Search

The natural environment in the high-altitude regions of Northwest China is extremely harsh, characterized by numerous salt lakes. The high concentrations of chloride salts, sulfates, and alkali metal ions in these areas can induce alkali–silica reactions (ASRs) in concrete. These reactions generate harmful gel within the concrete, causing expansion and cracking, which significantly impacts the durability of concrete structures. This study investigates the evolution of the mechanical properties in high-performance concrete (HPC) under long-term ASR by incorporating different admixtures and varying the equivalent alkali content. A three-dimensional random aggregate mesoscopic model was used to simulate static compression tests under various operational conditions. Non-destructive testing methods were utilized to determine the expansion rate, internal, and surface damage variables of the concrete. The experimental results indicate that the 10-year expansion rate differs from the 1-year rate by approximately 1%, and under long-term ASR mitigation measures, the internal damage in the HPC is minimal, though the surface damage is more severe. As the equivalent alkali content increases, the compressive strength of the concrete cubes decreases, initially rising before falling by 5–15% over time. The HPC with only air-entraining agent added exhibited better mechanical performance than the HPC with both air-entraining and corrosion inhibitors added, with the poorest performance observed in the HPC with only a corrosion inhibitor. A relationship was established between the surface and internal damage variables, with the surface damage initially increasing rapidly before stabilizing as the internal damage rose. Numerical simulations effectively describe the damage behavior of HPC under static uniaxial compression. Comparisons with actual failure morphologies revealed that, in the cube compression tests, crack propagation directly penetrated both coarse and fine aggregates rather than circumventing them. The simulations closely matched the experimental outcomes, demonstrating their accuracy in modeling experiments. This study discusses the compressive mechanical properties of concrete under prolonged ASR through a combination of experimental and simulation approaches. It also delves into the impact of surface damage on the overall mechanical performance and failure modes of concrete. The findings provide experimental and simulation support for the concrete structures in regions with high alkali contents.

In regions characterized by the challenging combination of brine corrosion in the salt lakes and river sand with alkali silica reaction (ASR) activity in areas of the Northwest, high-performance concrete (HPC) formulated with high-volume composite mineral admixtures as ASR suppression measures has been preferred for civil engineering structures in the region. This study investigates the splitting tensile strength, corrosion products, microscopic structure characteristics, and mesoscopic mechanical mechanisms of splitting failure of such HPC under 10-year corrosion from salt lake brine. The relationship between mechanical properties and corrosion damage, as well as the characteristics of internal crack propagation paths and failure mechanisms of HPC under splitting load, are explored. The findings reveal that as the alkali content within HPC rises, corrosion damage intensifies, resulting in a reduction in splitting tensile strength. Moreover, a linear association between mechanical properties and corrosion damage is observed. Microscopic structural analysis and numerical simulation of the splitting failure process of HPC elucidate that while the substantial presence of mineral admixtures effectively suppresses the ASR risk associated with alkali-reactive aggregates in concrete, uneven ASR gel products persist. These discontinuous micro-fine interface cracks induced by the gel products and the cracks induced by the gel products around the selective alkali-active aggregate particles distributed in the local area are the initiation sources of mortar cracks in HPC splitting failure. In terms of the overall failure state observed during the concrete splitting process, mortar cracks manifest two distinct extension paths: along the coarse aggregate interface and directly through the aggregates themselves. Notably, a greater proportion of coarse aggregates are directly penetrated by mortar cracks, as opposed to the number of interface failures bypassing coarse aggregates. More importantly, the above work establishes a theoretical reference in three dimensions: macroscopic, mesoscopic, and microscopic, for studying concrete corrosion damage in complex environments such as salt lake brine corrosion and ASR inhibition.

