Search

Background: Cardiovascular disease (CVD) remains a leading cause of mortality globally. Environmental pollutants, specifically volatile organic compounds (VOCs), have been identified as significant risk factors. This study aims to develop a machine learning (ML) model to predict CVD risk based on VOC exposure and demographic data using SHapley Additive exPlanations (SHAP) for interpretability. Methods: We utilized data from the National Health and Nutrition Examination Survey (NHANES) from 2011 to 2018, comprising 5098 participants. VOC exposure was assessed through 15 urinary metabolite metrics. The dataset was split into a training set (70 %) and a test set (30 %). Six ML models were developed, including Random Forest (RF), Light Gradient Boosting Machine (LightGBM), Decision Tree (DT), Extreme Gradient Boosting (XGBoost), Multi-Layer Perceptron (MLP), and Support Vector Machines (SVM). Model performance was evaluated using the Area Under the Receiver Operating Characteristic Curve (AUROC), accuracy, balanced accuracy, F1 score, J-index, kappa, Matthew's correlation coefficient (MCC), positive predictive value (PPV), negative predictive value (NPV), sensitivity (sens), specificity (spec) and SHAP was applied to interpret the best-performing model. Results: The RF model exhibited the highest predictive performance with an ROC of 0.8143. SHAP analysis identified age and ATCA as the most significant predictors, with ATCA showing a protective effect against CVD, particularly in older adults and those with hypertension. The study found a significant interaction between ATCA levels and age, indicating that the protective effect of ATCA is more pronounced in older individuals due to increased oxidative stress and inflammatory responses associated with aging. E-values analysis suggested robustness to unmeasured confounders. Conclusions: This study is the first to utilize VOC exposure data to construct an ML model for predicting CVD risk. The findings highlight the potential of combining environmental exposure data with demographic information to enhance CVD risk prediction, supporting the development of personalized prevention and intervention strategies.

Two-dimensional layered transition metal carbides (MXenes), have huge potential advantage for applications in hydrogen evolution reaction (HER). However, the hindered hydrogen evolution at large current densities and the instability of MXenes during HER remains major challenges. Herein, we report the MoS2/Mo2CTx nanoarray with aerophobic structure via molten salt synthesis. In situ vertical distribution of MoS2 nanoarray on the surface of Mo2CTx accelerates hydrogen gas release from the electrode, exhibiting significantly enhanced catalytic activity and stability to bare MoS2 and Mo2CTx. The MoS2/Mo2CTx nanoarray possesses excellent stability at −100 mA/cm2 for 100 h with only 3% overpotential increase. Our work provides guidance for developing high-stability MXene-based catalysts by virtue of in situ bonding between nanoarray and MXene.

Smartphones, due to the integration of low-cost GNSS chips and linearly polarized antennas, frequently experience abnormal errors in their observations, particularly during positioning on water surfaces. In response to this issue, this paper proposes a method for detecting and correcting abnormal errors in GNSS observations on smartphones. Firstly, the state and observation equations of the Kalman filter are formulated based on the continuous and smooth characteristics of pseudorange and carrier observations. Secondly, real-time detection of abnormal error occurrence in observations is performed by assessing whether the difference between the predicted and observed values computed by the Kalman filter exceeds a specified threshold. Finally, depending on abnormal errors within the epoch, different strategies are applied for real-time reparation of observations containing anomalies. Two smartphones have been used for static tests on land and kinematic tests on water. Results show that under various environmental conditions, the proposed method effectively enhances the quality of observations on smartphones. Specifically, the method achieved a maximum improvement of 86.03% in pseudorange quality and 84.31% in carrier phase quality. The method proposed in this paper outperformed the State-Based method by approximately 10% on land and by 10–35% on water. It also shows high stability and reliability, particularly in complex environments such as navigation on water.

