Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective:To investigate the feasibility and effectiveness of three-dimensional visualization technology in the precise diagnosis and treatment of locally advanced differentiated thyroid cancer(DTC).Methods:A retrospective analysis was conducted on the clinical data of 196 patients with locally advanced DTC treated at the 960th Hospital of the PLA from December 2021 to August 2023. The cohort included 71 male and 125 female patients, with a mean age of 43.7 years (rangd from 18 to 77 years). All patients underwent neck-enhanced CT scans and were divided into two groups: the study group( n=102), which underwent preoperative three-dimensional visualization of CT data, and the control group( n=94), which did not. Baseline data for both groups were matched using SPSS27.0 with 1∶1 propensity score matching (PSM) and the caliper value was 0.02. A total of 49 patients were included in each group, including 35 first-time surgeries and 14 reoperation. Among the 70 first-time surgeries, 29 patients underwent robotic surgery and 41 underwent open surgery. Among the 28 reoperations, 4 underwent robotic surgery and 24 underwent open surgery. In the study group, three-dimensional visual models were used to comprehensively evaluate the tumor and metastatic lesion size, spatial location, and adjacent relationship with surrounding organs, surgical treatments were guided by these models, whereas the control group relied on two-dimensional imaging for guidance. The clinical data were statistically analyzed using SPSS27.0. Results:All operations were successfully completed. There were no statistical differences in baseline data between the two groups( P>0.05). Among first-time surgeries, the study group showed shorter operation times [175(145, 200) min vs 205(182, 249) min, P<0.001], a lower incidence of postoperative chyle leak (0 vs 8.57%, P=0.027), a higher rate of robotic surgery (48.57% vs 34.28%, P=0.225), a greater number of harvested lymph nodes [46(40, 62) vs 37(28, 56), P=0.032], a greater number of cervical lymph node metastasis[15(7, 22) vs 5(1, 14), P=0.004] and a larger diameter of metastasis lymph nodes[12(10, 16) mm vs 4(1, 10) mm, P<0.001]. There were no significant differences in intraoperative blood loss, postoperative drainage days and incidence of hypoparathyroidism( P>0.05). During the reoperation, the study group had shorter operation times[103.5(95.0, 122.5) min vs 146.50(133.25, 172.25) min, P<0.001], less intraoperative blood loss[12.50(8.75, 22.50) mL vs 30.00(17.50, 35.00) mL, P=0.021], fewer postoperative drainage days[5.00(4.00, 6.00) d vs 6.00(5.00, 7.25) d, P=0.016] and a lower incidence of hypoparathyroidism(7.14% vs 42.86%, P=0.038).The robotic surgery rate was higher in the study group (21.42% vs 7.14%, P=0.596). There were no significant differences in lymph node dissection numbers, metastatic lymph node counts, or chyle leak incidences between the two groups ( P>0.05). No acute bleeding or incision infection occurred in any patient postoperatively. Conclusion:Three-dimensional visualization technology is an effective preoperative assessment method for evaluating the resectability of tumors and metastases lesions in locally advanced DTC. It enhances the accuracy and safety of surgery for locally advanced DTC.

