Polymeric viologen-based electron transfer mediator for improving the photoelectrochemical water splitting on Sb2Se3 photocathode.

The photogenerated charge carrier separation and transportation of inside photocathodes can greatly influence the performance of photoelectrochemical (PEC) H2 production devices. Coupling TiO2 with p-type semiconductors to construct heterojunction structures is one of the most widely used strategies to facilitate charge separation and transportation. However, the band position of TiO2 could not perfectly match with all p-type semiconductors. Here, taking antimony selenide (Sb2Se3) as an example, a rational strategy was developed by introducing a viologen electron transfer mediator (ETM) containing polymeric film (poly-1,1'-dially-[4,4'-bipyridine]-1,1'-diium, denoted as PV2+) at the interface between Sb2Se3 and TiO2 to regulate the energy band alignment, which could inhibit the recombination of photogenerated charge carriers of interfaces. With Pt as a catalyst, the constructed Sb2Se3/PV2+/TiO2/Pt photocathode showed a superior PEC hydrogen generation activity with a photocurrent density of -18.6 mA cm-2 vs. a reversible hydrogen electrode (RHE) and a half-cell solar-to-hydrogen efficiency (HC-STH) of 1.54% at 0.17 V vs. RHE, which was much better than that of the related Sb2Se3/TiO2/Pt photocathode without PV2+ (-9.8 mA cm-2, 0.51% at 0.10 V vs. RHE).

ESMSec: Prediction of Secreted Proteins in Human Body Fluids Using Protein Language Models and Attention.

The secreted proteins of human body fluid have the potential to be used as biomarkers for diseases. These biomarkers can be used for early diagnosis and risk prediction of diseases, so the study of secreted proteins of human body fluid has great application value. In recent years, the deep-learning-based transformer language model has transferred from the field of natural language processing (NLP) to the field of proteomics, leading to the development of protein language models (PLMs) for protein sequence representation. Here, we propose a deep learning framework called ESM Predict Secreted Proteins (ESMSec) to predict three types of proteins secreted in human body fluid. The ESMSec is based on the ESM2 model and attention architecture. Specifically, the protein sequence data are firstly put into the ESM2 model to extract the feature information from the last hidden layer, and all the input proteins are encoded into a fixed 1000 × 480 matrix. Secondly, multi-head attention with a fully connected neural network is employed as the classifier to perform binary classification according to whether they are secreted into each body fluid. Our experiment utilized three human body fluids that are important and ubiquitous markers. Experimental results show that ESMSec achieved average accuracy of 0.8486, 0.8358, and 0.8325 on the testing datasets for plasma, cerebrospinal fluid (CSF), and seminal fluid, which on average outperform the state-of-the-art (SOTA) methods. The outstanding performance results of ESMSec demonstrate that the ESM can improve the prediction performance of the model and has great potential to screen the secretion information of human body fluid proteins.

A joint model for lesion segmentation and classification of MS and NMOSD.

Introduction: Multiple sclerosis (MS) and neuromyelitis optic spectrum disorder (NMOSD) are mimic autoimmune diseases of the central nervous system with a very high disability rate. Their clinical symptoms and imaging findings are similar, making it difficult to diagnose and differentiate. Existing research typically employs the T2-weighted fluid-attenuated inversion recovery (T2-FLAIR) MRI imaging technique to focus on a single task in MS and NMOSD lesion segmentation or disease classification, while ignoring the collaboration between the tasks. Methods: To make full use of the correlation between lesion segmentation and disease classification tasks of MS and NMOSD, so as to improve the accuracy and speed of the recognition and diagnosis of MS and NMOSD, a joint model is proposed in this study. The joint model primarily comprises three components: an information-sharing subnetwork, a lesion segmentation subnetwork, and a disease classification subnetwork. Among them, the information-sharing subnetwork adopts a dualbranch structure composed of a convolution module and a Swin Transformer module to extract local and global features, respectively. These features are then input into the lesion segmentation subnetwork and disease classification subnetwork to obtain results for both tasks simultaneously. In addition, to further enhance the mutual guidance between the tasks, this study proposes two information interaction methods: a lesion guidance module and a crosstask loss function. Furthermore, the lesion location maps provide interpretability for the diagnosis process of the deep learning model. Results: The joint model achieved a Dice similarity coefficient (DSC) of 74.87% on the lesion segmentation task and accuracy (ACC) of 92.36% on the disease classification task, demonstrating its superior performance. By setting up ablation experiments, the effectiveness of information sharing and interaction between tasks is verified. Discussion: The results show that the joint model can effectively improve the performance of the two tasks.