The fermentation process of Chinese Baijiu’s fermented grains involves the intricate succession and metabolism of microbial communities, collectively shaping the Baijiu’s quality. Understanding the composition and succession of these living microbial communities within fermented grains is crucial for comprehending fermentation and flavor formation mechanisms. However, conducting high-throughput analysis of living microbial communities within the complex microbial system of fermented grains poses significant challenges. Thus, this study addressed this challenge by devising a high-throughput analysis framework using light-flavor Baijiu as a model. This framework combined propidium monoazide (PMA) pretreatment technology with amplicon sequencing techniques. Optimal PMA treatment parameters, including a concentration of 50 μM and incubation in darkness for 5 min followed by an exposure incubation period of 5 min, were identified. Utilizing this protocol, viable microorganism biomass ranging from 8.71 × 106 to 1.47 × 108 copies/μL was successfully detected in fermented grain samples. Subsequent amplicon sequencing analysis revealed distinct microbial community structures between untreated and PMA-treated groups, with notable differences in relative abundance compositions, particularly in dominant species such as Lactobacillus, Bacillus, Pediococcus, Saccharomycopsis, Issatchenkia and Pichia, as identified by LEfSe analysis. The results of this study confirmed the efficacy of PMA-amplicon sequencing technology for analyzing living microbial communities in fermented grains and furnished a methodological framework for investigating living microbial communities in diverse traditional fermented foods. This technical framework holds considerable significance for advancing our understanding of the fermentation mechanisms intrinsic to traditional fermented foods.

This research presents a new, eco-friendly, and swift method combining solid-phase extraction and hydrophobic deep eutectic solvents (DES) with high-performance liquid chromatography (SPE-DES-HPLC) for extracting and quantifying catechin and epicatechin in Shanxi aged vinegar (SAV). The parameters, such as the elution solvent type, the XAD-2 macroporous resin dosage, the DES ratio, the DES volume, the adsorption time, and the desorption time, were optimized via a one-way experiment. A central composite design using the Box–Behnken methodology was employed to investigate the effects of various factors, including 17 experimental runs and the construction of three-dimensional response surface plots to identify the optimal conditions. The results show that the optimal conditions were an HDES (tetraethylammonium chloride and octanoic acid) ratio of 1:3, an XAD-2 macroporous resin dosage of 188 mg, and an adsorption time of 11 min. Under these optimal conditions, the coefficients of determination of the method were greater than or equal to 0.9917, the precision was less than 5%, and the recoveries ranged from 98.8% to 118.8%. The environmentally friendly nature of the analytical process and sample preparation was assessed via the Analytical Eco-Scale and AGREE, demonstrating that this method is a practical and eco-friendly alternative to conventional determination techniques. In summary, this innovative approach offers a solid foundation for the assessment of flavanol compounds present in SAV samples.

This study addresses the issue of poor construction labor productivity, exploring the process and methodology for increasing construction workers’ participation in labor productivity improvement, as well as a situational awareness (SA) development approach for construction workers based on lean construction (LC). A framework for enhancing labor productivity through SA has been developed. A case study approach is utilized to describe the LC improvement process, which includes enhancing construction workers’ SA for waste minimization and process optimization and engaging them in LC with improved value stream mapping (VSM). The labor productivity measurement approach, combined with VSM, is used to evaluate the labor productivity improvement with labor productivity improvement rate, resource efficiency, and flow efficiency. The results demonstrate that the labor productivity of the case project has increased by 24.07%, with 11.54% contributing resource efficiency and 88.46% contributing flow efficiency, indicating a greater increase in flow efficiency. This study fills a research gap in terms of the combination of construction workers’ SA enhancement and the involvement of LC practices to boost labor productivity. Furthermore, this study proposes an SA development approach based on LC at three levels: waste perception, VSM implementation, and labor productivity improvement assessment. This provides new perspectives for leveraging construction workers’ SA to increase labor productivity. The improved VSM approach and labor productivity measurements provide an operationalization of workers’ participation in continuous improvement. This research is of great practical relevance for augmenting the competencies of construction laborers and inspiring them to engage in labor productivity enhancement.

