Efficient Clustering Network Based on Matrix Factorization

Contrastive learning is a significant research direction in the field of deep learning.However,existing data augmentation methods often lead to issues such as semantic drift in generated views while the complexity of model pre-training limits further improvement in the performance of existing methods.To address these challenges,we propose the Efficient Clustering Network based on Matrix Factorization(ECN-MF).Specifically,we design a batched low-rank Singular Value Decomposition(SVD)algorithm for data augmentation to eliminate redundant information and uncover major patterns of variation and key information in the data.Additionally,we design a Mutual Information-Enhanced Clustering Module(MI-ECM)to accelerate the training process by leveraging a simple architecture to bring samples from the same cluster closer while pushing samples from other clusters apart.Extensive experiments on six datasets demonstrate that ECN-MF exhibits more effective performance compared to state-of-the-art algorithms.

NFA:A neural factorization autoencoder based online telephony fraud detection

The proliferation of internet communication channels has increased telecom fraud,causing billions of euros in losses for customers and the industry each year.Fraudsters constantly find new ways to engage in illegal activity on the network.To reduce these losses,a new fraud detection approach is required.Telecom fraud detection involves identifying a small number of fraudulent calls from a vast amount of call traffic.Developing an effective strategy to combat fraud has become challenging.Although much effort has been made to detect fraud,most existing methods are designed for batch processing,not real-time detection.To solve this problem,we propose an online fraud detection model using a Neural Factorization Autoencoder(NFA),which analyzes customer calling patterns to detect fraudulent calls.The model employs Neural Factorization Machines(NFM)and an Autoencoder(AE)to model calling patterns and a memory module to adapt to changing customer behaviour.We evaluate our approach on a large dataset of real-world call detail records and compare it with several state-of-the-art methods.Our results show that our approach outperforms the baselines,with an AUC of 91.06%,a TPR of 91.89%,an FPR of 14.76%,and an F1-score of 95.45%.These results demonstrate the effectiveness of our approach in detecting fraud in real-time and suggest that it can be a valuable tool for preventing fraud in telecommunications networks.

Health risk assessment of trace metal(loid)s in agricultural soils based on Monte Carlo simulation coupled with positive matrix factorization model in Chongqing, southwest China

This study aimed to investigate the pollution characteristics, source apportionment, and health risks associated with trace metal(loid)s(TMs) in the major agricultural producing areas in Chongqing, China. We analyzed the source apportionment and assessed the health risk of TMs in agricultural soils by using positive matrix factorization(PMF) model and health risk assessment(HRA) model based on Monte Carlo simulation. Meanwhile, we combined PMF and HRA models to explore the health risks of TMs in agricultural soils by different pollution sources to determine the priority control factors. Results showed that the average contents of cadmium(Cd), arsenic (As), lead(Pb), chromium(Cr), copper(Cu), nickel(Ni), and zinc(Zn) in the soil were found to be 0.26, 5.93, 27.14, 61.32, 23.81, 32.45, and 78.65 mg/kg, respectively. Spatial analysis and source apportionment analysis revealed that urban and industrial sources, agricultural sources, and natural sources accounted for 33.0%, 27.7%, and 39.3% of TM accumulation in the soil, respectively. In the HRA model based on Monte Carlo simulation, noncarcinogenic risks were deemed negligible(hazard index <1), the carcinogenic risks were at acceptable level(10^(-6)<total carcinogenic risk ≤ 10^(-4)), with higher risks observed for children compared to adults. The relationship between TMs, their sources, and health risks indicated that urban and industrial sources were primarily associated with As, contributing to 75.1% of carcinogenic risks and 55.7% of non-carcinogenic risks, making them the primary control factors. Meanwhile, agricultural sources were primarily linked to Cd and Pb, contributing to 13.1% of carcinogenic risks and 21.8% of non-carcinogenic risks, designating them as secondary control factors.

