification is based on Traffic-Net. Experiments show that the method in this article can not only obtain a prediction accuracy of more than 96% but also can effectively reduce the model training time and meet the needs of practical applications.

Case series: Diquat poisoning with acute kidney failure, myocardial damage, and rhabdomyolysis.

Diquat is a herbicide that can have deleterious effects on the kidneys, liver, heart, lungs, and central nervous system on ingestion. Diquat poisoning-associated rhabdomyolysis has rarely been reported. We describe two cases of diquat poisoning with acute renal failure, myocardial damage, and rhabdomyolysis. Case 1: A 17-year-old man experienced anuria after ingesting ~200 mL of diquat 16 h prior. On admission, his creatinine (400 µmol/L), urea (11.7 mmol/L), creatine kinase (2,534 IU/L), and myohemoglobin (4,425 ng/mL) concentrations were elevated. Case 2: An 18-year-old woman who ingested ~200 mL of diquat 5.5 h prior to admission had normal creatinine, urea, and creatine kinase concentrations. Eleven hours after ingestion, she developed anuria with elevated creatinine (169 µmol/L) concentration; her creatine kinase (13,617 IU/L) and myohemoglobin (>3,811 ng/mL) concentrations were remarkably elevated 24 h after ingestion. Both patients also had elevated aminotransferase and myocardial enzyme concentrations. After undergoing hemoperfusion and hemofiltration, blood diquat concentrations in cases 1 and 2 on admission (16/6 h after ingestion), after hemoperfusion (20/11 h after ingestion), and after 8 h of hemofiltration/8 h of hemofiltration and 2 h of hemoperfusion (29/21 h after ingestion) were 4.9/9.1, 3.4/5.4, and 1.5/1.2 µg/mL, respectively. Severe diquat poisoning can cause acute kidney failure and rhabdomyolysis. Rhabdomyolysis may induce myocardial injury, aggravating kidney damage, and also increase transaminase concentration. Hemoperfusion and hemofiltration could be effective treatments for eliminating diquat in the blood.

A general sample-weighted framework for epileptic seizure prediction.

OBJECTIVE: Effective epileptic seizure prediction can make the patients know the onset of the seizure in advance to take timely preventive measures. Many studies based on machine learning methods have been proposed to tackle this problem and achieve significant progress in recent years. However, most studies treat each EEG training sample's contribution to the model as equal, while different samples have different predictive effects on epileptic seizures (e.g., preictal samples from different times). To this end, in this paper, we propose a general sample-weighted framework for patient-specific epileptic seizure prediction. METHODS: Specifically, we define the mapping from the sample weights of training sets to the performance of the validation sets as the fitness function to be optimized. Then, the genetic algorithm is employed to optimize this fitness function and obtain the optimal sample weights. Finally, we obtain the final model by using the training sets with optimized sample weights. RESULTS: To evaluate the effectiveness of our framework, we conduct extensive experiments on both traditional machine learning methods and prevalent deep learning methods. Our framework can significantly improve performance based on these methods. Among them, our framework based on Transformer achieves an average sensitivity of 94.6%, an average false prediction rate of 0.06/h, and an average AUC of 0.939 in 12 pediatric patients from the CHB-MIT database with the leave-one-out method, which outperforms the state-of-the-art methods. CONCLUSION: This study provides new insights into the field of epileptic seizure prediction by considering the discrepancies between EEG samples. Moreover, we develop a general sample-weighted framework, which applies to almost all classical classification methods and can significantly improve performance based on these methods.

Pediatric Seizure Prediction in Scalp EEG Using a Multi-Scale Neural Network With Dilated Convolutions.

Objective: Epileptic seizure prediction based on scalp electroencephalogram (EEG) is of great significance for improving the quality of life of patients with epilepsy. In recent years, a number of studies based on deep learning methods have been proposed to address this issue and achieve excellent performance. However, most studies on epileptic seizure prediction by EEG fail to take full advantage of temporal-spatial multi-scale features of EEG signals, while EEG signals carry information in multiple temporal and spatial scales. To this end, in this study, we proposed an end-to-end framework by using a temporal-spatial multi-scale convolutional neural network with dilated convolutions for patient-specific seizure prediction. Methods: Specifically, the model divides the EEG processing pipeline into two stages: the temporal multi-scale stage and the spatial multi-scale stage. In each stage, we firstly extract the multi-scale features along the corresponding dimension. A dilated convolution block is then conducted on these features to expand our model's receptive fields further and systematically aggregate global information. Furthermore, we adopt a feature-weighted fusion strategy based on an attention mechanism to achieve better feature fusion and eliminate redundancy in the dilated convolution block. Results: The proposed model obtains an average sensitivity of 93.3%, an average false prediction rate of 0.007 per hour, and an average proportion of time-in-warning of 6.3% testing in 16 patients from the CHB-MIT dataset with the leave-one-out method. Conclusion: Our model achieves superior performance in comparison to state-of-the-art methods, providing a promising solution for EEG-based seizure prediction.