The aim of this study was to examine the effects of dietary protein and lipid levels on the growth performance and homeostasis of the intestinal flora in Paramisgurnus dabryanus. An 8-week 3 × 3 two-factorial experiment was conducted to investigate the interaction between dietary crude protein (CP: 30%, 35%, 40%) and ether extract (EE: 6%, 10%, 14%) on the growth rate and the intestinal microflora of P. dabryanus. A total of 2,160 fish (5.19 ± 0.01 g) were randomly allotted to 36 aquariums each with 60 fish. Fish were fed the experimental diet twice daily. Results revealed that weight gain rate (WGR), specific growth rate (SGR), protein efficiency ratio and net protein utilization significantly increased when increasing protein levels from 30% to 40% (P

Abstract Background Based on the few available studies on the prognostic benefit of using direct oral anticoagulants (DOACs) after atrial fibrillation (AF) ablation. Therefore, this study aimed to evaluate the prognostic differences between patients who underwent radiofrequency ablation (RFA) and those without RFA taking DOACs. Methods This is a multicenter retrospective cohort study enrolling 6137 patients with non-valvular AF (NVAF) at 15 hospitals in China. Patient information was collected through a mean follow-up of 10 months and medical record queries. Clinical outcomes included major bleeding, total bleeding, thrombosis, all-cause death, and a composite endpoint of bleeding, thrombosis, and all-cause death. Results After adjusting for confounders and propensity score matching (PSM), patients with RFA of NVAF had a significantly lower risk of major bleeding [OR 0.278 (95% CI, 0.150-0.515), P

The visual perception model is critical to autonomous driving systems. It provides the information necessary for self-driving cars to make decisions in traffic scenes. We propose a lightweight multi-task network (Mobip) to simultaneously perform traffic object detection, drivable area segmentation, and lane line detection. The network consists of a shared encoder for feature extraction and two decoders for handling detection and segmentation tasks collectively. By using MobileNetV2 as the backbone and an extremely efficient multi-task architecture to implement the perception model, our network has great advantages in inference speed. The performance of the multi-task network is verified on a challenging public Berkeley Deep Drive(BDD100K) dataset. The model achieves an inference speed of 58 FPS on NVIDIA Tesla V100 while still maintaining competitive performance on all three tasks compared to other multi-task networks. Besides, the effectiveness and efficiency of the multi-task architecture are verified via ablative studies.

Objectives Antibody-mediated rejection (AMR) is a large obstacle to the long-term survival of allograft kidneys. It is urgent to find novel strategies for its prevention and treatment. Bibliometric analysis is helpful in understanding the directions of one field. Hence, this study aims to analyze the state and emerging trends of AMR in kidney transplantation.Methods Literature on AMR in kidney transplantation from 1999 to 2022 was collected from the Web of Science Core Collection. HistCite (version 12.03.17), CiteSpace (version 6.2.R2), Bibliometrix 4.1.0 Package from R language, and Gephi (https://gephi.org) were applied to the bibliometric analysis of the annual publications, leading countries/regions, core journals, references, keywords, and trend topics.Results A total of 2522 articles related to AMR in kidney transplantation were included in the analysis and the annual publications increased year by year. There were 10874 authors from 118 institutions located in 70 countries/regions contributing to AMR studies, and the United States took the leading position in both articles and citation scores. Halloran PF from Canada made the most contribution to AMR in kidney transplantation. The top 3 productive journals, American Journal of Transplantation, Transplantation, and Transplantation Proceedings, were associated with transplantation. Moreover, the recent trend topics mainly focused on transplant outcomes, survival, and clinical research.Conclusions North American and European countries/regions played central roles in AMR of kidney transplantation. Importantly, the prognosis of AMR is the hotspot in the future. Noninvasive strategies like plasma and urine dd-cfDNA may be the most potential direction in the AMR field.