Significant risk factors for intensive care unit-acquired weakness:A processing strategy based on repeated machine learning

BACKGROUND Intensive care unit-acquired weakness(ICU-AW)is a common complication that significantly impacts the patient's recovery process,even leading to adverse outcomes.Currently,there is a lack of effective preventive measures.AIM To identify significant risk factors for ICU-AW through iterative machine learning techniques and offer recommendations for its prevention and treatment.METHODS Patients were categorized into ICU-AW and non-ICU-AW groups on the 14th day post-ICU admission.Relevant data from the initial 14 d of ICU stay,such as age,comorbidities,sedative dosage,vasopressor dosage,duration of mechanical ventilation,length of ICU stay,and rehabilitation therapy,were gathered.The relationships between these variables and ICU-AW were examined.Utilizing iterative machine learning techniques,a multilayer perceptron neural network model was developed,and its predictive performance for ICU-AW was assessed using the receiver operating characteristic curve.RESULTS Within the ICU-AW group,age,duration of mechanical ventilation,lorazepam dosage,adrenaline dosage,and length of ICU stay were significantly higher than in the non-ICU-AW group.Additionally,sepsis,multiple organ dysfunction syndrome,hypoalbuminemia,acute heart failure,respiratory failure,acute kidney injury,anemia,stress-related gastrointestinal bleeding,shock,hypertension,coronary artery disease,malignant tumors,and rehabilitation therapy ratios were significantly higher in the ICU-AW group,demonstrating statistical significance.The most influential factors contributing to ICU-AW were identified as the length of ICU stay(100.0%)and the duration of mechanical ventilation(54.9%).The neural network model predicted ICU-AW with an area under the curve of 0.941,sensitivity of 92.2%,and specificity of 82.7%.CONCLUSION The main factors influencing ICU-AW are the length of ICU stay and the duration of mechanical ventilation.A primary preventive strategy,when feasible,involves minimizing both ICU stay and mechanical ventilation duration.

Are TrkB receptor agonists the right tool to fulfill the promises for a therapeutic value of the brain-derived neurotrophic factor?

Brain-derived neurotrophic factor signaling via its receptor tro pomyosin receptor kinase B regulates several crucial physiological processes.It has been shown to act in the brain,promoting neuronal survival,growth,and plasticity as well as in the rest of the body where it is involved in regulating for instance aspects of the metabolism.Due to its crucial and very pleiotro pic activity,reduction of brain-derived neurotrophic factor levels and alterations in the brain-derived neurotrophic factor/tropomyosin receptor kinase B signaling have been found to be associated with a wide spectrum of neurological diseases.Howeve r,because of its poor bioavailability and pharmacological properties,brain-derived neurotrophic factor itself has a very low therapeutic value.Moreover,the concomitant binding of exogenous brain-derived neurotrophic factor to the p75 neurotrophin receptor has the potential to elicit several unwanted and deleterious side effects.Therefo re,developing tools and approaches to specifically promote tropomyosin receptor kinase B signaling has become an important goal of translational research.Among the newly developed tools are different categories of tropomyosin receptor kinase B receptor agonist molecules.In this review,we give a comprehensive description of the diffe rent tro pomyosin receptor kinase B receptor agonist drugs developed so far and of the res ults of their application in animal models of several neurological diseases.Moreover,we discuss the main benefits of tropomyosin receptor kinase B receptor agonists,concentrating especially on the new tropomyosin receptor kinase B agonist antibodies.The benefits observed both in vitro and in vivo upon application of tropomyosin receptor kinase B receptor agonist drugs seem to predominantly depend on their general neuroprotective activity and their ability to promote neuronal plasticity.Moreover,tro pomyosin receptor kinase B agonist antibodies have been shown to specifically bind the tropomyosin receptor kinase B receptor and not p75 neurotrophin receptor.Therefore,while,based on the current knowledge,the tropomyosin receptor kinase B receptor agonists do not seem to have the potential to reve rse the disease pathology per se,promoting brainderived neurotrophic factor/tro pomyosin receptor kinase B signaling still has a very high therapeutic relevance.

Transcription factor OsSPL10 interacts with OsJAmyb to regulate blast resistance in rice

Transcription factors(TFs)play essential roles in transcriptional reprogramming during activation of plant immune responses to pathogens.OsSPL10(SQUAMOSA promoter binding protein-like10)is an important TF regulating trichome development and salt tolerance in rice.Here we report that knockout of OsSPL10 reduces whereas its overexpression enhances rice resistance to blast disease.OsSPL10 positively regulates chitin-induced immune responses including reactive oxygen species(ROS)burst and callose deposition.We show that OsSPL10 physically associates with OsJAmyb,an important TF involved in jasmonic acid(JA)signaling,and positively regulates its protein stability.We then prove that OsJAmyb positively regulates resistance to blast.Our results reveal a molecular module consisting of OsSPL10 and OsJAmyb that positively regulates blast resistance.