Comparison of the efficacy of taxanes with carboplatin and anthracyclines with taxanes in neoadjuvant chemotherapy for stage II-III triple negative breast cancer: a retrospective analysis.

PURPOSE: The neoadjuvant chemotherapy (NACT) regimen for triple negative breast cancer (TNBC) primarily consists of anthracyclines and taxanes, and the addition of platinum-based drugs can further enhance the efficacy. However, it is also accompanied by more adverse events, and considering the potential severe and irreversible toxicity of anthracyclines, an increasing number of studies are exploring nonanthracycline regimens that combine taxanes and platinum-based drugs. METHODS: The retrospective study included 273 stage II-III TNBC patients who received NACT. The AT group, consisting of 195 (71.4%) patients, received a combination of anthracyclines and taxanes, while the TCb group, consisting of 78 (28.6%) patients, received a combination of taxanes and carboplatin. Logistic regression analysis was performed to evaluate the factors influencing pathological complete response (pCR) and residual cancer burden (RCB). The log-rank test was used to assess the differences in event-free survival (EFS) and overall survival (OS) among the different treatment groups. Cox regression analysis was conducted to evaluate the factors influencing EFS and OS. RESULTS: After NACT and surgery, the TCb group had a higher rate of pCR at 44.9%, as compared to the AT group at 31.3%. The difference between the two groups was 13.6% (OR = 0.559, 95% CI 0.326-0.959, P = 0.035). The TCb group had a 57.7% rate of RCB 0-1, which was higher than the AT group's rate of 42.6%. The difference between the two groups was 15.1% (OR = 0.543, 95% CI 0.319-0.925, P = 0.024), With a median follow-up time of 40 months, the TCb group had better EFS (log-rank, P = 0.014) and OS (log-rank, P = 0.040) as compared to the AT group. Clinical TNM stage and RCB grade were identified as independent factors influencing EFS and OS, while treatment group was identified as an independent factor influencing EFS, with a close-to-significant impact on OS. CONCLUSION: In stage II-III triple TNBC patients, the NACT regimen combining taxanes and carboplatin yields higher rates of pCR and significant improvements in EFS and OS as compared to the regimen combining anthracyclines and taxanes.

A multimodal material route planning problem considering key processes at work zones.

With the continuous development of large-scale engineering projects such as construction projects, relief support, and large-scale relocation in various countries, engineering logistics has attracted much attention. This paper addresses a multimodal material route planning problem (MMRPP), which considers the transportation of engineering material from suppliers to the work zones using multiple transport modes. Due to the overall relevance and technical complexity of engineering logistics, we introduce the key processes at work zones to generate a transport solution, which is more realistic for various real-life applications. We propose a multi-objective multimodal transport route planning model that minimizes the total transport cost and the total transport time. The model by using the ε - constraint method that transforms the objective function of minimizing total transportation cost into a constraint, resulting in obtaining pareto optimal solutions. This method makes up for the lack of existing research on the combination of both engineering logistics and multimodal transportation, after which the feasibility of the model and algorithm is verified by examples. The results show that the model solution with the introduction of the key processes at work zones produces more time-efficient and less time-consuming route planning results, and that the results obtained using the ε - constraint method are more reliable than the traditional methods for solving multi-objective planning problems and are more in line with the decision maker's needs.

Application of two-dimensional speckle-tracking echocardiography in radiotherapy-related cardiac systolic dysfunction and analysis of its risk factors: a prospective cohort study.

