Tumors are serious diseases threatening human health,and the early diagnosis is essential to improve treatment success and patient survival.The study of tumor gene expression data has become a major tool for revealing tumor disease mechanisms,in which artificial intelligence plays an important role.The potential advantages of supervised learning,unsupervised learning and deep learning in tumor prediction and classification are explored from the perspective of machine learning methods.Special attention is paid to the impact of feature selection algorithms on gene screening and their importance in high-dimensional gene expression data.By providing a comprehensive overview of the application and development of artificial intelligence in the analysis of tumor gene expression data,the study aims to provide an outlook for future research directions and promote further development.

Objective To verify the genetic characteristics associated with gastric cancer,and to propose a hybrid feature selection method for identifying target genes,further analyzing their significance and establishing a new diagnostic prediction model.Methods Analysis of variance in bioinformatics was performed on the original gastric cancer data,and then machine learning methods such as random forest,recursive feature elimination of support vector machine,and LASSO algorithm were used to screen gastric cancer associated genes,and the intersection of results was taken as the key gene set.The key genes were identified and verified through enrichment analysis.The diagnosis and prediction models based on 8 kinds of machine learning classification algorithms such as multi-layer perceptron,logistic regression and decision tree,were constructed using the key genes.Results The key genes selected by the hybrid feature selection method were closely related to the tumorigenesis and development.Eight key genes(TXNDC5,BMP8A,ONECUT2,COL10A1,JCHAIN,INHBA,LCTL and TRIM59)were identified as potential markers of good diagnostic efficacy in gastric cancer.The ROC curve and accuracy results demonstrated that among the 8 classification models,MLP is the best gastric cancer prediction model,with an accuracy of 97.77%,which was 3.83%higher than that of Xgboost gastric cancer prediction model.Conclusion The study identifies 8 key genes for the diagnosis and prevention of gastric cancer,and establishes the optimal prognosis model.

Objective:To investigate the mechanism of Wenjing Decoction in the treatment of hepatic fibrosis through network pharmacological methods, and conducting animal experiments to verify the core targets.Methods:The TCMSP database platform was used to screen the active components and related targets of Wenjing Decoction, and the Uniprot database was used to obtain the target genes corresponding to the active components of Wenjing Decoction. The network diagram of "Chinese materia medica-compound-target" was constructed in Cytoscape 3.7.2, and the GeneCards database was used to search liver fibrosis related targets. String database was used to construct a protein interaction network (PPI) to screen the core components and key targets of liver fibrosis, and GO analysis and KEGG pathway enrichment were performed. Animal experiments were conducted to verify the results of the analysis. 10 mice were selected as the blank group, and the remaining 45 rats were induced with carbon tetrachloride induced liver fibrosis model. After modeling, 40 successfully modeled rats were divided into model group and Wenjing Decoction high, medium-, and low-dosage groups using a random number table method, with 10 rats in each group. Wenjing Decoction high, medium-, and low-dosage groups were orally administered with 1.5×3.18, 3.18, and 0.5×3.18 g/kg Wenjing Decoction, respectively. The blank group was orally administered with equal volume distilled water once a day for 8 consecutive weeks. HE staining was used to observe the histopathological and morphological changes in the liver of rats. The serum GPT and GOT levels of rats were detected using a fully automated biochemical analyzer, and the expressions of TNF, AKT, and IL-6 proteins in rat liver tissue was detected using Western Blot.Results:A total of 188 active components of Wenjing Decoction were obtained, and the active components with higher degree values were β-sitosterol, quercetin, naringenin, etc. 799 liver fibrosis gene targets were collected, and the core target genes of the PPI network were TNF, AKT, IL6, etc. The key anti-hepatic fibrosis related pathways were obtained by GO function and KEGG analysis, including pathway in cancer, TNF, PI3K-Akt and other signalling pathways. Results of animal experiments showed that there were obvious inflammatory infiltration, collagen fibre and pseudo lobe generation in the liver tissue of rats in the model group, and the levels of inflammation and fibrosis in the liver tissue of rats in the Wenjing Decoction high, medium-, and low-dosage groups were improved to different degrees compared with that of the model group; compared with the model group, the levels of serum GPT and GOT decreased ( P<0.05); the protein expressions of TNF, AKT and IL6 in the Wenjing Decoction high, medium-, and low-dosage groups decreased ( P<0.05). Conclusion:Wenjing Decoction may exert anti-liver fibrosis effects by intervening in TNF, AKT, IL6 targets, regulating cancer pathways, TNF, PI3K Akt and other signaling pathways.