With the rapid development of deep learning, its powerful capabilities make it possible to perform mechanical fault diagnosis of high-voltage circuit breakers (HVCBs). Among deep learning approaches, the convolutional neural network is widely used. However, while it can extract features effectively, it also has some limitations. Specifically, it depends on a large number of training data and only takes data information into account without considering structural information. These shortcomings lead to unused information and unsatisfactory model results. To address these shortcomings, this paper proposes AKNN-DMGCN, a novel dynamic multi-attention graph convolutional network based on an adaptively constructed graph, which can achieve high accuracy and robust mechanical fault diagnosis of HVCBs. First, a novel adaptive k-nearest neighbor (AKNN) graph construction method is proposed to construct informative graphs. The AKNN method can mine the relationship between the original data samples and utilize the data and label information. Thus, it has high fault tolerance to noise signals and can construct a structure graph with rich and accurate information, which can improve the overall model performance. Then, a dynamic multi-attention graph convolutional network (DMGCN) is applied for mechanical fault diagnosis of HVCBs. DMGCN fully utilizes structural and numerical information representing HVCB signals to perform classification. DMGCN has a dynamic multi-attention mechanism with strong expressive ability, which allows it to achieve high diagnostic accuracy. The experimental results indicate that the accuracy of AKNN-DMGCN reaches 97.22% on a balanced dataset and 95.01% on an imbalanced dataset, which demonstrates that the proposed method is effective for both balanced and imbalanced samples.

High-voltage circuit breakers (HVCBs) handle the important tasks of controlling and safeguarding electricity networks. In the case of insufficient data samples, improving the accuracy of the traditional HVCB mechanical fault diagnosis method is difficult, so it poses challenges in meeting performance requirements for mechanical fault diagnosis. In this study, a HVCB fault diagnosis method is introduced. It utilizes a combination of grey wolf optimization (GWO) and multi-grained cascade forest (gcForest) algorithms to resolve these issues and improve the accuracy of HVCB mechanical fault diagnosis. To simplify the original vibration signal, the input feature quantity for the fault diagnosis method is obtained by calculating the energy entropy of the wavelet packet decomposition. The GWO algorithm is employed to optimize the parameters of the gcForest model, leading to identification of the optimum parameter configuration. Subsequently, the diagnostic effect in the case of a small sample size was analyzed through a VS1 vacuum circuit breaker example, and the accuracy reached 95.89%. In the case of unbalanced samples, further analysis and comparison with different methods confirm the feasibility and efficiency of the combination of GWO and gcForest algorithms. This study provides an effective solution for the diagnosis of mechanical faults in HVCBs.

Heteroepitaxial growth of Ge films on Si is necessary for the progress of integrated Si photonics technology. In this work, an in-house assembled plasma enhanced chemical vapor deposition reactor was used to grow high quality epitaxial Ge films on Si (100) substrates. Low economic and thermal budget were accomplished by the avoidance of ultra-high vacuum conditions or high temperature substrate pre-deposition bake for the process. Films were deposited with and without plasma assistance using germane (GeH4) precursor in a single step at process temperatures of 350–385 °C and chamber pressures of 1–10 Torr at various precursor flow rates. Film growth was realized at high ambient chamber pressures (>10−6 Torr) by utilizing a rigorous ex situ substrate cleaning process, closely controlling substrate loading times, chamber pumping and the dead-time prior to the initiation of film growth. Plasma allowed for higher film deposition rates at lower processing temperatures. An epitaxial growth was confirmed by X-Ray diffraction studies, while crystalline quality of the films was verified by X-ray rocking curve, Raman spectroscopy, transmission electron microscopy and infra-red spectroscopy.

Deep learning methods, especially convolutional neural networks (CNNs), have achieved good results in the partial discharge (PD) diagnosis of gas-insulated switchgear (GIS) in the laboratory. However, the relationship of features ignored in CNNs and the heavy dependance on the amount of sample data make it difficult for the model developed in the laboratory to achieve high-precision, robust diagnosis of PD in the field. To solve these problems, a subdomain adaptation capsule network (SACN) is adopted for PD diagnosis in GIS. First, the feature information is effectively extracted by using a capsule network, which improves feature representation. Then, subdomain adaptation transfer learning is used to accomplish high diagnosis performance on the field data, which alleviates the confusion of different subdomains and matches the local distribution at the subdomain level. Experimental results demonstrate that the accuracy of the SACN in this study reaches 93.75% on the field data. The SACN has better performance than traditional deep learning methods, indicating that the SACN has potential application value in PD diagnosis of GIS.