BACKGROUND: The cardiac toxicity of radiotherapy (RT) can affect cancer survival rates over the long term. This has been confirmed in patients with breast cancer and lymphoma. However, there are few studies utilizing the two-dimensional speckle-tracking echocardiography (2D-STE) to evaluate the risk factors affecting radiation induced heart disease (RIHD), and there is a lack of quantitative data. Therefore, we intend to explore the risk factors for RIHD and quantify them using 2D-STE technology. METHODS: We ultimately enrolled 40 patients who received RT for thoracic tumors. For each patient, 2D-STE was completed before, during, and after RT and in the follow up. We analyzed the sensitivity of 2D-STE in predicting RIHD and the relationship between RT parameters and cardiac systolic function decline. RESULTS: Left ventricle global longitudinal strain (LVGLS), LVGLS of the endocardium (LVGLS-Endo), LVGLS of the epicardium (LVGLS-Epi), and right ventricle free-wall longitudinal strain (RVFWLS) decreased mid- and post-treatment compared with pre-treatment, whereas traditional parameters such as left ventricular ejection fraction (LVEF), cardiac Tei index (Tei), and peak systolic velocity of the free wall of the tricuspid annulus (s') did not show any changes. The decreases in the LVGLS and LVGLS-Endo values between post- and pre-treatment and the ratios of the decreases to the baseline values were linearly correlated with mean heart dose (MHD) (all P values < 0.05). The decreases in the LVGLS-Epi values between post- and pre-treatment and the ratios of the decreases to the baseline values were linearly correlated with the percentage of heart volume exposed to 5 Gy or more (V5) (P values < 0.05). The decrease in RVFWLS and the ratio of the decrease to the baseline value were linearly related to MHD and patient age (all P values < 0.05). Endpoint events occurred more frequently in the right side of the heart than in the left side. Patients over 56.5 years of age had a greater probability of developing right-heart endpoint events. The same was true for patients with MHD over 20.2 Gy in both the left and right sides of the heart. CONCLUSIONS: 2D-STE could detect damages to the heart earlier and more sensitively than conventional echocardiography. MHD is an important prognostic parameter for LV systolic function, and V5 may also be an important prognostic parameter. MHD and age are important prognostic parameters for right ventricle systolic function.

Harvest residue recycling rather than slash-burning results in the enhancement of soil fertility and bacterial community stability in Eucalyptus plantations.

Deforestation and slash combustion have substantial adverse impacts on the atmosphere, soil and microbe. Despite this awareness, numerous individuals persist in opting for high-intensity Eucalyptus planting through slash-burning in pursuit of immediate profits while disregarding the environmental significance and destroying the soil. Slash-unburnt agriculture can effectively safeguard the ecological environment, and compared with slash-burning, there remains a limited understanding of its regulatory mechanisms on soil fertility and microbial community. Also, large uncertainty persists regarding the utilization of harvest residues. Thoroughly investigating these questions from various perspectives encompassing physical soil characteristics, nutrient availability, bacterial community structures, and stability is crucial. To explore the ecological advantages of slash-unburnt techniques on microorganisms and their associated ecosystems, we used two slash-unburnt (Unburnt) planting techniques: Spread (naturally and evenly covering the forest floor after logging) and Stack (residues are piled along contour lines) as well as the traditional slash Burnt method (Burnt) in a Eucalyptus plantation. A comparative analysis was conducted between the two methods. We observed that over a span of 4 years, despite the initial lower application of fertilizer in the Unburnt treatments compared with the Burnt treatment during the first 2 years, the Unburnt treatment gradually caught up or even surpassed and attained similar nutrient levels as the Burnt treatment. Alphaproteobacteria was the main phyla that indicated the difference in soil bacterial communities between Burnt and Unburnt treatments. The microbial networks also highlighted the significance of the Unburnt method, as it contributed to the preservation of crucial network nodes and the stability of soil bacterial communities. Therefore, rational utilization of harvest residue may effectively avoid the vast damage caused by slash-burning to Eucalyptus trees and the soil environment but may also increase the potential for restoring soil fertility, improving fertilizer utilization efficiency, and maintaining microbial community stability over time.

Promoting Water Oxidation by Proton Acceptable Groups Surrounding Catalyst on Electrode Surface.

Large-scale hydrogen production through water splitting represents an optimal approach for storing sustainable but intermittent energy sources. However, water oxidation, a complex and sluggish reaction, poses a significant bottleneck for water splitting efficiency. The impact of outer chemical environments on the reaction kinetics of water oxidation catalytic centers remains unexplored. Herein, chemical environment impacts were integrated by featuring methylpyridinium cation group (Py+) around the classic Ru(bpy)(tpy) (bpy=2,2'-bipyridine, tpy=2,2' : 6',2''-terpyridine) water oxidation catalyst on the electrode surface via electrochemical co-polymerization. The presence of Py+ groups could significantly enhance the turnover frequencies of Ru(bpy)(tpy), surpassing the performance of typical proton acceptors such as pyridine and benzoic acid anchored around the catalyst. Mechanistic investigations reveal that the flexible internal proton acceptor anions induced by Py+ around Ru(bpy)(tpy) are more effective than conventionally anchored proton acceptors, which promoted the rate-determining proton transfer process and enhanced the rate of water nucleophilic attack during O-O bond formation. This study may provide a novel perspective on achieving efficient water oxidation systems by integrating cations into the outer chemical environments of catalytic centers.

