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.

AIM To establish LC-MS and GC-MS method and analyze the chemical constituents of Dendrobium huoshanense C.Z.Tang & S.J.Cheng flowers.METHODS LC-MS was performed on a Zorbax Eclipse C18 column(2.1 mm×100 mm,1.8 μm),with the mobile phase comprising of water(containing 0.1％formic acid)-acetonitrile flowing at 0.3 mL/min,and electrospray ionization was operated in both positive and negative ion modes.The GC-MS employed headspace solid-phase microextraction for sample preparation,and the analysis was performed on an HP-5MS column(30 m×0.25 mm,0.25 μm),with the following temperature program:initial temperature 50 ℃(held for 2 min),increased at 5 ℃/min to 180 ℃(held for 5 min),then raised at 10 ℃/min to 250 ℃(held for 5 min),and electron impact ion source was employed.RESULTS A total of 62 compounds were identified by LC-MS,including 35 flavonoids,4 coumarins,6 alkaloids,6 terpenoids,3 amino acids,2 polyphenols,2 ketones and 4 others.A total of 101 volatile components were identified by GC-MS,including ketones,aldehydes,alcohols,esters,ethers,and acid.CONCLUSION This method can comprehensively analyze the chemical constituents of D.huoshanense flowers,and provide a scientific basis for elucidating its pharmacodynamic material basis.

Objective:To explore the effects of multi-dimensional nursing based on empowerment theory in patients undergoing thoracoscopic and laparoscopic esophagectomy.Methods:A convenience sampling method was used to select 110 esophageal cancer patients who were admitted to Henan Provincial People's Hospital from August 2022 to April 2024. Patients were randomly divided into two groups using a random number table: the control group and the observation group, with 55 patients in each group. The control group received routine care, while the observation group received multi-dimensional nursing based on empowerment theory in addition to routine care. The two groups were compared in terms of stress responses (heart rate, systolic blood pressure, diastolic blood pressure) , self-care ability, nutritional status (hemoglobin, albumin) , and nursing satisfaction.Results:After the intervention, the observation group had lower heart rate, systolic blood pressure, and diastolic blood pressure compared to the control group, with statistically significant differences ( P<0.01) . The self-care ability score in the control group was lower than that in the observation group, with a statistically significant difference ( P<0.01) . The observation group also had higher hemoglobin and albumin levels compared to the control group, with statistically significant differences ( P<0.01) . The nursing satisfaction rate in the observation group was higher than that in the control group, with a statistically significant difference ( P<0.05) . Conclusions:Multi-dimensional nursing based on empowerment theory can effectively reduce stress responses, improve self-care ability, enhance nutritional status, and increase nursing satisfaction in esophageal cancer patients.

Objective:To analyze the short-term hospital-based transmission characteristics and gene variation of Carbapenem-Resistant Klebsiella pneumoniae (CRKP) by genome-wide technique to provide evidence for transmission control. Methods:The experimental strain was derived from all the CRKP isolated in Affiliated Hospital of North China University of Science and Technology from October 2022 to December 2023. Strain identification and drug susceptibility were tested with VITEK 2-Compact automatic bacterial identification drug susceptibility analyzer or disk method, and the results were interpreted through whole genome sequencing. The ST type, carbapenem resistance gene, virulence factor, and O serotype of the collected strains were analyzed.Results:Among the 115 strains of CRKP, 94 strains were isolated from the intensive care unit (ICU), accounting for 81.7%, and 21 strains were isolated from the non-intensive care unit (NICU), accounting for 18.3%. The 115 strains of CRKP can be divided into 11 ST types, of which ST11 type was the most (54.8%, 63/115), followed by ST15 type (22.6%, 26/115) and ST5492 type (15.7%, 18/115). Type ST5492 was a new clonal group in the region. The 115 strains of CRKP could be divided into 7 O serotypes, most of which were O2a type(32.2%,37/115), followed by O5 type(30.4%,35/115) and O1 type(27.8%,32/115). The resistance genes of carbapenem antibiotics showed that there were 107 strains carrying the blaKPC-2 gene, one strain with the blaNDM-1 gene, and one strain with both the blaKPC-2 and blaNDM-13 genes. Virulence genes were detected in 55 CRKP strains (47.8%, 55/115), among which six strains detected peg-344, iucA, iroB, rmpA, and rmpA2 virulence genes (5.2%, 6/115). Four virulence genes ( peg-344, iucA, rmpA, and rmpA2) were detected in 34 strains (29.6%, 34/115). Three virulence genes ( iucA, iroB and rmpA) were detected in two strains (1.7%, 2/115). Three virulence genes ( peg-344, iucA and rmpA) were detected in one strain (0.8%, 1/115). IucA and rmpA virulence genes were detected in 12 strains (10.4%, 12/115). KPC-2_ST11_O2a, KPC-2_ST15_O1 and KPC-2_ST5492_O5 were dominant clones, and their distribution was mainly in the intensive care unit. The whole genome sequence analysis showed that there were three dominant clones, among which ST11 clones were subdivided into three dominant O serotypes, all of which were mainly in the intensive care unit. Conclusion:The popular strain in the hospital of CRKP is a KPC-2_ST11 clone group carrying iucA, rmpA/rmpA2, with cross-department transmission and mutation. ST5492 is a newly-launched clone type. The intensive care unit of hvKP carrying five virulence genes, including peg-344, should be alert to the epidemic risk of CR-hvKP outbreak.