ObjectiveTo analyze the results of fit testing and its influencing factors on half-mask respirator among workers exposed to organic solvents. Methods A total of 84 workers exposed to organic solvents were selected as the research subjects using a convenience sampling method. The qualitative fit test apparatus of respiratory protection was tested after the workers had put on the half-mask respirats, and 11 facial indicators of the subjects were measured. Results The overall pass rate of the respirator fit testing was 71.4% (60/84). The lowest pass rate was 63.1% (53/84), which occurred during bending movements of workers. The head width, minimum forehead width, face length, nose length, nose depth, head circumference and head length were higher in workers who passed respirator fit testing, compared with those in the failing group (all P<0.05). The result of binary logistic regression analysis showed that gender and face width were influencing factors of the respirator fit testing (both P<0.05). Female workers had a lower pass rate of the fit testing than male workers, and workers with larger face width had a lower pass rate in the fit testing. Conclusion Drastic movement may lead to a decrease in the seal of half-mask respirator of workers exposed to organic solvents. When providing half-mask respirator to workers exposed to organic solvents, employers need to pay attention to the fit of respirators of female works and those with larger face width to ensure the effectiveness of respiratory protection for workers.

ObjectiveTo explore the protective effect of hearing protectors worn by noise-exposed workers and its influencing factors. Methods A total of 329 occupational noise-exposed workers were selected as the research subjects by judgment sampling method. A questionnaire survey on the use of ear protectors and individual suitability tests was conducted. Intervention was carried out for those whose personal attenuation rating (PAR) did not pass the baseline standard. Results The median (M) and the 25th and 75th percentiles of baseline PAR were 17.0 (5.0, 22.5) dB. The baseline PAR of the workers who were male, aged 25-<35 years, with a working experience of 5-<15 years, with a college degree or above, wearing ear protectors for 5-<15 years, knowing the right way to wear ear protectors, and workers who wore ear protectors correctly during work was relatively high (all P<0.01). The unqualified rate of baseline PAR of the study subjects was 32.8%. The unqualified rate of baseline PAR of workers in automobile manufacturing enterprises was lower than that of workers in plastic enterprises and textile enterprises (9.2% vs 43.6%, and 9.2% vs 50.0%, both P<0.01). The M of the 108 unqualified worker on baseline PAR was improved after intervention (22.0 vs 1.0 dB, P<0.01). The rates of knowing the right way to wear ear protectors, wearing ear protectors correctly during work, and receiving training on wearing ear protectors correctly for the research subjects were 88.1%, 84.8%, and 86.6%, respectively. Workers in automobile manufacturing enterprises and plastic enterprises had higher rates of knowing the right way to wear ear protectors, wearing ear protectors correctly during work, and receiving training on wearing ear protectors correctly than those in textile enterprises (all P<0.01). Conclusion Gender, age, working experience, education level, duration of wearing ear protectors, knowledge and use of ear protectors correctly are influencing factors of the protective effect of ear protectors for noise-exposed workers.

Objective:To assess the efficacy of silicone earplugs in protecting workers exposed to noise in a typical manufacturing environment, and to provide training interventions for workers who do not achieve the anticipated noise reduction levels, as well as examining the spectral characteristics of earplug attenuation.Methods:From June to August 2022, a total of 294 noise-exposed workers in two manufacturing enterprises equipped with the same type of earplug were studied by cluster sampling method, by conducting questionnaire surveys, collecting data, fitting tests, and providing trainings, the current noise exposure levels of workers in the industry as well as the perception about the earplug were understood. Additionally, the attenuation before and after intervention in workplace were measured, the spectral characteristics of noise reduction were were described and compared.Results:The percentage of workers with Personal Attenuation Rating (PAR) of 0 is 32.7% (96/294), and the baseline pass rates are all below 60%. There were no significant differences in pass rates based on gender, age, noise exposure, education level, or cognition of earplug effectiveness. After adjusting the way that earplugs are worn or changing the type of earplugs, all workers were able to meet their noise reduction requirements. The median PAR improvement for both companies is above 10 dB. The noise attenuation of the earplug vary with frequency, with lower attenuation at 4 000 Hz and higher attenuation at 8 000 Hz, showing some deviation from the nominal values.Conclusion:The difference between the actual sound attenuation value of earplugs and the nominal value is related to the noise frequency. When using silicone earplugs, attention should be paid to the spectral composition of the noise in the workplace.

Objective:To assess the efficacy of silicone earplugs in protecting workers exposed to noise in a typical manufacturing environment, and to provide training interventions for workers who do not achieve the anticipated noise reduction levels, as well as examining the spectral characteristics of earplug attenuation.Methods:From June to August 2022, a total of 294 noise-exposed workers in two manufacturing enterprises equipped with the same type of earplug were studied by cluster sampling method, by conducting questionnaire surveys, collecting data, fitting tests, and providing trainings, the current noise exposure levels of workers in the industry as well as the perception about the earplug were understood. Additionally, the attenuation before and after intervention in workplace were measured, the spectral characteristics of noise reduction were were described and compared.Results:The percentage of workers with Personal Attenuation Rating (PAR) of 0 is 32.7% (96/294), and the baseline pass rates are all below 60%. There were no significant differences in pass rates based on gender, age, noise exposure, education level, or cognition of earplug effectiveness. After adjusting the way that earplugs are worn or changing the type of earplugs, all workers were able to meet their noise reduction requirements. The median PAR improvement for both companies is above 10 dB. The noise attenuation of the earplug vary with frequency, with lower attenuation at 4 000 Hz and higher attenuation at 8 000 Hz, showing some deviation from the nominal values.Conclusion:The difference between the actual sound attenuation value of earplugs and the nominal value is related to the noise frequency. When using silicone earplugs, attention should be paid to the spectral composition of the noise in the workplace.

