Explore the vast range of titles available.

This study retrospectively collected clinical data from 480 patients with connective tissue diseases (CTDs) at Nanjing First Hospital between August 2019 and December 2023 to develop and validate a multi-classification machine learning (ML) model for assessing depression risk. Addressing the limitations of traditional assessment tools, six ML models were constructed using univariate analysis and the LASSO algorithm, with the categorical boosting (Catboost) model emerging as the best performer, demonstrating strong predictive ability across different depression severity levels (none_F1 = 0.879, mild_F1 = 0.627, moderate and severe_F1 = 0.588). Additionally, the study provided an interpretation of the best-performing model using SHAP and developed a user-friendly R Shiny application ( https://macnomogram.shinyapps.io/Catboost/ ) to facilitate clinical use. The findings suggest that the Catboost model represents a significant advancement in assessing depression risk among CTD patients, highlighting the potential of ML in enhancing mental health management for this patient population.

Background Despite endovascular coiling as a valid modality in treatment of aneurysmal subarachnoid hemorrhage (aSAH), there is a risk of poor prognosis. However, the clinical utility of previously proposed early prediction tools remains limited. We aimed to develop a clinically generalizable machine learning (ML) models for accurately predicting unfavorable outcomes in aSAH patients after endovascular coiling. Methods Functional outcomes at 6 months after endovascular coiling were assessed via the modified Rankin Scale (mRS) and unfavorable outcomes were defined as mRS 3-6. Five ML algorithms (logistic regression, random forest, support vector machine, deep neural network, and extreme gradient boosting) were used for model development. The area under precision-recall curve (AUPRC) and receiver operating characteristic curve (AUROC) was used as main indices of model evaluation. SHapley Additive exPlanations (SHAP) method was applied to interpret the best-performing ML model. Results A total of 371 patients were eventually included into this study, and 85.4% of them had favorable outcomes. Among the five models, the DNN model had a better performance with AUPRC of 0.645 (AUROC of 0.905). Postoperative GCS score, size of aneurysm, and age were the top three powerful predictors. The further analysis of five random cases presented the good interpretability of the DNN model. Conclusion Interpretable clinical prediction models based on different ML algorithms have been successfully constructed and validated, which would serve as reliable tools in optimizing the treatment decision-making of aSAH. Our DNN model had better performance to predict the unfavorable outcomes at 6 months in aSAH patients compared with Yan’s nomogram model.

Background Chronic lymphocytic leukemia (CLL) is a common hematologic malignancy. Although previous research has explored associations between plasma proteins and CLL, the causal relationships remain unclear. This study used Mendelian randomization (MR) to investigate the causal relationship between 7156 plasma proteins and CLL risk. Methods A two-sample MR analysis assessed the impact of specific plasma proteins on CLL risk, using data from the Finngen Proteomics project (analyzing 828 participants) and the UK Biobank. Additional analyses included colocalization, phenomenon-wide MR, and protein–protein interaction networks. Results The study identified nine plasma proteins significantly associated with CLL risk. Increased levels of Peptidyl-prolyl cis-trans isomerase E (PPIE) (OR = 1.66, 95% CI 1.22–2.27, P = 0.001) were associated with an increased risk of developing CLL, whereas Protein O-Mannosyltransferase 2 (POMGNT2) (OR = 0.62, 95% CI 0.41–0.91, P = 0.017) and C–C Motif Chemokine Ligand 14(CCL14) (OR = 0.80, 95% CI 0.67–0.94, P = 0.010) were associated with a reduced risk of CLL. Colocalization analysis suggested that PPIE may share pathogenic variants with CLL (PP.H4 = 0.758). Phenomenon-wide MR analysis of PPIE also indicated associations with other clinical features, including rheumatic diseases and type 2 diabetes. Protein–protein interaction and drug-gene interaction analyses highlighted CDC5L and SNW1 as potential therapeutic targets. Conclusion This study identifies nine plasma proteins linked to CLL risk, with PPIE offering new insights into the disease's pathogenesis. Further research is needed to validate these findings and explore their potential as therapeutic targets.

IgA nephropathy (IgAN) and Sjogren's syndrome (SS) are two autoimmune diseases with undetermined etiology and related to abnormal activation of lymphocytes. This study aims to explore the crucial genes, pathways and immune cells between IgAN and SS. Gene expression profiles of IgAN and SS were obtained from the Gene Expression Omnibus and Nephroseq data. Differentially expressed gene (DEG) and weighted gene co-expression network analyses (WGCNA) were done to identify common genes. Enrichment analysis and protein–protein interaction network were used to explore potential molecular pathways and crosstalk genes between IgAN and SS. The results were further verified by external validation and immunohistochemistry (IHC) analysis. Additionally, immune cell analysis and transcription factor prediction were also conducted. The DEG analysis revealed 28 commonly up-regulated genes, while WGCNA identified 98 interactively positive-correlated module genes between IgAN and SS. The enrichment analysis suggested that these genes were mainly involved in the biological processes of response to virus and antigen processing and presentation. The external validation and IHC analysis identified 5 hub genes (PSMB8, PSMB9, IFI44, ISG15, and CD53). In the immune cell analysis, the effector memory CD8 T and T follicular helper cells were significantly activated, and the corresponding proportions showed positively correlations with the expressions of the 5 hub genes in the two autoimmune diseases. Together, our data identified the crosstalk genes, molecular pathways, and immune cells underlying the IgAN and SS, which provides valuable insights into the intricate mechanisms of these diseases and offers potential intervention targets.

This article examines the vibration properties of reactors across various operational scenarios, including normal operation, interturn arc short circuit faults, and interturn metal fusion short circuit faults. It begins by analyzing the vibration mechanism of reactors, drawing upon principles of electromagnetic induction and Ampere’s law. Then, a multi condition mechanical-electromagnetic interaction model was established for the series reactor, and the axial electrodynamic force distribution of the reactor was analyzed. Finally, a vibration characteristics test platform for series reactors under multiple operating conditions was built, and the vibration velocity distribution of the reactors was analyzed. The research results indicate that under normal operating condition, the maximum vibration velocity of the reactor appears at its lower end; When the Interturn arc short circuit fault occurs, the vibration speed at different positions of the reactor increases, and the vibration velocity at the short-circuit point will significantly increase with the development of the short-circuit fault; When the interturn metal fusion short circuit fault occurs, the amplitude of the vibration signal at the short-circuit point is greater than that of the arc short-circuit vibration signal.

The flora and community physiognomy of degraded plantation ecosystems on purple soil were investigated in Ninghua County of Fujian Province, China to understand the relationship between plant diversity and ecosystem processes.. Four different restoration communities (labeled as ecological restoration treatment I, II, Ill and IV) were selected by space-time replacement method according to the erosion intensity in degraded purple soil ecosystem. The results showed that there were totally 86 plant species belonging to 78 genera and 43 families in the degraded purple soil ecosystem. Of the 15 types of distribution area in spermatophyte genus, 12 types were found in the purple soil ecosystem. Along restoration gradient from low to high, plant growth type and life form spectra became abundant more and more, and the spermatophyte genera for each distribution area type and genera numbers for different foliage characters increased as well. It is concluded that the plant flora and physiognomy in ecological restoration process become more complex and diverse, indicating that the forest ecosystem on purple soil tends to be more stable.