Analysis of the influencing factors and clinical related characteristics of pulmonary tuberculosis in patients with type 2 diabetes mellitus

BACKGROUND In China,the prevalence of type 2 diabetes mellitus(T2DM)among diabetic patients is estimated to be between 90%-95%.Additionally,China is among the 22 countries burdened by a high number of tuberculosis cases,with approximately 4.5 million individuals affected by active tuberculosis.Notably,T2DM poses a significant risk factor for the development of tuberculosis,as evidenced by the increased incidence of T2DM coexisting with pulmonary tuberculosis(T2DMPTB),which has risen from 19.3%to 24.1%.It is evident that these two diseases are intricately interconnected and mutually reinforcing in nature.AIM To elucidate the clinical features of individuals diagnosed with both T2DM and tuberculosis(T2DM-PTB),as well as to investigate the potential risk factors associated with active tuberculosis in patients with T2DM.METHODS T2DM-PTB patients who visited our hospital between January 2020 and January 2023 were selected as the observation group,Simple DM patients presenting to our hospital in the same period were the control group,Controls and case groups were matched 1:2 according to the principle of the same sex,age difference(±3)years and disease duration difference(±5)years,patients were investigated for general demographic characteristics,diabetes-related characteristics,body immune status,lifestyle and behavioral habits,univariate and multivariate analysis of the data using conditional logistic regression,calculate the odds ratio(OR)values and 95%CI of OR values.RESULTS A total of 315 study subjects were included in this study,including 105 subjects in the observation group and 210 subjects in the control group.Comparison of the results of both anthropometric and biochemical measures showed that the constitution index,systolic blood pressure,diastolic blood pressure and lymphocyte count were significantly lower in the case group,while fasting blood glucose and high-density lipoprotein cholesterol levels were significantly higher than those in the control group.The results of univariate analysis showed that poor glucose control,hypoproteinemia,lymphopenia,TB contact history,high infection,smoking and alcohol consumption were positively associated with PTB in T2DM patients;married,history of hypertension,treatment of oral hypoglycemic drugs plus insulin,overweight,obesity and regular exercise were negatively associated with PTB in T2DM patients.Results of multivariate stepwise regression analysis found lymphopenia(OR=17.75,95%CI:3.40-92.74),smoking(OR=12.25,95%CI:2.53-59.37),history of TB contact(OR=6.56,95%CI:1.23-35.03)and poor glycemic control(OR=3.37,95%CI:1.11-10.25)was associated with an increased risk of developing PTB in patients with T2DM,While being overweight(OR=0.23,95%CI:0.08-0.72)and obesity(OR=0.11,95%CI:0.02-0.72)was associated with a reduced risk of developing PTB in patients with T2DM.CONCLUSION T2DM-PTB patients are prone to worse glycemic control,higher infection frequency,and a higher proportion of people smoking,drinking alcohol,and lack of exercise.Lymphopenia,smoking,history of TB exposure,poor glycemic control were independent risk factors for T2DM-PTB,and overweight and obesity were associated with reduced risk of concurrent PTB in patients with T2DM.

Biological factors driving colorectal cancer metastasis

Approximately 20%of colorectal cancer(CRC)patients present with metastasis at diagnosis.Among Stage I-III CRC patients who undergo surgical resection,18%typically suffer from distal metastasis within the first three years following initial treatment.The median survival duration after the diagnosis of metastatic CRC(mCRC)is only 9 mo.mCRC is traditionally considered to be an advanced stage malignancy or is thought to be caused by incomplete resection of tumor tissue,allowing cancer cells to spread from primary to distant organs;however,increa-sing evidence suggests that the mCRC process can begin early in tumor development.CRC patients present with high heterogeneity and diverse cancer phenotypes that are classified on the basis of molecular and morphological alterations.Different genomic and nongenomic events can induce subclone diversity,which leads to cancer and metastasis.Throughout the course of mCRC,metastatic cascades are associated with invasive cancer cell migration through the circulatory system,extravasation,distal seeding,dormancy,and reactivation,with each step requiring specific molecular functions.However,cancer cells presenting neoantigens can be recognized and eliminated by the immune system.In this review,we explain the biological factors that drive CRC metastasis,namely,genomic instability,epigenetic instability,the metastatic cascade,the cancer-immunity cycle,and external lifestyle factors.Despite remarkable progress in CRC research,the role of molecular classification in therapeutic intervention remains unclear.This review shows the driving factors of mCRC which may help in identifying potential candidate biomarkers that can improve the diagnosis and early detection of mCRC cases.