Promoting H2 generation of BiFeO3 photocathodes by a catalyst-sensitizer dyad linked with Sn(dipicolinate)2.

An innovative method for the fabrication of a catalyst-sensitizer dyad-based photoelectrode was developed by using the coordinated interaction between the pyridine-2,6-dicarboxylic group and Sn4+. A dyad (C1 + PDI) was loaded on the mesoporous BiFeO3 (BFO) photocathode for light-driven H2 generation. The dyad could expand the light absorption range and promote the surface charge separation of BFO, resulting in an enhanced photocurrent.

The mechanism of USP43 in the development of tumor: a literature review.

Ubiquitination of the proteins is crucial for governing protein degradation and regulating fundamental cellular processes. Deubiquitinases (DUBs) have emerged as significant regulators of multiple pathways associated with cancer and other diseases, owing to their capacity to remove ubiquitin from target substrates and modulate signaling. Consequently, they represent potential therapeutic targets for cancer and other life-threatening conditions. USP43 belongs to the DUBs family involved in cancer development and progression. This review aims to provide a comprehensive overview of the existing scientific evidence implicating USP43 in cancer development. Additionally, it will investigate potential small-molecule inhibitors that target DUBs that may have the capability to function as anti-cancer medicines.

J-Aggregate Promoting NIR-II Emission for Fluorescence/Photoacoustic Imaging-Guided Phototherapy.

J-aggregate is a promising strategy to enhance second near-infrared window (NIR-II) emission, while the controlled synthesis of J-aggregated NIR-II dyes is a huge challenge because of the lack of molecular design principle. Herein, bulk spiro[fluorene-9,9'-xanthene] functionalized benzobisthiadiazole-based NIR-II dyes (named BSFX-BBT and OSFX-BBT) are synthesized with different alkyl chains. The weak repulsion interaction between the donor and acceptor units and the S…N secondary interactions make the dyes to adopt a co-planar molecular conformation and display a peak absorption >880 nm in solution. Importantly, BSFX-BBT can form a desiring J-aggregate in the condensed state, and femtosecond transient absorption spectra reveal that the excited states of J-aggregate are the radiative states, and J-aggregate can facilitate stimulated emission. Consequently, the J-aggregated nanoparticles (NPs) display a peak emission at 1124 nm with a high relative quantum yield of 0.81%. The efficient NIR-II emission, good photothermal effect, and biocompatibility make the J-aggregated NPs demonstrate efficient antitumor efficacy via fluorescence/photoacoustic imaging-guided phototherapy. The paradigm illustrates that tuning the aggregate states of NIR-II dye via spiro-functionalized strategy is an effective approach to enhance photo-theranostic performance.

Planar-structured thiadiazoloquinoxaline-based NIR-II dye for tumor phototheranostics.

Second near-infrared (NIR-II) fluorescence imaging shows huge application prospects in clinical disease diagnosis and surgical navigation, while it is still a big challenge to exploit high performance NIR-II dyes with long-wavelength absorption and high fluorescence quantum yield. Herein, based on planar π-conjugated donor-acceptor-donor systems, three NIR-II dyes (TP-DBBT, TP-TQ1, and TP-TQ2) were synthesized with bulk steric hindrance, and the influence of acceptor engineering on absorption/emission wavelengths, fluorescence efficiency and photothermal properties was systematically investigated. Compared with TP-DBBT and TP-TQ2, the TP-TQ1 based on 6,7-diphenyl-[1,2,5]thiadiazoloquinoxaline can well balance absorption/emission wavelengths, NIR-II fluorescence brightness and photothermal effects. And the TP-TQ1 nanoparticles (NPs) possess high absorption ability at a peak absorption of 877 nm, with a high relative quantum yield of 0.69% for large steric hindrance hampering the close π-π stacking interactions. Furthermore, the TP-TQ1 NPs show a desirable photothermal conversion efficiency of 48% and good compatibility. In vivo experiments demonstrate that the TP-TQ1 NPs can serve as a versatile theranostic agent for NIR-II fluorescence/photoacoustic imaging-guided tumor phototherapy. The molecular planarization strategy provides an approach for designing efficient NIR-II fluorophores with extending absorption/emission wavelength, high fluorescence brightness, and outstanding phototheranostic performance.