Fast and Automated Segmentation for the Three-Directional Multi-Slice Cine Myocardial Velocity Mapping.

Three-directional cine multi-slice left ventricular myocardial velocity mapping (3Dir MVM) is a cardiac magnetic resonance (CMR) technique that allows the assessment of cardiac motion in three orthogonal directions. Accurate and reproducible delineation of the myocardium is crucial for accurate analysis of peak systolic and diastolic myocardial velocities. In addition to the conventionally available magnitude CMR data, 3Dir MVM also provides three orthogonal phase velocity mapping datasets, which are used to generate velocity maps. These velocity maps may also be used to facilitate and improve the myocardial delineation. Based on the success of deep learning in medical image processing, we propose a novel fast and automated framework that improves the standard U-Net-based methods on these CMR multi-channel data (magnitude and phase velocity mapping) by cross-channel fusion with an attention module and the shape information-based post-processing to achieve accurate delineation of both epicardial and endocardial contours. To evaluate the results, we employ the widely used Dice Scores and the quantification of myocardial longitudinal peak velocities. Our proposed network trained with multi-channel data shows superior performance compared to standard U-Net-based networks trained on single-channel data. The obtained results are promising and provide compelling evidence for the design and application of our multi-channel image analysis of the 3Dir MVM CMR data.

MiR-30a suppresses clear cell renal cell carcinoma proliferation and metastasis by targeting LRP6.

Recently, the role of miR-30a in tumor development has attracted extensive attention. In this study, we aimed to elucidate the role of miR-30a and its associated target low-density lipoprotein receptor-related protein 6 (LRP6) in clear cell renal cell carcinoma (ccRCC) cells. Here, miR-30a was markedly down-regulated in ccRCC tissues and cells, and was correlated with the advanced TNM stage and poor prognosis. By contrast, LRP6 protein level was increased in ccRCC specimens and cell lines, and inversely correlated with miR-30a expression. Stable overexpression of miR-30a suppressed cell proliferation in vitro, impeded tumor growth in vivo, prevented migration and invasion, and triggered apoptosis of ccRCC cells. Also, over-expression of miR-30a in ccRCC cells promoted the expression of the epithelial marker E-cadherin and reduced the levels of mesenchymal markers. Mechanistically, the dual-luciferase reporter, RNA immunoprecipitation and western blot assays confirmed that miR-30a directly targeted the 3'-untranslated regions of LRP6 to inhibit its expression. Further, miR-30a-mediated effect was partially reversed by co-transfection with LRP6 plasmids or enhanced by silencing of LRP6. In conclusion, miR-30a exhibits effective antitumor properties by targeting LRP6 in proliferation and metastasis of ccRCC. This study could provide new insights into the treatment of ccRCC.

Effect of transforming growth factor-ß1 on acute lung injury caused by paraquat.

In China, and other Asian countries, numerous patients have succumbed to pulmonary fibrosis induced by paquarat poisoning, but the early pathogenesis remains unclear. In this study the effect of cytokine transforming growth factor (TGF)-ß1 was observed in early acute paraquat poisoning and examined the mechanism by which paraquat caused early acute lung injury. It was discovered that the rat serum TGF-ß1 levels in the paraquat groups were significant higher than that in the control group (P<0.05) and the rat pulmonary TGF-ß1 mRNA expression levels were also higher than that in the control group (P<0.05). Histological examination indicated that the rat lung tissue was broad and congested, and had been infiltrated by inflammatory cells. Masson's trichrome staining for collagen showed that the lung tissue appeared fibrotic following paraquat poisoning. Ultramicrostructure observation found that macrophages, red blood cells, lymphocytes and granulocytes infiltrated the alveolar space and there were cytolysosomes in the macrophages. The shape of the type II alveolar epithelial cell nuclei were irregular with karyopyknosis. The heterochromatin migrated to the cell edge and lamellar body vacuolization was also observed. Type I alveolar epithelial cells shrank. In conclusion, the effect of cytokine TGF-ß1 on paraquat-induced acute lung tissue injury may be important.