Spin polarization is at the basis of quantum information and underlies some natural processes, but many aspects still need to be explored. Here, the authors, by quantum mechanical computations, show that even a weak spin-orbit coupling near a conical intersection can induce large spin selection, with consequences for spin manipulation in photochemical or electrochemical reactions.

BackgroundAcute myocardial infarction (AMI) is one of the most common causes of mortality around the world. Early diagnosis of AMI contributes to improving prognosis. In our study, we aimed to construct a novel predictive model for the diagnosis of AMI using an artificial neural network (ANN), and we verified its diagnostic value via constructing the receiver operating characteristic (ROC).MethodsWe downloaded three publicly available datasets (training sets GSE48060, GSE60993, and GSE66360) from Gene Expression Omnibus (GEO) database, and differentially expressed genes (DEGs) were identified between 87 AMI and 78 control samples. We applied the random forest (RF) and ANN algorithms to further identify novel gene signatures and construct a model to predict the possibility of AMI. Besides, the diagnostic value of our model was further validated in the validation sets GSE61144 (7 AMI patients and 10 controls), GSE34198 (49 AMI patients and 48 controls), and GSE97320 (3 AMI patients and 3 controls).ResultsA total of 71 DEGs were identified, of which 68 were upregulated and 3 were downregulated. Firstly, 11 key genes in 71 DEGs were screened with RF classifier for the classification of AMI and control samples. Then, we calculated the weight of each key gene using ANN. Furthermore, the diagnostic model was constructed and named neuralAMI, with significant predictive power (area under the curve [AUC] = 0.980). Finally, our model was validated with the independent datasets GSE61144 (AUC = 0.900), GSE34198 (AUC = 0.882), and GSE97320 (AUC = 1.00).ConclusionMachine learning was used to develop a reliable predictive model for the diagnosis of AMI. The results of our study provide potential gene biomarkers for early disease screening.

BackgroundAcute myocardial infarction (AMI) is a fatal disease that causes high morbidity and mortality. It has been reported that AMI is associated with immune cell infiltration. Now, we aimed to identify the potential diagnostic biomarkers of AMI and uncover the immune cell infiltration profile of AMI.MethodsFrom the Gene Expression Omnibus (GEO) data set, three data sets (GSE48060, GSE60993, and GSE66360) were downloaded. Differentially expressed genes (DEGs) from AMI and healthy control samples were screened. Furthermore, DEGs were performed via gene ontology (GO) functional and kyoto encyclopedia of genes and genome (KEGG) pathway analyses. The Gene set enrichment analysis (GSEA) was used to analyze GO terms and KEGG pathways. Utilizing the Search Tool for Retrieval of Interacting Genes/Proteins (STRING) database, a protein–protein interaction (PPI) network was constructed, and the hub genes were identified. Then, the receiver operating characteristic (ROC) curves were constructed to analyze the diagnostic value of hub genes. And, the diagnostic value of hub genes was further validated in an independent data set GSE61144. Finally, CIBERSORT was used to represent the compositional patterns of the 22 types of immune cell fractions in AMI.ResultsA total of 71 DEGs were identified. These DEGs were mainly enriched in immune response and immune-related pathways. Toll-like receptor 2 (TLR2), interleukin-1B (IL1B), leukocyte immunoglobulin-like receptor subfamily B2 (LILRB2), Fc fragment of IgE receptor Ig (FCER1G), formyl peptide receptor 1 (FPR1), and matrix metalloproteinase 9 (MMP9) were identified as diagnostic markers with the value of p < 0.05. Also, the immune cell infiltration analysis indicated that TLR2, IL1B, LILRB2, FCER1G, FPR1, and MMP9 were correlated with neutrophils, monocytes, resting natural killer (NK) cells, gamma delta T cells, and CD4 memory resting T cells. The fractions of monocytes and neutrophils were significantly higher in AMI tissues than in control tissues.ConclusionTLR2, IL1B, LILRB2, FCER1G, FPR1, and MMP9 are involved in the process of AMI, which can be used as molecular biomarkers for the screening and diagnosis of AMI. In addition, the immune system plays a vital role in the occurrence and progression of AMI.

