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.

Objective To observe the effects of Daizong Prescription on glycogen metabolism in adipose tissue of obese mice;To explore its regulatory mechanism in activating browning in the white adipose tissue.Methods A obesity model was established by feeding high-fat diet to C57BL/6J mice.The obese mice were divided into model group,metformin group(0.15 g/kg),and Daizong Prescription low-(0.20 g/kg)and high-dosage(0.40 g/kg)groups.Mice fed a standard diet were set as the normal group,with 12 mice in each group.Each medication group was given corresponding drugs by gavage for 6 consecutive weeks.Body mass and fasting blood glucose were monitored,serum triglycerides(TG),total cholesterol(TC),high-density lipoprotein cholesterol(HDL-C),and low-density lipoprotein cholesterol(LDL-C)contents were measured.Brown adipose tissue from the interscapular region and white adipose tissue from the inguinal,perirenal and epididymal region were collected,the adipose tissue mass was measured,and the body fat coefficient was calculated.HE staining was performed to observe morphological changes in adipose tissue,PAS staining was used to observe glycogen distribution in adipose tissue,immunohistochemistry staining was performed to detect the expressions of Gys2,Ppp1r3c,and GSK-3β in inguinal white adipose tissue.Results Compared with the normal group,the body mass and fasting blood glucose in different time points of the model group significant increase(P<0.05,P<0.01),and serum TC and HDL-C contents significantly increased(P<0.01);the mass and body fat coefficient of white adipose tissue in inguinal,perirenal,and epididymis significantly increased(P<0.01),the cells in white adipose tissue in inguinal were hypertrophic and appeared as large vacuoles,with less glycogen accumulation,the expressions of Gys2 and Ppp1r3c significantly decreased(P<0.01).Compared with the model group,the mice in Daizong Prescription high-dosage group showed a significant decrease in body mass and fasting blood glucose at 4 and 6 weeks of administration(P<0.05,P<0.01),and the contents of serum TG,TC,HDL-C,and LDL-C were significantly decreased(P<0.01);the mass and body fat coefficient in white adipose tissue of perirenal and epididymal significantly decreased(P<0.05,P<0.01),and the mass of inguinal white adipose tissue significantly decreased(P<0.05),multiple irregularly shaped small vacuoles could be seen in inguinal white adipose tissue,accompanied by nuclear aggregation and increased glycogen accumulation,the expressions of Gys2 and Ppp1r3c significantly increased(P<0.01).There was no significant difference in the expression of GSK-3β inguinal white adipose tissue of mice among the groups.Conclusion Daizong Prescription can increase the activity of Gys2 by upregulating the expression of Ppp1r3c,promote glycogen synthesis,induce browning of adipose tissue,increase fat heat production,and improve obesity and related disorders of glycolipid metabolism.

BACKGROUND: Currently, the effect of the 2022 nationwide coronavirus disease 2019 (COVID-19) wave on the perioperative prognosis of surgical patients in China is unclear. Thus, we aimed to explore its influence on postoperative morbidity and mortality in surgical patients. METHODS: An ambispective cohort study was conducted at Xijing Hospital, China. We collected 10-day time-series data from December 29 until January 7 for the 2018-2022 period. The primary outcome was major postoperative complications (Clavien-Dindo class III-V). The association between COVID-19 exposure and postoperative prognosis was explored by comparing consecutive 5-year data at the population level and by comparing patients with and without COVID-19 exposure at the patient level. RESULTS: The entire cohort consisted of 3350 patients (age: 48.5 ± 19.2 years), including 1759 females (52.5%). Overall, 961 (28.7%) underwent emergency surgery, and 553 (16.5%) had COVID-19 exposure (from the 2022 cohort). At the population level, major postoperative complications occurred in 5.9% (42/707), 5.7% (53/935), 5.1% (46/901), 9.4% (11/117), and 22.0% (152/690) patients in the 2018-2022 cohorts, respectively. After adjusting for potential confounding factors, the 2022 cohort (80% patients with COVID-19 history) had a significantly higher postoperative major complication risk than did the 2018 cohort (adjusted risk difference [aRD], 14.9% (95% confidence interval [CI], 11.5-18.4%); adjusted odds ratio [aOR], 8.19 (95% CI, 5.24-12.81)). At the patient level, the incidence of major postoperative complications was significantly greater in patients with (24.6%, 136/553) than that in patients without COVID-19 history (6.0% [168/2797]; aRD, 17.8% [95% CI, 13.6-22.1%]; aOR, 7.89 [95% CI, 5.76-10.83]). Secondary outcomes of postoperative pulmonary complications were consistent with primary findings. These findings were verified through sensitivity analyses using time-series data projections and propensity score matching. CONCLUSION: Based on a single-center observation, patients with recent COVID-19 exposure were likely to have a high incidence of major postoperative complications. REGISTRATION NCT05677815 at https://clinicaltrials.gov/ .
Female ; Humans ; Adult ; Middle Aged ; Aged ; Cohort Studies ; COVID-19/complications* ; Pandemics ; Retrospective Studies ; Postoperative Complications/epidemiology*