Previous studies revealed that both Helicobacter pylori infection and some cytokine gene polymorphisms are risk factors for gastric diseases. The association between H. pylori and gene polymorphisms is worth exploring. Here we conducted a case–control study and systematically evaluate on association between H. pylori infection and IL4, TNFA, and IL10 polymorphisms in a Chinese Han population in northwestern China, where gastric cancer is the major burden on the health and the leading cause of death in local community. The Sequenom MassArray platform was used to screen the genotypes and 14C-urea breath test was employed to determine H. pylori infection status of 705 participants of the local rural residents. Significant association between H. pylori infection and the IL4 rs34142320 polymorphism was observed in the dominant model (OR = 0.57, 95% CI = 0.40–0.80, P = 0.030). No significant association was found between IL4 rs2243250, TNFA rs1800630, TNFA rs1800629, TNFA rs1799964, IL10 rs1800871, IL10 rs1800896 and H. pylori infection. Haplotype analysis showed that T-DEL and G-C haplotypes of the observed IL4 SNPs were significantly associated with H. pylori infection. Our analysis demonstrated that the IL4 rs34142320 polymorphism has a protective effect on H. pylori infection in Chinese Han population.

Background Rheumatic heart disease (RHD) is a serious global public health problem. Objectives This study aims to characterise the regional burden, trends, and inequalities of RHD in countries and territories in the Asian Region. Methods The RHD disease burden was measured in terms of the numbers of cases and deaths, prevalence, disability-adjusted life years (DALYs), disability-loss healthy life years (YLDs), and years of life lost (YLLs) in 48 countries in the Asian Region. Data on RHD were extracted from the 2019 Global Burden of Disease. This study analysed changing trends in the burden between 1990 and 2019, quantified regional inequalities in mortality, and classified countries by 2019 YLLs. Results There were an estimated 22 246 127 cases of RHD in the Asian Region in 2019 and 249 830 deaths. The prevalence of RHD in the Asian Region in 2019 was 9% lower than the global estimate, while mortality was 41% higher. The mortality rate for RHD in the Asian Region trended downwards from 1990 to 2019, with an average annual percentage change of −3.2% (95% UI −3.3 to −3.1). From 1990 to 2019, absolute inequality in RHD-related mortality decreased in the Asian Region while relative inequality increased. Of the 48 countries studied, twelve had the highest level of RHD YLLs in 2017 and the smallest reduction in YLLs from 1990 to 2019. Conclusion Although the burden of RHD in the Asian Region has steadily decreased since 1990, it remains a serious public health issue requiring greater attention. In the Asian Region, inequalities in the distribution of the RHD burden remain significant, with economically deprived countries typically bearing a greater share of the load.

Abstract Background Thrombolysis-related intracranial hemorrhage has a high mortality rate, and many factors can cause intracranial hemorrhage. Until now, systematic reviews and assessments of the certainty of the evidence have not been updated. Aim We conducted a systematic review to identify risk factors for thrombolysis-related intracranial hemorrhage. Method The protocol for this systematic review was prospectively registered with PROSPERO (CRD42022316160). All English studies that met the inclusion criteria published before January 2022 were obtained from PubMed, EMBASE, Web of Science, and Cochrane Library. Two researchers independently screened articles, extracted data, and evaluated the quality and evidence of the included studies. Risk factors for intracranial hemorrhage were used as the outcome index of this review. Random or fixed-effect models were used in statistical methods. Results Of 6083 citations, we included 105 studies in our analysis. For intracranial hemorrhage, moderate-certainty evidence showed a probable association with age, National Institutes of Health stroke scale, leukoaraiosis, hypertension, atrial fibrillation, diabetes, total cholesterol, proteinuria, fibrinogen levels, creatinine, homocysteine, early infarct signs, antiplatelet therapy and anticoagulant therapy; In addition, we found low-certainty evidence that there may be little to no association between risk of intracranial hemorrhage and weight, sex, platelet count, uric acid, albumin and white matter hyperintensity. Leukoaraiosis, cardiovascular disease, total cholesterol, white blood cell count, proteinuria, fibrinogen levels, creatinine, homocysteine and early CT hypodensities are not included in most intracranial hemorrhage risk assessment models. Conclusion This study informs risk prediction for thrombolysis-related intracranial hemorrhage, it also informs guidelines for intracranial hemorrhage prevention and future research.

