Background Long working hours, as a common risk factor for occupational stress, is closely related to the occurrence of depressive symptoms. Understanding how long working hours affect occupational stress and depressive symptoms will inform occupational health interventions. Objective To quantify the impact of long working hours exposure on occupational stress and depressive symptoms among Internet industry employees, translate black-box outputs into actionable insights, and demonstrate the value of interpretable machine learning for early-warning occupational-health surveillance. Methods A dataset was derived from a cross-sectional survey involving 2866 internet industry employees in China. This survey was part of the project Risk Assessment Of Long Working Hour Exposure And Its Adverse Health Effects, conducted by the National Institute for Occupational Health and Poisoning Control, Chinese Center for Disease Control and Prevention, from 2021 to 2023. Working hours, occupational stress and depressive symptoms were quantified with a set of structured questionnaires including the Core Occupational Stress Scale and the Patient Health Questionnaire. Pairwise associations were screened by Mantel tests and variance-inflation factors. Key predictors identified through feature selection were fed into six machine-learning risk-prediction models. Visual interpretation was provided by feature importance, Shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME), while directed causal effects and intervention impacts of prolonged working hours exposure on occupational stress and depressive symptoms were dissected with causal explanation of features techniques. Results The positive rates of occupational stress and depressive symptoms among internet employees were 12.9% and 77.8% respectively. Twelve core features for occupational stress and nine for depressive symptoms were retained after selection. After these features were supplied to six predictive algorithms and evaluated on five metrics, the Light Gradient Boosting Machine (LGBM) achieved the highest accuracy—0.89 for occupational stress and 0.79 for depressive symptoms on the hold-out test set. The feature-importance rankings converged on fatigue accumulation and life satisfaction as dominant drivers for both outcomes, whereas weekly working hours and daily overtime emerged as the principal exposure-related predictors. The SHAP summary plots revealed that longer weekly hours and daily overtime systematically elevated the probability of occupational stress. The causal feature explanation further quantified that ascending one category in weekly working hours increased the probability of occupational stress by 7.04%. Conclusion Exposure to long working hours is associated with both occupational stress and depressive symptoms among internet industry employees. Interpretable machine-learning frameworks translate these associations into transparent, defensible drivers, enabling precise identification of the pivotal factors and their interplay. This evidence base equips occupational-health practitioners with actionable insights for designing targeted prevention and intervention strategies.

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.

Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by cognitive decline and memory loss, with few effective treatments currently available. The multifactorial nature of AD, shaped by genetic, environmental, and biological factors, complicates both research and clinical management. Recent advances in artificial intelligence (AI) and multi-omics technologies provide new opportunities to elucidate the molecular mechanisms of AD and identify early biomarkers for diagnosis and prognosis. AI-driven approaches such as machine learning, deep learning, and network-based models have enabled the integration of large-scale genomic, transcriptomic, proteomic, metabolomic, and microbiomic datasets. These efforts have facilitated the discovery of novel molecular signatures and therapeutic targets. Methods including deep belief networks and joint deep semi-non-negative matrix factorization have contributed to improvements in disease classification and patient stratification. However, ongoing challenges remain. These include data heterogeneity, limited interpretability of complex models, a lack of large and diverse datasets, and insufficient clinical validation. The absence of standardized multi-omics data processing methods further restricts progress. This review systematically summarizes recent advances in AI-driven multi-omics research in AD, highlighting achievements in early diagnosis and biomarker discovery while discussing limitations and future directions needed to advance these approaches toward clinical application.