Sorl1 knockout inhibits expression of brain-derived neurotrophic factor:involvement in the development of late-onset Alzheimer's disease

Sortilin-related receptor 1(SORL1)is a critical gene associated with late-onset Alzheimer’s disease.SORL1 contributes to the development and progression of this neurodegenerative condition by affecting the transport and metabolism of intracellularβ-amyloid precursor protein.To better understand the underlying mechanisms of SORL1 in the pathogenesis of late-onset Alzheimer s disease,in this study,we established a mouse model of SorI1 gene knockout using cluste red regularly inters paced short palindro mic repeats-associated protein 9 technology.We found that Sorl1-knocko ut mice displayed deficits in learning and memory.Furthermore,the expression of brain-derived neurotrophic factor was significantly downregulated in the hippocampus and co rtex,and amyloidβ-protein deposits were observed in the brains of 5orl1-knockout mice.In vitro,hippocampal neuronal cell synapses from homozygous Sorl1-knockout mice were impaired.The expression of synaptic proteins,including Drebrin and NR2B,was significantly reduced,and also their colocalization.Additionally,by knocking out the Sorl1 gene in N2a cells,we found that expression of the N-methyl-D-aspartate receptor,NR2B,and cyclic adenosine monophosphate-response element binding protein was also inhibited.These findings suggest that SORL1 participates in the pathogenesis of late-onset Alzheimer s disease by regulating the N-methyl-D-aspartate receptor NR2B/cyclic adenosine monophosphate-response element binding protein signaling axis.

Spatial-temporal differentiation and influencing factors of rural settlements in mountainous areas: an example of Liangshan Yi Autonomous Prefecture, Southwestern China

Rural settlement is the basic spatial unit for compact communities in rural area. Scientific exploration of spatial-temporal differentiation and its influencing factors is the premise of spatial layout rationalization. Based on land use data of Liangshan Yi Autonomous Prefecture(hereinafter referred to as Liangshan Prefecture) in Sichuan Province, China from 1980 to 2020, compactness index, fractal dimension, imbalance index, location entropy and the optimal parameters-based geographical detector(OPGD) model are used to analyze the spatial-temporal evolution of the morphological characteristics of rural settlements, and to explore the influence of natural geographical factors, socioeconomic factors, and policy factors on the spatial differentiation of rural settlements. The results show that:(1) From 1980 to 2020, the rural settlements area in Liangshan Prefecture increased by 15.96 km^(2). In space, the rural settlements are generally distributed in a local aggregation, dense in the middle and sparse around the periphery. In 2015, the spatial density and expansion index of rural settlements reached the peak.(2) From 1980 to 2020, the compactness index decreased from 0.7636 to 0.7496, the fractal dimension increased from 1.0283 to 1.0314, and the fragmentation index decreased from 0.1183 to 0.1047. The spatial morphological structure of rural settlements tended to be loose, the shape contour tended to be complex, the degree of fragmentation decreased, and the spatial distribution was significantly imbalanced.(3) The results of OPGD detection in 2015 show that the influence of each factor is slope(0.2371) > traffic accessibility(0.2098) > population(0.1403) > regional GDP(0.1325) > elevation(0.0987) > poverty alleviation(0). The results of OPGD detection in 2020 show that the influence of each factor is slope(0.2339) > traffic accessibility(0.2198) > population(0.1432) > regional GDP(0.1219) > poverty alleviation(0.0992) > elevation(0.093). Natural geographical factors(slope and elevation) are the basic factors affecting the spatial distribution of rural settlements, and rural settlements are widely distributed in the river valley plain and the second half mountain area. Socioeconomic factors(traffic accessibility, population, and regional GDP) have a greater impact on the spatial distribution of rural settlements, which is an important factor affecting the spatial distribution of rural settlements. Policy factors such as poverty alleviation relocation have an indispensable impact on the spatial distribution of rural settlements. The research results can provide decisionmaking basis for the spatial arrangement of rural settlements in Liangshan Prefecture, and optimize the implementation of rural revitalization policies.