Computer-aided cognitive training combined with tDCS can improve post-stroke cognitive impairment and cerebral vasomotor function: a randomized controlled trial.

BACKGROUND: Post-stroke cognitive impairment (PSCI) is the focus and difficulty of poststroke rehabilitation intervention with an incidence of up to 61%, which may be related to the deterioration of cerebrovascular function. Computer-aided cognitive training (CACT) can improve cognitive function through scientific training targeting activated brain regions, becoming a popular training method in recent years. Transcranial direct current stimulation (tDCS), a non-invasive brain stimulation technique, can regulate the cerebral vascular nerve function, and has an effect on the rehabilitation of cognitive dysfunction after stroke. This study examined the effectiveness of both CACT and tDCS on cognitive and cerebrovascular function after stroke, and explored whether CACT combined with tDCS was more effective. METHODS: A total of 72 patients with PSCI were randomly divided into the conventional cognitive training (CCT) group (n = 18), tDCS group (n = 18), CACT group (n = 18), and CACT combined with tDCS group (n = 18). Patients in each group received corresponding 20-minute treatment 15 times a week for 3 consecutive weeks. Montreal Cognitive Assessment (MoCA) and the Instrumental Activities of Daily Living Scale (IADL) were used to assess patients' cognitive function and the activities of daily living ability. Transcranial Doppler ultrasound (TCD) was used to assess cerebrovascular function, including cerebral blood flow velocity (CBFV), pulse index (PI), and breath holding index (BHI). These outcome measures were measured before and after treatment. RESULTS: Compared with those at baseline, both the MoCA and IADL scores significantly increased after treatment (P < 0.01) in each group. There was no significantly difference in efficacy among CCT, CACT and tDCS groups. The CACT combined with tDCS group showed greater improvement in MoCA scores compared with the other three groups (P < 0.05), especially in the terms of visuospatial and executive. BHI significantly improved only in CACT combined with tDCS group after treatment (p ≤ 0.05) but not in the other groups. Besides, no significant difference in CBFV or PI was found before and after the treatments in all groups. CONCLUSION: Both CACT and tDCS could be used as an alternative to CCT therapy to improve cognitive function and activities of daily living ability after stroke. CACT combined with tDCS may be more effective improving cognitive function and activities of daily living ability in PSCI patients, especially visuospatial and executive abilities, which may be related to improved cerebral vasomotor function reflected by the BHI. TRIAL REGISTRATION NUMBER: The study was registered in the Chinese Registry of Clinical Trials (ChiCTR2100054063). Registration date: 12/08/2021.

MMGAT: a graph attention network framework for ATAC-seq motifs finding.

BACKGROUND: Motif finding in Assay for Transposase-Accessible Chromatin using sequencing (ATAC-seq) data is essential to reveal the intricacies of transcription factor binding sites (TFBSs) and their pivotal roles in gene regulation. Deep learning technologies including convolutional neural networks (CNNs) and graph neural networks (GNNs), have achieved success in finding ATAC-seq motifs. However, CNN-based methods are limited by the fixed width of the convolutional kernel, which makes it difficult to find multiple transcription factor binding sites with different lengths. GNN-based methods has the limitation of using the edge weight information directly, makes it difficult to aggregate the neighboring nodes' information more efficiently when representing node embedding. RESULTS: To address this challenge, we developed a novel graph attention network framework named MMGAT, which employs an attention mechanism to adjust the attention coefficients among different nodes. And then MMGAT finds multiple ATAC-seq motifs based on the attention coefficients of sequence nodes and k-mer nodes as well as the coexisting probability of k-mers. Our approach achieved better performance on the human ATAC-seq datasets compared to existing tools, as evidenced the highest scores on the precision, recall, F1_score, ACC, AUC, and PRC metrics, as well as finding 389 higher quality motifs. To validate the performance of MMGAT in predicting TFBSs and finding motifs on more datasets, we enlarged the number of the human ATAC-seq datasets to 180 and newly integrated 80 mouse ATAC-seq datasets for multi-species experimental validation. Specifically on the mouse ATAC-seq dataset, MMGAT also achieved the highest scores on six metrics and found 356 higher-quality motifs. To facilitate researchers in utilizing MMGAT, we have also developed a user-friendly web server named MMGAT-S that hosts the MMGAT method and ATAC-seq motif finding results. CONCLUSIONS: The advanced methodology MMGAT provides a robust tool for finding ATAC-seq motifs, and the comprehensive server MMGAT-S makes a significant contribution to genomics research. The open-source code of MMGAT can be found at https://github.com/xiaotianr/MMGAT , and MMGAT-S is freely available at https://www.mmgraphws.com/MMGAT-S/ .