Objective:To explore the influence of operation timing on the prognosis of hip fracture in patients who used direct oral anticoagulant (DOAC) before injury.Methods:A retrospective case-control study was conducted to analyze the clinical data of 90 patients who used DOAC before hip fracture and were admitted to Nanjing Hospital of Chinese Medicine affiliated to Nanjing University of Chinese Medicine from January 2022 to August 2023. Among them, there were 53 males and 37 females, aged 65 to 89 years with a mean age of (76.24±6.92) years. Patients were divided into the early operation group ( n=45) and the delayed operation group ( n=45) according to the timing of operation. The early operation group underwent hip fracture surgery within 2 days after DOAC withdrawal, while the delayed operation group underwent hip fracture surgery more than 2 days after DOAC withdrawal. The two groups were compared and evaluated in terms of fracture site, surgical method, operation time, length of hospital stay, Harris hip score (HHS), intraoperative blood loss, blood transfusion rate, blood transfusion volume, hemoglobin (Hb) change rate, incidence of postoperative complications, intensive care unit (ICU) admission rate and duration, and mortality rate. The measurement data with normal distribution were expressed as mean ± standard deviation ( ± s), and intergroup comparison was performed using the t-test. The count data were expressed as cases and percentages, and intergroup comparison was conducted using the Chi-test or Fisher exact test probability method. Comparisons among multiple time points were analyzed by repeated measures analysis of variance. Results:There was no statistically significant differences were observed between the two groups in terms of fracture site and surgical method ( P>0.05). The ICU admission rate and length of hospital stay in the early operation group were lower than those in the delayed operation group, with statistically significant differences ( P<0.05). There were no statistically significant differences between the two groups in intraoperative blood loss, operation time, blood transfusion rate, blood transfusion volume, Hb change rate and other indicators ( P>0.05). The total incidence of postoperative complications in the early operation group was lower than that in the delayed operation group [15.6% (7/45) vs 53.3% (24/45)], with statistically significant difference ( P<0.05). The HHS score of the early operation group at 1 month after operation was significantly higher than that of the delayed operation group, with statistically significant difference ( F=7.75, P<0.05). At 1 and 12 months after operation, there were no statistically significant differences in the mortality between the two groups of patients who used DOAC before hip fracture [0 (0/45) vs 2.2% (1/45); 4.4% (2/45) vs 6.7% (3/45); P>0.05]. Conclusion:For patients who used DOAC before injury, hip fracture surgery within 2 days after DOAC was stopped after admission can help to reduce the ICU admission rate, shorten the length of stay, reduce the risk of postoperative complications, and promote the early recovery of hip joint function, without affecting the amount of blood loss, blood transfusion rate and blood transfusion.

Objective To investigate the work capability need of offshore workers,and then to construct the evaluation indicator system of work capability for different positions of offshore workers.Methods Literature search,cluster analysis,key events,weight calculation and expert assessment were applied in this study.Results After the indicator screening,weight calculation and expert verification,the work capability evaluation indicator system was established,which contained 5 dimensions and 24 items.The indicators were sequenced according to the weight calculation,and the coefficient of variation of each indicator was less than 20%.Conclusion The construction of the work capability evaluation indicator system for different positions of offshore workers not only improves the content of the offshore job performance evaluation system,but also meets the demand for enhancing offshore operation support.It has greatly practical significance and promotion value.

Objective To explore the correlation between the rs7296288 single nucleotide polymorphism(SNP)of the DHH gene and the onset of depression.Methods From March 2018 to December 2019,480 patients with depression in Sichuan Provincial People's Hospital,Jining Mental Hospital,Yunnan Mental Health Center were collected as the case group,and 329 patients without depression were collected as the control group.Peripheral blood samples were collected and DNA was extracted.After multiple amplification and high-throughput sequencing,statistical software was used to analyze the relevant data.Results The rs7296288 polymorphism of the DHH gene,the AA genotype was 32.9％in the control group and 36.7％in the case group,with no statistical difference;the AC genotype was 52.8％in the control group and 47.7％in the case group,with no statistical difference;the CC genotype was 14.3％in the control group and 15.6％in the case group,with no statistical difference.The co-dominant,dominant,and recessive statistical models were not statistically significant.Subgroup analysis of the degree of depressive episodes,suicide attempts,and first-episode patients did not find an association between the rs7296288 SNP locus of the DHH gene and the clinical features of depression,that is,the SNP rs7296288 of the DHH gene had no significant correlation with depression.Conclusion The rs7296288 polymorphism of DHH gene is not correlated with the pathogenesis of depression.

Objective To explore the relationship between NANOS3 and P-bodies in oocytes and the mechanism of their interaction during early oogenesis.Methods The co-localization of NANOS3 and dead box helicase 6(DDX6)in day post postnatal 1(1dpp)mouse oocytes was observed by immunofluorescence,and the interaction between NANOS3 and DDX6 was detected by immunoprecipitation.NANOS3 and DDX6 full-length plasmids were constructed to transfect HEK293T cells,and the mechanism of their interaction was investigated by immunofluorescence and immunoprecipitation.NANOS3 transfected HeLa cells to investigate whether NANOS3 had the ability of liquid-liquid phase separation(LLPS)by live-cell imaging.The proteins recruited by P-bodies in early oogenesis were identified by DDX6-immunoprecipitation-mass spectrometry(DDX6-IP-MS).Results NANOS3 and DDX6 colocalized and interacted with each other in 1dpp mouse oocytes.However,the co-localization of NANOS3 and DDX6 was not observed in HEK293T cells that had been transfected,but co-immunoprecipitation still demonstrated an interaction between these two proteins.Besides,live-cell imaging revealed that NANOS3 exhibited dynamic fluid-like properties within cells,which may promote the formation of P-bodies through LLPS.Finally,DDX6-IP-MS revealed that DDX6 might recruit NANOS3 into P-bodies by binding to the NANOS3 interacting protein Pumilio.Conclusion NANOS3 serves as a specific component of P-bodies in neonatal oocytes and may be involved in the regulation of early oogenesis.