Prevalence and risk factors of diabetes mellitus among elderly patients in the Lugu community

BACKGROUND Age is a significant risk factor of diabetes mellitus(DM).With the develop of population aging,the incidence of DM remains increasing.Understanding the epidemiology of DM among elderly individuals in a certain area contributes to the DM interventions for the local elderly individuals with high risk of DM.AIM To explore the prevalence of DM among elderly individuals in the Lugu community and analyze the related risk factors to provide a valid scientific basis for the health management of elderly individuals.METHODS A total of 4816 elderly people who came to the community for physical examination were retrospectively analyzed.The prevalence of DM among the elderly was calculated.The individuals were divided into a DM group and a non-DM group according to the diagnosis of DM to compare the differences in diastolic blood pressure(DBP)and systolic blood pressure(SBP),fasting blood glucose,body mass index(BMI),waist-to-hip ratio(WHR)and incidence of hypertension(HT),coronary heart disease(CHD),and chronic kidney disease(CKD).RESULTS DM was diagnosed in 32.70%of the 4816 elderly people.The BMI of the DM group(25.16±3.35)was greater than that of the non-DM group(24.61±3.78).The WHR was 0.90±0.04 in the non-DM group and 0.90±0.03 in the DM group,with no significant difference.The left SBP and SBP in the DM group were 137.9 mmHg±11.92 mmHg and 69.95 mmHg±7.75 mmHg,respectively,while they were 126.6 mmHg±12.44 mmHg and 71.15 mmHg±12.55 mmHg,respectively,in the non-DM group.These findings indicate higher SBP and lower DBP in DM patients than in those without DM.In the DM group,1274 patients were diagnosed with HT,accounting for 80.89%.Among the 3241 non-DM patients,1743(53.78%)were hypertensive and 1498(46.22%)were nonhypertensive.The DM group had more cases of HT than did the non-DM group.There were more patients with CHD or CKD in the DM group than in the non-DM group.There were more patients who drank alcohol more frequently(≥3 times)in the DM group than in the non-DM group.CONCLUSION Older adults in the Lugu community are at a greater risk of DM.In elderly individuals,DM is closely related to high BMI and HT,CHD,and CKD.Physical examinations should be actively carried out for elderly people to determine their BMI,SBP,DBP,and other signs,and sufficient attention should be given to abnormalities in the above signs before further diagnosis.

Assessment of Dependent Performance Shaping Factors in SPAR-H Based on Pearson Correlation Coefficient

With the improvement of equipment reliability,human factors have become the most uncertain part in the system.The standardized Plant Analysis of Risk-Human Reliability Analysis(SPAR-H)method is a reliable method in the field of human reliability analysis(HRA)to evaluate human reliability and assess risk in large complex systems.However,the classical SPAR-H method does not consider the dependencies among performance shaping factors(PSFs),whichmay cause overestimation or underestimation of the risk of the actual situation.To address this issue,this paper proposes a new method to deal with the dependencies among PSFs in SPAR-H based on the Pearson correlation coefficient.First,the dependence between every two PSFs is measured by the Pearson correlation coefficient.Second,the weights of the PSFs are obtained by considering the total dependence degree.Finally,PSFs’multipliers are modified based on the weights of corresponding PSFs,and then used in the calculating of human error probability(HEP).A case study is used to illustrate the procedure and effectiveness of the proposed method.