In this study, ultrafine-grained (UFG) ferrite/martensite (F/M) layer-structured (LS) steels were fabricated by hot rolling of intercritical annealed bainite steels with a rolling reduction of 75% to ease the strength-toughness trade-off dilemma, and the effect of prior-austenite grain (PAG) size of the bainitic steels on the microstructure and mechanical properties were systematically studied. The results showed that the layer thickness of martensite and ferrite was not affected by the PAG size, but the spacing of parallel lamellae bands (PLS), which evolved from the packet of bainite, decreased with the decrease of PAG size. The PLS had negligible influence on strength and ductility, but the decrease of the PLS led to the increase of delamination and both room temperature (RT) and cryogenic toughness enhancement. By reducing the PLS to introduce more delamination in this steel, the RT and cryogenic impact energy were increased 5.7 times (301 J) and 21 times (102 J at −196 °C), but without the sacrifice of strength (over 1.5 GPa) and ductility (total elongation of about 14%), compared with the initial bainite steel with the same composition respectively. The significantly improved toughness, especially the cryogenic toughness, was considered to result from the special UFG dual-phase layered structure as strain localization could be restrained and ductile fracture could be promoted by this special microstructure even at −196 °C. The cryogenic toughness improvement with the decrease of the spacing of PLS was confirmed to originate from the ductile crack path increase induced by delamination.

BackgroundLead is widely distributed. Lead exposure interferes with early life development in zebrafish, but the mechanisms by which lead exposure affects skeletal development and cardiac development are not clear as yet. ObjectiveTo investigate the molecular mechanisms of bone development and cardiac development toxicity induced by lead acetate exposure. MethodsZebrafish embryos were exposed to different concentrations of lead acetate (0, 6, 12, 24, and 48 μmol·L−1) for 3 h post-fertilization (3 hpf) until 5 d post-fertilization (5 dpf). The malformation phenotypes of 5 dpf were counted, and the mRNA expressions of spinal development-related genes (bmp2b, bmp4, bmp9, runx2a, runx2b) and heart development-related genes (nkx2.5, myh6, myh7) were detected by quantitative PCR (qPCR). Expressions of genes of development-related regulatory pathways including Wnt/β-catenin pathway (wnt5a, wnt8a, wnt10a, β-catenin) and TGF-β pathway (tgf-β1, tgf-β2) as well as key molecule eph of Eph-Ephrin signaling were analyzed. ResultsAt 5 dpf, the zebrafish in the lead acetate treated groups showed deformed phenotypes including spinal curvature and pericardial sac edema compared to the control group. In the lead acetate groups at 24 and 48 μmol·L−1, the spinal curvature deformity rates reached 26.47% and 71.52% (P

Abstract The problem of solving a class of Sylvester‐conjugate periodic matrix equations is investigated in this paper. Utilising conjugate gradient method, an iterative algorithm is provided, from which a matrix sequence can be generated to approximate the unknown matrix of the equation to be solved. Theoretical derivation proves that the proposed algorithm is convergent starting from any initial value, and simulation examples show the effectiveness of the proposed algorithm.

Abstract The parameter identification problem of linear discrete period time‐varying (LDPV) systems is studied in this paper and a two‐step identification algorithm based on the recursive least squares principle is proposed. The recursive principle‐based identification algorithm is mostly used to deal with the parameter identification of time‐invariant systems. Combine with the cyclic reconstruction method, the LDPV system is converted to a linear time‐invariant system. Then, based on this and combined with recursive least squares identification, a discrimination algorithm is proposed for the parameter estimation of the LDPV system. Finally, a numerical simulation example is given to demonstrate the effectiveness of the proposed algorithm.