Bioinspired photoelectrochemical NADH regeneration based on a molecular catalyst-modified photocathode.

For photoelectrochemical NADH regeneration, an electrode-supported "lipid bilayer membrane" photocathode based on a p-Si semiconductor, an electron transport mediator (OBV2+), and a [Rh(Cp*)(bpy)Cl]+ catalyst was constructed by self-assembly. Mechanistic study shows that OBV2+ can enhance the charge transfer between the semiconductor and catalyst, leading to a significant improvement of the NADH photo-regeneration rate.

A Wireless Passive Pressure-Sensing Method for Cryogenic Applications Using Magnetoresistors.

In this study, we developed a novel wireless, passive pressure-sensing method functional at cryogenic temperatures (-196 °C). The currently used pressure sensors are inconvenient and complicated in cryogenic environments for their weak low-temperature tolerances and long wires for power supply and data transmission. We propose a novel pressure-sensing method for cryogenic applications by only using low-temperature-tolerant passive devices. By innovatively integrating a magnetoresistor (MR) on a backscattering antenna, the pressure inside a cryogenic environment is transferred to a wirelessly obtainable return loss. Wireless passive measurement is thus achieved using a backscattering method. In the measurement, the pressure causes a relative displacement between the MR and a magnet. The MR's resistance changes with the varied magnetic field, thus modulating the antenna's return loss. The experimental results indicate that our fabricated sensor successfully identified different pressures, with high sensitivities of 4.3 dB/MPa at room temperature (24 °C) and 1.3 dB/MPa at cryogenic temperature (-196 °C). Additionally, our method allows for simultaneous wireless readings of multi sensors via a single reading device by separating the frequency band of each sensor. Our method performs low-cost, simple, robust, passive, and wireless pressure measurement at -196 °C; thus, it is desirable for cryogenic applications.

Single-cell multi-omics analysis of lineage development and spatial organization in the human fetal cerebellum.

Human cerebellum encompasses numerous neurons, exhibiting a distinct developmental paradigm from cerebrum. Here we conducted scRNA-seq, scATAC-seq and spatial transcriptomic analyses of fetal samples from gestational week (GW) 13 to 18 to explore the emergence of cellular diversity and developmental programs in the developing human cerebellum. We identified transitory granule cell progenitors that are conserved across species. Special patterns in both granule cells and Purkinje cells were dissected multidimensionally. Species-specific gene expression patterns of cerebellar lobes were characterized and we found that PARM1 exhibited inconsistent distribution in human and mouse granule cells. A novel cluster of potential neuroepithelium at the rhombic lip was identified. We also resolved various subtypes of Purkinje cells and unipolar brush cells and revealed gene regulatory networks controlling their diversification. Therefore, our study offers a valuable multi-omics landscape of human fetal cerebellum and advances our understanding of development and spatial organization of human cerebellum.

An unsupervised water quality anomaly detection method based on a combination of time-frequency analysis and clustering.

Anomalies in water quality, which frequently arise due to pollution, constitute a substantial menace to human health. The preservation of public welfare critically entails the timely recognition of abnormal water quality. Conventional techniques for detecting water quality anomalies face obstacles such as the necessity of expert knowledge, limited accuracy in detection, and delays in identification. In this paper, we proposed an original unsupervised technique for identifying water quality anomalies combined with time-frequency analysis and clustering (TCAD). We chose time-frequency analysis because it effectively evaluates water quality changes, generating distinct multi-band signals that reflect different aspects of water quality dynamics. We also proposed a clustering technique which can identify water quality markers and amalgamate data from multi-band signals for accurate anomaly detection. We seek to clarify the reasoning behind our methodology by portraying how time-frequency analysis and clustering address the deficiencies of conventional methods. Our experiments evaluated various indicators of water quality, and the effectiveness of our proposed approach was supported by comparative analyses with commonly used models for detecting anomalies in water quality.