DoS Attack Detection Based on Deep Factorization Machine in SDN

Software-Defined Network(SDN)decouples the control plane of network devices from the data plane.While alleviating the problems presented in traditional network architectures,it also brings potential security risks,particularly network Denial-of-Service(DoS)attacks.While many research efforts have been devoted to identifying new features for DoS attack detection,detection methods are less accurate in detecting DoS attacks against client hosts due to the high stealth of such attacks.To solve this problem,a new method of DoS attack detection based on Deep Factorization Machine(DeepFM)is proposed in SDN.Firstly,we select the Growth Rate of Max Matched Packets(GRMMP)in SDN as detection feature.Then,the DeepFM algorithm is used to extract features from flow rules and classify them into dense and discrete features to detect DoS attacks.After training,the model can be used to infer whether SDN is under DoS attacks,and a DeepFM-based detection method for DoS attacks against client host is implemented.Simulation results show that our method can effectively detect DoS attacks in SDN.Compared with the K-Nearest Neighbor(K-NN),Artificial Neural Network(ANN)models,Support Vector Machine(SVM)and Random Forest models,our proposed method outperforms in accuracy,precision and F1 values.

Prognostic model for prostate cancer based on glycolysis-related genes and non-negative matrix factorization analysis

Background:Establishing an appropriate prognostic model for PCa is essential for its effective treatment.Glycolysis is a vital energy-harvesting mechanism for tumors.Developing a prognostic model for PCa based on glycolysis-related genes is novel and has great potential.Methods:First,gene expression and clinical data of PCa patients were downloaded from The Cancer Genome Atlas(TCGA)and Gene Expression Omnibus(GEO),and glycolysis-related genes were obtained from the Molecular Signatures Database(MSigDB).Gene enrichment analysis was performed to verify that glycolysis functions were enriched in the genes we obtained,which were used in nonnegative matrix factorization(NMF)to identify clusters.The correlation between clusters and clinical features was discussed,and the differentially expressed genes(DEGs)between the two clusters were investigated.Based on the DEGs,we investigated the biological differences between clusters,including immune cell infiltration,mutation,tumor immune dysfunction and exclusion,immune function,and checkpoint genes.To establish the prognostic model,the genes were filtered based on univariable Cox regression,LASSO,and multivariable Cox regression.Kaplan–Meier analysis and receiver operating characteristic analysis validated the prognostic value of the model.A nomogram of the risk score calculated by the prognostic model and clinical characteristics was constructed to quantitatively estimate the survival probability for PCa patients in the clinical setting.Result:The genes obtained from MSigDB were enriched in glycolysis functions.Two clusters were identified by NMF analysis based on 272 glycolysis-related genes,and a prognostic model based on DEGs between the two clusters was finally established.The prognostic model consisted of LAMPS,SPRN,ATOH1,TANC1,ETV1,TDRD1,KLK14,MESP2,POSTN,CRIP2,NAT1,AKR7A3,PODXL,CARTPT,and PCDHGB2.All sample,training,and test cohorts from The Cancer Genome Atlas(TCGA)and the external validation cohort from GEO showed significant differences between the high-risk and low-risk groups.The area under the ROC curve showed great performance of this prognostic model.Conclusion:A prognostic model based on glycolysis-related genes was established,with great performance and potential significance to the clinical application.

Vertex centrality of complex networks based on joint nonnegative matrix factorization and graph embedding

Finding crucial vertices is a key problem for improving the reliability and ensuring the effective operation of networks,solved by approaches based on multiple attribute decision that suffer from ignoring the correlation among each attribute or the heterogeneity between attribute and structure. To overcome these problems, a novel vertex centrality approach, called VCJG, is proposed based on joint nonnegative matrix factorization and graph embedding. The potential attributes with linearly independent and the structure information are captured automatically in light of nonnegative matrix factorization for factorizing the weighted adjacent matrix and the structure matrix, which is generated by graph embedding. And the smoothness strategy is applied to eliminate the heterogeneity between attributes and structure by joint nonnegative matrix factorization. Then VCJG integrates the above steps to formulate an overall objective function, and obtain the ultimately potential attributes fused the structure information of network through optimizing the objective function. Finally, the attributes are combined with neighborhood rules to evaluate vertex's importance. Through comparative analyses with experiments on nine real-world networks, we demonstrate that the proposed approach outperforms nine state-of-the-art algorithms for identification of vital vertices with respect to correlation, monotonicity and accuracy of top-10 vertices ranking.