Recently, deep learning methods, particularly the convolutional neural networks, have been extensively employed for extracting spectral–spatial features in hyperspectral image (HSI) classification tasks, yielding promising results. Conventional methods often use small image patches as input and combine spectral and spatial features with fixed strategies. However, the equal treatment of all pixels within heterogeneous patches can negatively impact feature extraction performance. In this article, we propose a semisupervised dual-branch spectral–spatial adversarial representation learning (SSARL) method for HSI classification. SSARL adaptively assigns attention weights to different pixels and adds a spectral constraint to spatial features. Our approach consists of three main components: 1) a dual-branch framework designed to independently extract spectral and spatial information from pixel and patch samples; 2) a class consistency loss that adaptively combines spectral and spatial classification results, mitigating the adverse effects of heterogeneous patches and enabling appropriate feature selection for various situations; and 3) the deep learning model on the labeled sample size by adding the adversarial representation module and conditional entropy to two branches, reducing the deep learning model's reliance on labeled sample size. Experimental results demonstrate that SSARL outperforms competitive methods on small-sized (0.3%–5%) labeled samples and exhibits superior performance for boundary test pixels.

This work aimed to adopt a transformer model combined with deep learning neural network to discuss the segmentation of medical ultrasound images. A network combining a transformer model with a deep neural network model (ConvTrans-Net) is proposed. The image content is preselected based on a multilayer perceptron and attention mechanism, different feature vectors are concatenated and fed into the multilayer perceptron, and the results of multiple attentions are mapped to a larger dimensional space using a feed-forward network. The lesion areas segmented by ultrasonic scan were analysed, and an attention mechanism and multilayer perceptron were combined to preselect image content. The performance and convergence of the model were analysed, and the Jaccard similarity coefficient precision and recall of the model were measured. In the experiment, two different iterative step sizes were selected, the convergence trend of the model increased with the increase in the number of iterative steps, and the model gradually stabilized. The Jaccard of ConvTrans-Net was 85.21%. The precision (85.17%) and recall (89.65%) were significantly higher than those of EfficientNet and DeepViT-L, and the differences were significant (P < 0.05). The experimental results show that the proposed model is stable, and the combination of Transformer model and deep learning neural network has a good effect on ultrasound image segmentation, which has some practical application value.

Abstract Background Porcine Teschovirus (PTV), also named Teschovirus A, is prevalent in pig populations, mainly causing neurological symptoms, diarrhea, pneumonia, and reproductive failure, however the morbidity and mortality are usually low in pig farms. Case presentation In this study, we reported a PTV outbreak investigation in one large-scale pig farm in China with severe symptoms including diarrhea, lethargy, locomotor ataxia, nystagmus, paralysis of the hind limbs, and coma in piglets. More importantly, the mortality reached 38% in suckling pigs, which is remarkably high in PTV history. A novel PTV strain, named HeNZ1, was isolated from cerebral samples of one suckling pig and the genome sequence was obtained by NGS sequencing. Phylogenetic and evolutionary divergence analyses revealed that HeNZ1 belongs to PTV genotype 2. Surprisingly, the VP1 coding region of HeNZ1 shares the highest sequence similarity with European PTV-2 strains, instead of China domestic PTV-2 strains, implying it may not derive from China local PTV-2 strains. Multiple sequence alignment and B cell epitope prediction of PTV VP1 and VP2 protein revealed 10 B cell epitopes, 5 mutant clusters and 36 unique mutation sites, of which 19 unique mutation sites are located in B cell epitopes and exposed on the surface of VP1 or VP2, implying significant antigenic drift potential of HeNZ1. Conclusion These results indicate that HeNZ1 is a highly virulent PTV-2 strain, which capable of causing severe neurological symptoms and high mortality in piglets. Bioinformatic analysis suggest that HeNZ1 is genetically and antigenically different from other Chinese PTV-2 strains. Overall, current case expanded our understanding of PTV-2 clinical spectrum and revealed the emergence of a highly virulent PTV-2 strain with substantial genetic diversity and antigenic drift potential in VP1 and VP2.