Objective Itproposes a WISN staffing demand model for clinical physicians to address the challenge that current physicians staffing standards fail to meet the operational needs of general hospitals.Methods Collect the 2023 annual operation data of a tertiary general hospital,using inpatient visits and surgeries as benchmarks to measure the workload demands of physicians in internal medicine and surgery,respectively.Additionally,integrate non-clinical workloads of physicians and the workload of resident physicians in standardized training to address the limitation of traditional models that focus solely on clinical tasks.Results The good applicability and robustness of the model in practical applications are verified through model comparison and sensitivity analysis,accurately reflecting the demand for physicians.Conclusion The model accurately reflects the workload of physicians in general hospitals,providing a quantitative estimation formula for physicians staffing.It has broad applicability and significant potential for wider adoption.

Objective To analyze the research status,hotspots,and trends of wearable devices in nursing applications both domestically and internationally.Methods Using China National Knowledge Infrastructure,Wanfang Data Knowledge Service Platform,and Embase core databases as data sources,VOSviewer was used to visualize and analyze the publication time,keywords,and other relevant literature.Results Total of 428 articles were included,including 196 Chinese articles and 232 English articles.The overall publication volume showed an upward trend.Domestic research focuses on chronic diseases,artificial intelligence,and nursing,with the main research subjects being the elderly;Foreign research focuses on smart devices,self-monitoring,and quality of life,with the main research subjects being adults.Conclusion Currently,the number of publications on the application of wearable devices in nursing is relatively small,but the overall research heat is on the rise,mainly used for chronic diseases and self-monitoring.In the future,the application scope of wearable devices should be expanded and their potential value should be explored to promote the innovation and progress of nursing models.