Objective To investigate the image quality,radiation dose and contrast medium(CM)intake in coronary computed tomography angiography(CCTA)of overweight patients based on wide-detector using different tube voltages and CM of different concentrations.Methods A total of 150 overweight patients[body mass index(BMI)≥ 25 kg/m2]who underwent CCTA were divided into three groups according to scan protocols:group A(120 kVp,370 mg I/mL CM),group B(100 kVp,350 mg I/mL CM),and group C(80 kVp,320 mg I/mL CM),with each group had 50 patients.The mean CT value,mean signal-to-noise ratio(SNR),mean contrast-to-noise ratio(CNR),figure of merit(FOM)of all images were measured and calculated.Images were assessed using a 5-point scale by two radiologists.The volume CT dose index(CTDIvol)and dose length product(DLP)of each patient were recorded and the effective dose(ED)was calculated.The total iodine intake values of patients in three groups were calculated.The above data were statistically analyzed by one-way ANOVA.Results The mean CT value,mean SNR,mean CNR,and mean subjective score of groups B and C were significantly higher than those of group A(P＜0.001),but there was no significant difference between groups B and C(P＞0.05).The FOM value of groups B and C was significantly higher than that of group A(P＜0.001),and the FOM value of group B was significantly lower than that of group C(P＜0.001).The total iodine intake values of groups B and C was significantly lower than that of group A(P＜0.001).The ED and total iodine intake values in groups B and C were 30.34％,68.53％and 10.22％,16.85％lower than those in group A,respectively(P＜0.001).Conclusion Under the premise of ensuring image quality,the lower tube voltage and lower concentration of CM based on wide-detector allows for significant reduction in radiation dose and total iodine intake in CCTA for overweight patients compared to routine scan protocols.

Effective albumin refers to serum albumin with intact structure and function.In the course of chronic liver disease,some serum albumin loses its functional integrity through different post-translational modifications such as oxidation and glycosylation.Level of effective albumin is lower in patients with decompensated cirrhosis and is significantly correlated with patient survival,underscoring that they are more sensitive than total serum al-bumin in reflecting the actual state of liver function.In addition,effective albumin not only serves as a predictor,but also plays a key role in the treatment of chronic liver disease by improving albumin preparations and develo-ping new therapeutics.

Objective To compare the acute effect of high-intensity interval training(HIIT)and moder-ate-intensity continuous training(MICT)on ectopic lipid levels in overweight and obese youth.Methods Twenty obese or overweight subjects,aged 24.15±1.98 years,participated in two crossover random-ized own-control trials of HIIT and MICT.In HIIT,participants performed high-intensity cycling at 85%VO2max for 9 sets of 2 minutes,interspersed with low-intensity cycling at 25%VO2max for 10 sets of 2 minutes each and the session started and ended with low-intensity cycling at 25%VO2max.Howev-er,in MICT,all participants cycled continuously at 50%VO2max for 60 minutes,maintaining a pedal-ing speed of 50-55 rpm,with a 7-day interval between the two interventions.Before,as well as im-mediately,60 and 120 minutes after exercise intervention,all subjects underwent magnetic resonance imaging(MRI)scans to observe the fat fraction(FF)and spin relaxation rate R2* of the rectus femo-ris,biceps femoris and liver.Results Rectus femoris FF decreased significantly immediately after HIIT and MICT(P<0.05),without significant differences.Moreover,sixty minutes after MICT,rectus femoris FF returned to pre-exercise levels,while 120 minutes after HIIT,the values restored to the pre-exer-cise levels.However,no significant changes were found in the biceps femoris and liver FF before and after the two exercise interventions(P>0.05).Meanwhile,the rectus femoris R2* was significantly lower in both the HIIT and MICT groups immediately after exercise(P<0.05)and remained significantly low-er in both groups 120 minutes after the exercise(P<0.05),with no significant differences between the two groups.Biceps femoris and liver R2* were significantly higher in both groups immediately after the exercise intervention(P<0.05).Liver R2* returned to pre-exercise levels 120 minutes after HIIT group,but remained significantly lower than pre-intervention levels after MICT(P<0.05).Conclusion Both acute HIIT and MICT are effective in reducing intramuscular fat in the working muscles of over-weight and obese adults but have no significant effect on liver fat.Acute HIIT and MICT show similar fat-burning effects,but a single bout of exercise proves more effective for fat loss in the active mus-cles compared to the antagonist muscles.