Background Occupational stress has emerged as a critical public health concern affecting the physical and mental well-being of workers in the manufacturing sector. However, researchers typically evaluate its core driver—cumulative fatigue—using a crude binary “present/absent” variable, thereby overlooking the high-dimensional complexity and heterogeneity inherent in fatigue characteristics. This oversimplification constrains both the precision and predictive performance of occupational stress risk assessment model. Objective Leveraging a data-driven approach, to survey data on cumulative fatigue among manufacturing employees, and then use this new classification to develop and validate an occupational stress prediction model, with an ultimate aim of enhancing the accuracy and effectiveness of occupational stress assessment. Methods A set of cross-sectional survey data on 3871 manufacturing employees in 2021 were derived from the “Long working hours exposure and its adverse health effect risk assessment” program of the National Institute for Occupational Health and Poison Control, Chinese Center for Disease Control and Prevention. Occupational stress was assessed using the Core Occupational Stress Measurement Scale, while cumulative fatigue was evaluated via the Worker’s Self-Diagnostic Questionnaire for Fatigue Accumulation. Boruta method was applied to screen core variables from 20 occupational stress influencing factors. Dimensionality reduction of cumulative fatigue features was performed using a Bayesian sparse autoencoder (BASE), followed by comparison and application of clustering methods to achieve multi-class classification of the reduced features. Six machine learning classification models were then selected including logistic regression, support vector machine, decision tree, random forest, adaptive boosting, and lightweight gradient boosting machine (LightGBM) to construct and compare two occupational stress prediction models involving cumulative fatigue combined with ten other core variables: one utilizing the original binary cumulative fatigue label as a core variable, and another employing the novel fatigue classification proposed herein as a core variable. Results The positive rate of occupational stress among the manufacturing employees was 38.9%. The Boruta method identified 11 core variables of occupational stress: depressive symptoms, cumulative fatigue, age, length of service, tenure in current position, average weekly working hours, average daily overtime hours, average monthly income, low levels of exercise, life satisfaction, and sleep quality. The BSAE reduced the original cumulative fatigue factors to 12 dimensions, while the K-means clustering grouped the reduced fatigue features into three categories: no fatigue, moderate fatigue, and sever fatigue. Six occupational stress prediction models were constructed using the three-category labels of cumulative fatigue and ten additional factors. The results indicated that the LightGBM model performed best, achieving an area under the curve (AUC) of 0.78, an accuracy of 0.77, and an F1 score of 0.72. Compared with the model incorporating the traditional binary labels for cumulative fatigue, the best prediction AUC (0.72), accuracy (0.66), and F1 score (0.65) improved by 6%, 11%, and 7%, respectively. Conclusion Cumulative fatigue is a significant predictor of occupational stress among manufacturing employees. Applying data dimensionality reduction combined with three-class cluster analysis to characterize cumulative fatigue improves the performance of occupational stress prediction models. From a data-driven perspective, machine learning methods demonstrate strengths in processing complex datasets, capturing nonlinear relationships, and generating predictions based on key variables. This study therefore confirms that refined processing of core factors substantially enhances the predictive capability of machine learning models in assessing occupational stress risk in the manufacturing workforce.

Objective To investigate the effects of scoparone(Sco)on proliferation and invasion of colon cancer cell line HCT116,and its effect on the expression of epidermal growth factor receptor(EGFR).Methods 1)HCT116 cells were divided into control group,50Sco group,100Sco group and 200Sco group.The cells in con-trol group were incubated with culture medium for 48 hrs.The 50Sco group,100Sco group and 200Sco group were incubated with 50,100 and 200 μmol/L scoparone for 48 hrs respectively.2)HCT116 cells were divided into con-trol group,NC-200Sco group,NC-LV+200Sco group and EGFR-LV+200Sco group.The control group was incuba-ted with normal culture medium for 48 hrs.NC-200Sco group was incubated with 200 μmol/L scoparone for 48 hrs.NC-LV and EGFR-LV were infected into HCT116 cells in NC-LV+200Sco group and EGFR-LV+200Sco group,then incubated with 200 μmol/L scoparone for 48 hrs.Cell proliferation was detected by MTT assay and EdU stai-ning,cell apoptosis was detected by flow cytometry and cell invasion was detected by Transwell assay.EGFR mRNA was detected by RT-qPCR,the level of EGFR,Bcl-2,Bax,matrix metalloproteinase(MMP)-2 and MMP-9 protein was detected by Western blot.Results Compared to the control group,the cell viability,proportion of EdU positive cells and counting number of invasive cells in 50Sco group,100Sco group and 200Sco group all decreased(P＜0.05).Cell apoptosis rate and Bax protein expression increased(P＜0.05),the protein expression of Bcl-2,MMP-2 and MMP-9 decreased(P＜0.05).mRNA and protein expression of EGFR were de-creased(P＜0.05).Compared with NC-200 Sco group and NC-LV+200Sco group,the expression level of mRNA and protein of EGFR in EGFR-LV+200Sco group was increased(P＜0.05).Cell viability,proportion of EdU posi-tive cells and counting number of invasive cells all increased(P＜0.05).The cell apoptosis rate and Bax protein expression level were decreased(P＜0.05).The protein expression of Bcl-2,MMP-2 and MMP-9 was increased(P＜0.05).Conclusions Scoparone has anti-colon cancer cell activity and inhibits proliferation as well as invasion of colon cancer cells through inhibition of EGFR.