The human brain has been a main source of inspiration for designing deep learning models. Recently, inspired by the specialized functions of two cerebral hemispheres in processing low and high spatial frequency information, some dual-path neural networks with global and local branches have been proposed to deal with both coarse- and fine-grained visual tasks simultaneously. However, in existing works, the interhemispheric communication mechanism, which is responded by the corpus callosum, the largest white matter structure in the human brain that connecting the left and right cerebral hemispheres, is still not fully explored and exploited. This paper aims to explore how the corpus callosum can inspire us to enable transfer and integration of information between global and local branches in hemisphere-inspired artificial neural networks, such that one branch can leverage the other's learned knowledge and benefit each other. To this end, we propose a gated intercommunication unit to selectively transfer useful knowledge between the two branches via attention mechanisms to alleviate the negative transfer. Experiments on sb-MNIST and two pedestrian attribute datasets show that the proposed method outperforms the compared ones in most cases.

In this paper, the CoZrTaB thin films are fabricated using sputtering on different substrates and characterized comprehensively. The CoZrTaB thin films have been fabricated in the single-layer and multi-layer structures with SiO2 as the insulator layer, of which the vibrating sample magnetometer results suggest that the saturation field and the coercivity change of the multi-layer structure can be minimized while the lamination structure can suppress the eddy current at high working frequency. Compared with the continuously sputtered 400 nm CoZrTaB thin film, the multi-layer thin film shows a hysteresis loop with a single domain and small coercivity. The surface roughness of each CoZrTaB thin film and two kinds of polyimide substrates is extracted by the atomic force microscope instrument. Besides, material characterization such as X-ray powder diffraction and Rutherford backscattering spectrometry have been conducted to acquire the information of phase and element ratio of the CoZrTaB thin film. Also, the different process conditions that could affect the magnetic properties are investigated and verified. A comparison is made with the previously reported results, sustaining the improvement of the CoZrTaB thin film on different substrates.

Background: Deep learning (DL)-assisted detection and segmentation of intracranial hemorrhage stroke in noncontrast computed tomography (NCCT) scans are well-established, but evidence on this topic is lacking. Materials and methods: PubMed and Embase databases were searched from their inception to November 2023 to identify related studies. The primary outcomes included sensitivity, specificity, and the Dice Similarity Coefficient (DSC); while the secondary outcomes were positive predictive value (PPV), negative predictive value (NPV), precision, area under the receiver operating characteristic curve (AUROC), processing time, and volume of bleeding. Random-effect model and bivariate model were used to pooled independent effect size and diagnostic meta-analysis data, respectively. Results: A total of 36 original studies were included in this meta-analysis. Pooled results indicated that DL technologies have a comparable performance in intracranial hemorrhage detection and segmentation with high values of sensitivity (0.89, 95% CI: 0.88-0.90), specificity (0.91, 95% CI: 0.89-0.93), AUROC (0.94, 95% CI: 0.93-0.95), PPV (0.92, 95% CI: 0.91-0.93), NPV (0.94, 95% CI: 0.91-0.96), precision (0.83, 95% CI: 0.77-0.90), DSC (0.84, 95% CI: 0.82-0.87). There is no significant difference between manual labeling and DL technologies in hemorrhage quantification (MD 0.08, 95% CI: -5.45-5.60, P= 0.98), but the latter takes less process time than manual labeling (WMD 2.26, 95% CI: 1.96-2.56, P=0.001). Conclusion: This systematic review has identified a range of DL algorithms that the performance was comparable to experienced clinicians in hemorrhage lesions identification, segmentation, and quantification but with greater efficiency and reduced cost. It is highly emphasized that multicenter randomized controlled clinical trials will be needed to validate the performance of these tools in the future, paving the way for fast and efficient decision-making during clinical procedure in patients with acute hemorrhagic stroke. [ABSTRACT FROM AUTHOR]