Predictive factors and model validation of post-colon polyp surgery Helicobacter pylori infection

BACKGROUND Recently,research has linked Helicobacter pylori(H.pylori)stomach infection to colonic inflammation,mediated by toxin production,potentially impacting colorectal cancer occurrence.AIM To investigate the risk factors for post-colon polyp surgery,H.pylori infection,and its correlation with pathologic type.METHODS Eighty patients who underwent colon polypectomy in our hospital between January 2019 and January 2023 were retrospectively chosen.They were then randomly split into modeling(n=56)and model validation(n=24)sets using R.The modeling cohort was divided into an H.pylori-infected group(n=37)and an H.pylori-uninfected group(n=19).Binary logistic regression analysis was used to analyze the factors influencing the occurrence of H.pylori infection after colon polyp surgery.A roadmap prediction model was established and validated.Finally,the correlation between the different pathological types of colon polyps and the occurrence of H.pylori infection was analyzed after colon polyp surgery.RESULTS Univariate results showed that age,body mass index(BMI),literacy,alcohol consumption,polyp pathology type,high-risk adenomas,and heavy diet were all influential factors in the development of H.pylori infection after intestinal polypectomy.Binary multifactorial logistic regression analysis showed that age,BMI,and type of polyp pathology were independent predictors of the occurrence of H.pylori infection after intestinal polypectomy.The area under the receiver operating characteristic curve was 0.969[95%confidence interval(95%CI):0.928–1.000]and 0.898(95%CI:0.773–1.000)in the modeling and validation sets,respectively.The slope of the calibration curve of the graph was close to 1,and the goodness-of-fit test was P>0.05 in the two sets.The decision analysis curve showed a high rate of return in both sets.The results of the correlation analysis between different pathological types and the occurrence of H.pylori infection after colon polyp surgery showed that hyperplastic polyps,inflammatory polyps,and the occurrence of H.pylori infection were not significantly correlated.In contrast,adenomatous polyps showed a significant positive correlation with the occurrence of H.pylori infection.CONCLUSION Age,BMI,and polyps of the adenomatous type were independent predictors of H.pylori infection after intestinal polypectomy.Moreover,the further constructed column-line graph prediction model of H.pylori infection after intestinal polypectomy showed good predictive ability.

Analysis of risk factors leading to anxiety and depression in patients with prostate cancer after castration and the construction of a risk prediction model

BACKGROUND Cancer patients often suffer from severe stress reactions psychologically,such as anxiety and depression.Prostate cancer(PC)is one of the common cancer types,with most patients diagnosed at advanced stages that cannot be treated by radical surgery and which are accompanied by complications such as bodily pain and bone metastasis.Therefore,attention should be given to the mental health status of PC patients as well as physical adverse events in the course of clinical treatment.AIM To analyze the risk factors leading to anxiety and depression in PC patients after castration and build a risk prediction model.METHODS A retrospective analysis was performed on the data of 120 PC cases treated in Xi'an People's Hospital between January 2019 and January 2022.The patient cohort was divided into a training group(n=84)and a validation group(n=36)at a ratio of 7:3.The patients’anxiety symptoms and depression levels were assessed 2 wk after surgery with the Self-Rating Anxiety Scale(SAS)and the Selfrating Depression Scale(SDS),respectively.Logistic regression was used to analyze the risk factors affecting negative mood,and a risk prediction model was constructed.RESULTS In the training group,35 patients and 37 patients had an SAS score and an SDS score greater than or equal to 50,respectively.Based on the scores,we further subclassified patients into two groups:a bad mood group(n=35)and an emotional stability group(n=49).Multivariate logistic regression analysis showed that marital status,castration scheme,and postoperative Visual Analogue Scale(VAS)score were independent risk factors affecting a patient's bad mood(P<0.05).In the training and validation groups,patients with adverse emotions exhibited significantly higher risk scores than emotionally stable patients(P<0.0001).The area under the curve(AUC)of the risk prediction model for predicting bad mood in the training group was 0.743,the specificity was 70.96%,and the sensitivity was 66.03%,while in the validation group,the AUC,specificity,and sensitivity were 0.755,66.67%,and 76.19%,respectively.The Hosmer-Lemeshow test showed aχ^(2) of 4.2856,a P value of 0.830,and a C-index of 0.773(0.692-0.854).The calibration curve revealed that the predicted curve was basically consistent with the actual curve,and the calibration curve showed that the prediction model had good discrimination and accuracy.Decision curve analysis showed that the model had a high net profit.CONCLUSION In PC patients,marital status,castration scheme,and postoperative pain(VAS)score are important factors affecting postoperative anxiety and depression.The logistic regression model can be used to successfully predict the risk of adverse psychological emotions.