Objective:To explore the effect of colonoscopy combined with X-ray stent implantation in the treatment of colorectal cancer intestinal obstruction, and analyze the risk factors of postoperative delayed bleeding.Methods:From November 2016 to December 2020, 382 patients with colorectal cancer intestinal obstruction in Hainan Provincial People′s Hospital were selected. Among them, 254 patients were treated by colonoscopy combined with X-ray stent implantation (stent implantation group), and 128 patients were treated by emergency radical resection (control group). The operation time, intraoperative bleeding, number of lymph node dissections, tumor diameter, incision length, exhaust time, hospital stay, fluid feeding time, fistulation, perioperative death and delayed bleeding were compared between 2 groups. Based on the random number generated by the computer, 254 patients who underwent colonoscopy combined with X-ray stent implantation were divided into training set (190 cases) and test set (64 cases) according to the ratio of 3∶1. In the training set, the patients were divided into postoperative delayed bleeding and non postoperative delayed bleeding, and the clinical indicators were compared; the multivariate Logistic regression model was performed to analyze the independent risk factors of postoperative delayed bleeding, and the prediction model of postoperative delayed bleeding was established and verified according to the independent risk factors.Results:All patients in the stent implantation group were successfully implanted with stents, and the obstructive symptoms were relieved 24 to 48 h after operation. The operation time, intraoperative bleeding, incision length, fistulation rate, exhaust time, hospital stay and fluid feeding time in stent implantation group were significantly lower than those in control group: (88.89 ± 5.97) min vs. (116.58 ± 20.17) min, (33.18 ± 16.52) ml vs. (92.35 ± 25.64) ml, (4.50 ± 0.96) cm vs. (14.26 ± 2.88) cm, 10.24% (26/254) vs. 98.44% (126/128), (1.18 ± 0.58) d vs. (1.53 ± 0.77) d, (7.69 ± 5.12) d vs. (12.88 ± 6.54) d and (1.46 ± 0.68) d vs. (2.12 ± 1.18) d, the number of lymph node dissections was significantly higher than that in control group: (19.88 ± 4.47) lymph nodes vs. (17.47 ± 3.11) lymph nodes, and there were statistical differences ( P<0.01); there were no statistical differences in tumor diameter and perioperative fatality rate between 2 groups ( P>0.05). Among 190 patients in the training set, 18 patients had postoperative delayed bleeding, with an incidence of 9.47%; 172 cases did not have postoperative delayed bleeding. The age, course of obstruction, complete obstruction rate, intestinal almost occlusion rate under enteroscopy, intraoperative bleeding rate and preoperative intestinal surgery history rate in patients with postoperative delayed bleeding were significantly higher than patients without postoperative delayed bleeding: (69.52 ± 10.54) years old vs. (58.65 ± 15.87) years old, (14.56 ± 10.12) d vs. (8.13 ± 7.68) d, 11/18 vs. 20.35% (35/172), 11/18 vs. 16.28% (28/172), 7/18 vs. 11.63% (20/172) and 12/18 vs. 37.79% (65/172), and there were statistical differences ( P<0.01 or <0.05). Multivariate Logistics regression analysis result showed that old age, long duration of obstruction, complete obstruction, almost intestinal obstruction under enteroscopy and intraoperative bleeding were independent risk factors for postoperative delayed bleeding in patients with colorectal cancer intestinal obstruction undergoing colonoscopy combined with X-ray stent implantation ( OR = 3.925, 4.802, 1.727, 2.710 and 2.581; 95% CI 1.352 to 8.330, 1.064 to 8.869, 1.063 to 2.804, 1.118 to 4.400 and 1.689 to 3.479; P<0.05 or<0.01), while the history of preoperative intestinal surgery was not related to postoperative delayed bleeding ( P>0.05). The consistency indexes of nomogram training set and test set were 0.742 and 0.726 (95% CI 0.684 to 0.845 and 0.640 to 0.812). The receiver operating characteristic (ROC) curve analysis results of 2 models showed that the area under the curve (AUC) of the training set nomogram model and Tree Augmented Na?ve Bayes (TAN) model was 0.758 and 0.752 respectively, and the AUC of the test set nomogram model and TAN model was 0.702 and 0.706 respectively. The prediction accuracy of training set nomogram model and TAN model was 84.74%(161/190) and 85.26%(162/190) respectively, the prediction accuracy of test set nomogram model and TAN model was 82.81%(53/64) and 84.38%(54/64) respectively. Conclusions:Colonoscopy combined with X-ray stent implantation is safe and feasible in patients with colorectal cancer intestinal obstruction. But for the old age, long duration of obstruction, complete obstruction, almost intestinal obstruction under colonoscopy and intraoperative bleeding, careful operation should be carried out to reduce the occurrence of postoperative delayed bleeding.