Objective To investigate the effect of Huangqi Shengmai Yin(HSY)on myocardial fibrosis in rats with acute myocardial infarction(AMI)by adjusting P2X purinoceptor 7(P2X7R)/NOD-like receptor protein 3(NLRP3)pathway.Methods Sixty rats were divied into a sham operation group and model group(5 groups),with 10 rats in each group.The AMI rat model was constructed by ligating the left anterior descending branch and randomly grouped into AMI group,the HSY-low group(intragastric administration of 1.6 ml/kg HSY),the HSY group(intragastric administration of 6.2 ml/kg HSY),the compound miltiorhiza group(intragastric administration of 300 mg/kg),and the HSY-high+P2X7R agonist-ATP group(intragastric administration of 6.2 ml/kg HSY,and tail vein administration of 10 mmol/L ATP).After the intervention,cardiac function,myocardial injury and inflammatory factor markers were detected.The tissue sections were prepared to examine pathological changes,myocardial fibrosis,type Ⅰ and type Ⅲ collagen(COL1A1,COL3A1).Western blotting was performed to detecte the protein expression of P2X7R,NLRP3,tumor necrosis factor-α(TNF-α),interleukin-1β(IL-1β),and the expression of activated Caspase-1.Results Compared with the sham surgery group,the AMI group showed an increase in the left ventricular end diastolic diameter(LVEDD),the coatent of brain natriuretic peptide(BNP)and cardiac troponin I(cTn I),fibrosis volume fraction,the positive expression of COL1A1,COL3A1,TNF-α,IL-1β,P2X7R,NLRP3,and activated Caspase-1 proteins(P＜0.05),and a decrease in left ventricular ejection fraction(LVEF)(P＜0.05).The HSY-low group,HSY-high groups,and compound miltiorhiza group showed a decrease in LVEDD,the content of BNP and cTn I,fibrosis volume fraction,the positive expression of COL1A1 and COL3A1,TNF-α,IL-1β,P2X7R,NLRP3,and activated Caspase-1 proteins(P＜0.05),and an increase in LVEF than these in the AMI group(P＜0.05).The HSY-high+ATP group showed an increase in LVEDD,the content of BNP,cTn I,fibrosis volume fraction,the positive expression of COL1A1 and COL3A1,TNF-α,IL-1β,P2X7R,NLRP3,and activated Caspase-1 proteins(P＜0.05),and a decrease in LVEF than those in the HSY-high group(P＜0.05).Conclusion HSY inhibits P2X7R/NLRP3 pathway to alleviate myocardial fibrosis in AMI rats.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Inflammatory bowel disease (IBD), including ulcerative colitis and Crohn's disease, is a chronic inflammation of the gastrointestinal tract with unknown etiology. The cause of IBD is widely considered multifactorial, with prevailing hypotheses suggesting that the microbiome and various environmental factors contribute to inappropriate activation of the mucosal immune system in genetically susceptible individuals. Although the incidence of IBD has stabilized in Western countries, it is rapidly increasing in newly industrialized countries, particularly China, making IBD a global disease. Significant changes in multiple biomarkers before IBD diagnosis during the preclinical phase provide opportunities for earlier diagnosis and intervention. Advances in technology have driven the development of telemonitoring tools, such as home-testing kits for fecal calprotectin, serum cytokines, and therapeutic drug concentrations, as well as wearable devices for testing sweat cytokines and heart rate variability. These tools enable real-time disease activity assessment and timely treatment strategy adjustments. A wide range of novel drugs for IBD, including interleukin-23 inhibitors (mirikizumab, risankizumab, and guselkumab) and small-molecule drugs (etrasimod and upadacitinib), have been introduced in the past few years. Despite these advancements, approximately one-third of patients remain primary non-responders to the initial treatment, and half eventually lose response over time. Precision medicine integrating multi-omics data, advanced combination therapy, and complementary approaches, including stem cell transplantation, psychological therapies, neuromodulation, and gut microbiome modulation therapy, may offer solutions to break through the therapeutic ceiling.
Humans ; Inflammatory Bowel Diseases/therapy*