2.5D transfer deep learning model for segmentation of contrast-enhancing lesions on brain magnetic resonance imaging of multiple sclerosis and neuromyelitis optica spectrum disorder.

Background: Multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD) are the two mimic autoimmune diseases of the central nervous system, which are rare in East Asia. Quantitative detection of contrast-enhancing lesions (CELs) on contrast-enhancing T1-weighted magnetic resonance (MR) images is of great significance for assessing the disease activity of MS and NMOSD. However, it is challenging to develop automatic segmentation algorithms due to the lack of data. In this work, we present an automatic segmentation model of CELs based on Fully Convolutional with Attention DenseNet (FCA-DenseNet) and transfer learning strategy to address the challenge of CEL quantification in small-scale datasets. Methods: A transfer learning approach was employed in this study, whereby pretraining was conducted using 77 MS subjects from the open access datasets (MICCAI 2016, MICCAI 2017, ISBI 2015) for white matter hyperintensity segmentation, followed by fine-tuning using 24 MS and NMOSD subjects from the local dataset for CEL segmentation. The proposed FCA-DenseNet combined the Fully Convolutional DenseNet and Convolutional Block Attention Module in order to improve the learning capability. A 2.5D data slicing strategy was used to process complex 3D MR images. U-Net, ResUNet, TransUNet, and Attention-UNet are used as comparison models to FCA-DenseNet. Dice similarity coefficient (DSC), positive predictive value (PPV), true positive rate (TPR), and volume difference (VD) are used as evaluation metrics to evaluate the performances of different models. Results: FCA-DenseNet outperforms all other models in terms of all evaluation metrics, with a DSC of 0.661±0.187, PPV of 0.719±0.201, TPR of 0.680±0.254, and VD of 0.388±0.334. Transfer learning strategy has achieved success in building segmentation models on a small-scale local dataset where traditional deep learning approaches fail to train effectively. Conclusions: The improved FCA-DenseNet, combined with transfer learning strategy and 2.5D data slicing strategy, has successfully addressed the challenges in constructing deep learning models on small-scale datasets, making it conducive to clinical quantification of brain CELs and diagnosis of MS and NMOSD.

Risk factor analysis and risk prediction study of obesity in steelworkers: model development based on an occupational health examination cohort dataset.

BACKGROUND: Obesity is increasingly recognized as a grave public health concern globally. It is associated with prevalent diseases including coronary heart disease, fatty liver, type 2 diabetes, and dyslipidemia. Prior research has identified demographic, socioeconomic, lifestyle, and genetic factors as contributors to obesity. Nevertheless, the influence of occupational risk factors on obesity among workers remains under-explored. Investigating risk factors specific to steelworkers is crucial for early detection, prediction, and effective intervention, thereby safeguarding their health. METHODS: This research utilized a cohort study examining health impacts on workers in an iron and steel company in Hebei Province, China. The study involved 5469 participants. By univariate analysis, multifactor analysis, and review of relevant literature, predictor variables were found. Three predictive models-XG Boost, Support Vector Machine (SVM), and Random Forest (RF)-were employed. RESULTS: Univariate analysis and cox proportional hazard regression modeling identified age, gender, smoking and drinking habits, dietary score, physical activity, shift work, exposure to high temperatures, occupational stress, and carbon monoxide exposure as key factors in the development of obesity in steelworkers. Test results indicated accuracies of 0.819, 0.868, and 0.872 for XG Boost, SVM, and RF respectively. Precision rates were 0.571, 0.696, and 0.765, while recall rates were 0.333, 0.592, and 0.481. The models achieved AUCs of 0.849, 0.908, and 0.912, with Brier scores of 0.128, 0.105, and 0.104, log losses of 0.409, 0.349, and 0.345, and calibration-in-the-large of 0.058, 0.054, and 0.051, respectively. Among these, the Random Forest model demonstrated superior performance. CONCLUSIONS: The research indicates that obesity in steelworkers results from a combination of occupational and lifestyle factors. Of the models tested, the Random Forest model exhibited superior predictive ability, highlighting its significant practical application.