RESUMEN
Objective:To design a lung function prediction method that combines transfer learning and multimodal feature fusion, aiming to improve the accuracy of lung function prediction in patients with idiopathic pulmonary fibrosis (IPF).Methods:CT images and clinical text data were reprocessed, and an adaptive module was designed to find the most suitable lung function attenuation function for IPF patients. The feature extraction module was utilized to comprehensively extract features. The feature extraction module comprises three sub-modules, including CT feature extraction, clinical text feature extraction, and lung function feature extraction. A multimodal feature prediction network was used to comprehensively evaluate the attenuation of lung function. The pre-trained model was fine-tuned to improve the predictive performance of the model.Results:Based on the OSIC pulmonary fibrosis progression competition dataset, it is found through the adaptive module that the linear attenuation hypothesis is more in line with the trend of pulmonary function decline in patients. Different modal data prediction experiments show that the model incorporating clinical text features has better predictive ability than the model using only CT images. The model combining CT images, clinical text features, and lung function features have optimal predictive results. The lung function prediction method combining transfer learning and multimodal feature fusion has modified version of the Laplace log likelihood (LLLm) of ?6.706 5, root mean squared error (RMSE) of 184.5, and mean absolute error (MAE) of 146.2, which outperforms other methods in terms of performance. The pre-trained model has higher prediction accuracy compared to the zero base training model.Conclusions:The lung function prediction method designed by combining transfer learning and multimodal feature fusion can effectively predict the lung function status of IPF patients at different weeks, providing important support for patient health management and disease diagnosis.
RESUMEN
Systemic sclerosis (SSc) is an autoimmune disease with unknown etiology, characterized by vasculopathy, inflammation, and extensive fibrosis in the skin and organs. Fibrosis is the hallmark of SSc and contributes to its high mortality. In recent years, with the in-depth study of the epigenetics of SSc (DNA methylation, histone modification, and non-coding RNA), the DNA methylation and miRNA has been the most widely studied. Abnormal DNA methylation can influence the function of vascular endothelial cells, CD4+ T cells, and fibroblasts in SSc. MiRNAs in serum is closely related to autoantibodies, SSc disease activity and complications, and miRNAs in fibroblasts can directly affect the activation of fibroblasts.
Asunto(s)
Humanos , Metilación de ADN , Epigénesis Genética , Epigenómica , Fibroblastos , Fibrosis , Investigación , Esclerodermia SistémicaRESUMEN
Objective To investigate the expression and antibacterial function of Neutrophil extracellular traps (NETs) in systemic lupus erythematosus (SLE) patients.Methods Thirty stable SLE patients and thirty normal controls (NC) were recruited to this study.The acitivity of SLE was assessed by SLE Disease Activity Index (SLEDAI).Density gradient centrifugation was uesd to isolate neutrophilic granulocytes.Picogreen assay was used to quantify NETs formation.Colony counting method was used to compare the antibacterial rate of NETs between two groups.Variation of quantity and activities of neutrophil elastase (NE) and myeloperoxidase (MPO) on induced NETs was tested by enzyme linked immunosorbent assay (ELISA).Results There was no significant difference in the number of NETs between SLE and NC.Compared to the control group,more NETs were induced from neutrophils in SLE,the antibacterial rate of induced NETs was significantly lower,with the activities of antibacterial protein MPO decreased.Conclusions Stable SLE patients are more easily to induce NETs,and the antibacterial function of induced NETs are truly defective,may be related to the decreased activity of the antibacterial protein MPO.
RESUMEN
Objective:To analyze the trend relevant factors leading to death and their patterns over a 10-year period in inpatients with connective tissue diseases (CTDs).Methods:All clinical data about death in inpatients with CTDs were retrospectively reviewed between 2005 and 2014 at the Department of Rheumatology and Immunology in Xiangya Hospital of Central South University.Results:In the 10-year time period,the overall hospital mortality was 15.689‰.The disease itself accounted for 44.71% of the total causes of death,infection accounted for 42.94%,and comorbidities accounted for 12.35%.The constituent ratio of deaths and the average hospital mortality caused by the disease itself declined gradually year by year,and the constituent ratio of deaths caused by infection and comorbidities increased gradually year by year (P<0.05).In 2013-2014,infection was the leading cause of death,which accounted for 51.06%.The survival time for CTDs inpatients with interstitial lung disease (ILD) was shorter than that of CTDs inpatients without ILD,and even the risk of death was 1.722 times of the latter.The proportion of deaths caused by the disease itself was the highest in systemic sclerosis and systemic lupus erythematosus,that by infection was the highest in idiopathic inflammatory myopathy (IIM),and that by comorbidities was the highest in rheumatoid arthritis.Conclusion:The proportion of deaths and the hospital mortality in CTDs inpatients caused by the disease itself show a declining trend,while the proportion of deaths caused by infection and comorbidities increase.CTDs patients with ILD have shorter survival time and an increase in risk of death.
RESUMEN
miRNAs are important post-transcriptional regulators. The aberrant expression of miRNAs is strongly associated with the initiation and progression of pathophysiologic processes in a wide range of human diseases. Scleroderma (systemic sclerosis; SSc) is a highly heterogeneous autoimmune disease that includes the progressive fibrotic replacement of normal tissue architecture in multiple organs. Our previous studies have suggested that SSc skin tissues display a different miRNA expression signature than that found in normal controls. miRNAs with pro- or antifibrotic properties are found to be dysregulated in SSc skin fibrosis. Serum miRNA levels are associated with SSc activity and severity. miRNAs have the potential to be therapeutic targets and serve as biomarkers for SSc diagnosis and assessment of disease state and severity. This review summarizes the SSc miRNA expression signature and the roles of dysregulation of miRNAs in SSc tissues and serum and examines the future therapeutic potential of targeting miRNAs in the management of SSc patients.
Asunto(s)
Animales , Humanos , Biomarcadores/metabolismo , Fibrosis/etiología , MicroARNs/genética , Esclerodermia Sistémica/diagnósticoRESUMEN
Objective To investigate the clinical significance of YMDD mutation during Lamivudine therapy on chronic hepatitis B.Methods Fluorometric analysis PCR, ELISA were used to estimate the YMDD mutation, HBVDNA quantative level and HBeAg for HBV of 72 cases with chronic hepatitis B before therapy (0 month), and after Lamivudine therapy for 9,12,18 months.Results The YMDD mutation was not observed in these cases before Lamivudine therapy. The mutation was found in 8 cases (11.1%), 17 cases (23.6%) and 28 cases (38.9%) at 9, 12, 18 month for therapy. The YMDD mutation rate rose with the therapy time lasting (P<0.05). Moreover, the YmDD mutation rate in the patients with HBVDNA quantity higher than 108 copies/ml was significantly higher than that in the patients with HBVDNA quantity lower than 108 copies/ml (P<0.005). The YMDD variation rate in patients with HBeAg positive and in patients with HBeAg negative showed no significant difference (P>0.05). The HBeAg negative conversion rate was significantly higher in non-mutation group than that in mutation group (P<0.05).Conclusion The serum virus quantity may be regard as an early estimate indication of the development of YMDD mutation during Lamivudine therapy.