Adolescent suicide risk factors and the integration of socialemotional skills in school-based prevention programs

Adolescents are considered one of the most vulnerable groups affected by suicide.Rapid changes in adolescents’physical and mental states,as well as in their lives,significantly and undeniably increase the risk of suicide.Psychological,social,family,individual,and environmental factors are important risk factors for suicidal behavior among teenagers and may contribute to suicide risk through various direct,indirect,or combined pathways.Social-emotional learning is considered a powerful intervention measure for addressing the crisis of adolescent suicide.When deliberately cultivated,fostered,and enhanced,selfawareness,self-management,social awareness,interpersonal skills,and responsible decision-making,as the five core competencies of social-emotional learning,can be used to effectively target various risk factors for adolescent suicide and provide necessary mental and interpersonal support.Among numerous suicide intervention methods,school-based interventions based on social-emotional competence have shown great potential in preventing and addressing suicide risk factors in adolescents.The characteristics of school-based interventions based on social-emotional competence,including their appropriateness,necessity,cost-effectiveness,comprehensiveness,and effectiveness,make these interventions an important means of addressing the crisis of adolescent suicide.To further determine the potential of school-based interventions based on social-emotional competence and better address the issue of adolescent suicide,additional financial support should be provided,the combination of socialemotional learning and other suicide prevention programs within schools should be fully leveraged,and cooperation between schools and families,society,and other environments should be maximized.These efforts should be considered future research directions.

Coupled multiphysical model for investigation of influence factors in the application of microbially induced calcite precipitation

The study presents a comprehensive coupled thermo-bio-chemo-hydraulic(T-BCH)modeling framework for stabilizing soils using microbially induced calcite precipitation(MICP).The numerical model considers relevant multiphysics involved in MICP,such as bacterial ureolytic activities,biochemical reactions,multiphase and multicomponent transport,and alteration of the porosity and permeability.The model incorporates multiphysical coupling effects through well-established constitutive relations that connect parameters and variables from different physical fields.It was implemented in the open-source finite element code OpenGeoSys(OGS),and a semi-staggered solution strategy was designed to solve the couplings,allowing for flexible model settings.Therefore,the developed model can be easily adapted to simulate MICP applications in different scenarios.The numerical model was employed to analyze the effect of various factors,including temperature,injection strategies,and application scales.Besides,a TBCH modeling study was conducted on the laboratory-scale domain to analyze the effects of temperature on urease activity and precipitated calcium carbonate.To understand the scale dependency of MICP treatment,a large-scale heterogeneous domain was subjected to variable biochemical injection strategies.The simulations conducted at the field-scale guided the selection of an injection strategy to achieve the desired type and amount of precipitation.Additionally,the study emphasized the potential of numerical models as reliable tools for optimizing future developments in field-scale MICP treatment.The present study demonstrates the potential of this numerical framework for designing and optimizing the MICP applications in laboratory-,prototype-,and field-scale scenarios.

Diverse Deep Matrix Factorization With Hypergraph Regularization for Multi-View Data Representation

Deep matrix factorization(DMF)has been demonstrated to be a powerful tool to take in the complex hierarchical information of multi-view data(MDR).However,existing multiview DMF methods mainly explore the consistency of multi-view data,while neglecting the diversity among different views as well as the high-order relationships of data,resulting in the loss of valuable complementary information.In this paper,we design a hypergraph regularized diverse deep matrix factorization(HDDMF)model for multi-view data representation,to jointly utilize multi-view diversity and a high-order manifold in a multilayer factorization framework.A novel diversity enhancement term is designed to exploit the structural complementarity between different views of data.Hypergraph regularization is utilized to preserve the high-order geometry structure of data in each view.An efficient iterative optimization algorithm is developed to solve the proposed model with theoretical convergence analysis.Experimental results on five real-world data sets demonstrate that the proposed method significantly outperforms stateof-the-art multi-view learning approaches.