Suillus bovinus is a wild edible ectomycorrhizal fungus with important economic and ecological value, which often forms an ectomycorrhiza with pine trees. We know little about the mechanisms associated with the metabolism and symbiosis of S. bovinus and its effects on the nutritional value. In this study, the whole-genome sequencing of S. bovinus was performed using Illumina, HiFi, and Hi-C technologies, and the sequencing data were subjected to genome assembly, gene prediction, and functional annotation to obtain a high-quality chromosome-level genome of S. bovinus. The final assembly of the S. bovinus genome includes 12 chromosomes, with a total length of 43.03 Mb, a GC content of 46.58%, and a contig N50 size of 3.78 Mb. A total of 11,199 coding protein sequences were predicted from genome annotation. The S. bovinus genome contains a large number of small secreted proteins (SSPs) and genes that encode enzymes related to carbohydrates, as well as genes related to terpenoids, auxin, and lipochitooligosaccharides. These genes may contribute to symbiotic processes. The whole-genome sequencing and genetic information provide a theoretical basis for a deeper understanding of the mechanism of the mycorrhizal symbiosis of S. bovinus and can serve as a reference for comparative genomics of ectomycorrhizal fungi.

High-precision spatial-temporal wind power prediction technology is of great significance for ensuring the safe and stable operation of power grids. The development of artificial intelligence technology provides a new scheme for modeling with strong spatial-temporal correlation. In addition, the existing prediction models are mostly ‘black box’ models, lacking interpretability, which may lead to a lack of trust in the model by power grid dispatchers. Therefore, improving the model to obtain interpretability has become an important challenge. In this paper, an interpretable short-term wind power prediction model based on ensemble deep graph neural network is designed. Firstly, the graph network model (GNN) with an attention mechanism is applied to the aggregate and the spatial-temporal features of wind power data are extracted, and the interpretable ability is obtained. Then, the long short-term memory (LSTM) method is used to process the extracted features and establish a wind power prediction model. Finally, the random sampling algorithm is used to optimize the hyperparameters to improve the learning rate and performance of the model. Through multiple comparative experiments and a case analysis, the results show that the proposed model has a higher prediction accuracy than other traditional models and obtains reasonable interpretability in time and space dimensions.

Background: Warfarin has a narrow therapeutic window and individual variation, and patients require regular follow-up and monitoring of the International Normalized Ratio (INR) for dose adjustment. The calculation method of Warfarin Dosing Calculator (WDC) software is based on the European and American populations, and its accuracy in the Chinese population is yet to be verified.Objective: This study was to evaluate the feasibility of applying Warfarin Dosing Calculator software intervention in a real-world clinical research setting in China.Methods: The pilot study divided the included patients after valve replacement into an experimental group and a control group, with 38 cases in each group. In the control group, the initial dose was fixed at 2.5 mg/d and the dose was adjusted empirically during the study period; in the experimental group, the Warfarin Dosing Calculator software was applied to guide the dosing, and patients in both groups were followed up for 3 months. Analysis of the incidence anticoagulation outcomes and excessive anticoagulation events in both groups. Kaplan-Meier survival curves were used to analyze the correlation between different dosing regimens and first International Normalized Ratio attainment, and Logrank tests were performed.Results: The mean time required for first International Normalized Ratio compliance in the experimental group was 4.38 days less than in the control group, and the mean number of tests was 1.43 less (p < 05). Time in therapeutic range (TTR) was significantly higher in the experimental group than in the control group (p < 05). Kaplan-Meier survival curve analysis showed that the first International Normalized Ratio attainment rate was significantly higher in the experimental group than in the control group (p = 01). No major bleeding events occurred in either group, but other excessive anticoagulation events (INR>3.5 and minor bleeding) were significantly reduced in the experimental group compared with the control group (p < 05).Conclusion: Application of Warfarin Dosing Calculator software to guide individualized warfarin dosing may be better than a fixed dose of 2.5 mg/d. It may be shorten the time to first International Normalized Ratio attainment, and the attainment rate in the same time, and can better improve the mean Time in therapeutic range level value and reduce excessive anticoagulation events, which improves the safety of warfarin anticoagulation therapy in clinical practice.Clinical Trial Registration:https://www.chictr.org.cn/showproj.html?proj=52793, ChiCTR2000032393.