Objective:To investigate the impact of ginseng alcohol extract(GEE)on improving sleep quality in the aged Drosophila model by regulating the redox balance,and to elucidate its associated mechanism.Methods:Thirty-two male drosophila melanogaster(7-days-old)were randomly selected as young group,while 64 male Drosophila melanogaster flies(35-days-old)were randomly assigned to aged model group(n=32)and GEE group(n=32).The sleep parameters,including total sleep duration,daytime sleep duration,night sleep duration,0-4 h of sleep duration after lights off(ZT0-4 sleep duration),deep sleep duration,sleep episodetimes,sleep fragmentation,and the activity parameters such as the total number of locomotor activity daytime locomotor activity amount and nighttime locomotor activity amount were analyzed using the DAM2 Drosophila behavioral analysis system 7 d after administration.The grouping of the drosophila was as above,and there were 100 drosophila ineach group.The differentially expressed proteins in drosophila brain tissue were screened,identified,and functionally analyzed using two-dimensional fluorescence difference gel electrophoresis(2D-DIGE)and matrix-assisted laser desorption/ionization time of flight mass spectrometry(MALDI-TOF/TOF-MS)proteomic methods.The grouping of the drosophila was as above,and there were 100 drosophila in each group.The activities of superoxide dismutase(SOD),catalase(CAT),and glutathione peroxidase(GSH-Px)and the levels of lipid peroxidation product(MDA)in brain tissue of the drosophila were determined using assay kits.Results:Compared with young group,the total sleep duration daytime sleep duration and night sleep cluration of the drosophila in agaed group were decreased(P<0.05 or P<0.01);and the sleep rhythm amplitude was shortened.Compared with aged group,the total sleep duration and daytime and nighttime sleep durations of the drosphila in GEE group were lengthened(P<0.01).Compared with young group,the ZT0-4 sleep duration deep sleep duration and sleep fragment of the drosophila in aged group were decreased(P<0.05 or P<0.01),and the sleep rhythm amplitude was shortened.Compared with young group,the ZT0-4 sleep duration,deep sleep duration,and single sleep fragment of the drosphila in GEE group were significantly prolonged(P<0.01),and the sleep amplitude was increased.Compared with young group,there was no significant difference in diurnal spontaneous activity or total spontaneous activity of the drosophila in aged group(P>0.05),while the nocturnal spontaneous activity was significantly increased(P<0.05).Compared with aged group,the diurnal spontaneous activity,nocturnal spontaneous activity,and total spontaneous activity of the drosophila in GEE group were significantly decreased(P<0.05 or P<0.01).A total of 47 differentially expressed proteins were selected in the 2D-DIGE electrophoretic mapping.Compared with young group,the expressions of 47 differentially expressed protein sites in aged group were down-regulated mainly including glutathione S-transferase,peroxiredoxin 1 and dihydrolipoic dehydrogenase,which were related to redox balance.Compared with young group,the activities of SOD,CAT and GSH-Px in brain tissue of the drosophila in aged group were decreased(P<0.05 or P<0.01),and the level of MDA was increased(P<0.01);compared with aged group,the activities of SOD,CAT and GSH-Px in brain tissue of the drosphila in GEE group were increased(P<0.05 or P<0.01),and the MDA level was decreased(P<0.05).Conclusion:GEE has improvement effect on the sleep quality of aged drosophila,and its possible mechanism may be related to upregulating the activities of antioxidant enzymes,inhibiting the accumulation of lipid peroxidation products,and maintaining redox balance.

Objective To explore the potential clinical value of the ratio of glycated albumin to albumin(GA/ALB)in the occurrence of heart failure(HF)among patients with coronary atherosclerotic heart disease(CHD).Methods A total of 337 CHD patients admitted to the Department of Cardiology in Shanxi Provincial People's Hospital from July 2023 to June 2024 were selected in this study.CHD patients were divided into HF group and non-HF group based on whether they progressed to HF.The clinical data and laboratory parame-ters of the two groups were compared.Restricted cubic spline curve was used to analyze the relationship be-tween GA/ALB levels and the risk of HF in CHD patients.Receiver operating characteristic curve was applied to evaluate the diagnostic efficacy of GA/ALB,GA,platelet to lymphocyte ratio(PLR),and monocyte to lym-phocyte ratio(MLR)in CHD patients with the occurrence of HF.Logistic regression was used to explore the relationship between serum GA/ALB levels and the risk of CHD patients occurrence of HF,and to analyze the degree of influence and stability of subgroup variables on results.Results There were statistically significant differences in GA/ALB,GA,PLR,MLR,and other indicators between the HF group and the non-HF group in CHD patients(P＜0.05).A non-linear relationship was observed between GA/ALB levels and the risk of HF in CHD patients.When the value of GA/ALB multiplied by 10 was less than 5.751,the risk of HF in CHD pa-tients increased with the increase of GA/ALB levels(P＜0.001).GA/ALB was an effective predictor for HF occurrence in CHD patients.Multivariable Logistic regression model showed that GA/ALB was an independ-ent risk factor for CHD patients with occurrence of HF.Subgroup analysis also confirmed the stability of GA/ALB in predicting the occurrence of HF in CHD patients.Conclusion GA/ALB is an independent risk factor for the occurrence of HF in CHD patients,and monitoring GA/ALB levels provides predictive value for the oc-currence of HF in these patients.

Abdominal war trauma is a common and high-risk type of injury in the modern battlefield,with rapid changes in condition and a high mortality rate.There is an urgent need for emerging medical technologies to improve the efficiency and success rate of first aid for military casualties.With the development of artificial intelligence(AI),5G,and other emerging technologies,the concept of intelligent medical treatment is gradually forming and can assist in the diagnosis and treatment of abdominal trauma.This paper reviews the characteristics of abdominal war trauma in modern wars,discusses the application of intelligent medical treatment for abdominal war trauma and its drawbacks to be solved,aiming to provide reference for research related to abdominal war trauma.