Objective:To investigate the clinical and pathologic features and diagnosis of follicular lymphoma (FL) with a predominantly diffuse growth pattern (DFL) with 1p36 deletion.Methods:Eight cases of DFL with 1p36 deletion diagnosed at Department of Pathology, Beijing Friendship Hospital, Capital Medical University ( n=5) and the Affiliated Cancer Hospital of Zhengzhou University, Henan Cancer Hospital ( n=3) from January 2017 to January 2023 were included. Their clinicopathologic features and follow-up data were analyzed. Immunohistochemistry and fluorescence in situ hybridization (FISH) were performed. Results:There were five males and three females, with a median age of 67 years, and inguinal lymphadenopathy was found as the main symptom. Histologically, similar morphologic features were sheared among all cases, with effaced nodal structure and characterized by proliferation of centrocytes in a diffuse pattern, with or without follicular components. The germinal center-related markers such as CD10 and/or bcl-6 were expressed in the tumor cells, and 1p36 deletion but not bcl-2 translocation was appreciable in these cases.Conclusions:DFL with 1p36 deletion is a rare subtype of FL, with some overlaps with other types of FL or indolent B-cell lymphomas in their pathologic features. An accurate diagnosis requires comprehensive considerations based on their clinical, pathologic, immunohistochemical, and molecular features.

Objective:Diabetic retinopathy (DR) has been reported as the leading cause of blindness among diabetic adults, which is closely related to poor quality of life and increased burden of disability. This study aimed to aggregate the optimally available evidence on modifiable risks of DR.Methods:Until June 2023, PubMed, Cochrane Library, CNKI, and Wanfang databases were used to retrieve Meta-analysis about various risk factors for DR, and Meta-analysis were analyzed and summarized. R 4.3.2 software was used for each Meta-analytic association to calculate the effect size, 95% CI, heterogeneity, small-study effects, excess significance bias, and 95% prediction intervals. The credibility of significant evidence was graded. Results:We captured 23 eligible papers (72 associations) covering a wide range of medication use, concomitant diseases, daily intervention, biomarkers, lifestyle, and physical measurement index. Among them, higher HbA1c variability ( RR=1.45, 95% CI: 1.26-1.66) and urine microalbumin positive ( OR=2.44, 95% CI: 1.99-2.97) were convincing (grade Ⅰ) evidence, and insulin use ( RR=3.48, 95% CI: 2.14-5.67) was highly suggestive (grade Ⅱ) evidence. Moreover, hypertension ( OR=2.03, 95% CI: 1.06-3.97), poor glycemic control ( OR=4.35, 95% CI: 1.47-12.85), positive macroalbuminuria ( OR=8.42, 95% CI: 3.52-20.15), long sleep duration ( OR=2.05, 95% CI: 1.37-3.05), vitamin D deficiency ( OR=2.02, 95% CI: 1.17-3.50), periodontitis ( OR=4.51, 95% CI: 1.76-11.55) were the main risk factors for DR. Intensive blood pressure intervention ( RR=0.78, 95% CI: 0.65-0.94), dietary control ( OR=0.64, 95% CI: 0.47-0.89) and moderate intensity physical activity ( RR=0.76, 95% CI: 0.59-0.97) yielded significant protective associations with DR. Conclusions:Intensive blood pressure glycemic control, and a healthy lifestyle pattern could reduce the risk of DR. This study provides the evidence to identify high-risk populations and recommends rational treatment options and healthy living interventions.

Objective:To investigate the association between serum uric acid,pulmonary function and airflow obstruction in Chinese Taiwan healthy subjects.Methods:All the cross-sectional analysis was performed in the population over 40 years old using the physical examination data of Chinese Taiwan MJ Health Resource Center between 1996 and 2016 stratification by gender.The correlation analyses between serum uric acid were done and multivariate Logistic regression analysis was used to explore the effect of serum uric acid on airflow obstruction.Results:A total of 35 465 people were included in the study,in-cluding 16 411 men and 19 054 women.Among them,the serum uric acid concentration of men was higher than that of women,and the serum uric acid concentration of the people with airflow obstruction was higher than that of the people without airflow obstruction.There was a negative correlation between serum uric acid level and the forced expiratory volume in one second(FEV1)and the force vital capacity(FVC)in women(P＜0.05),but in men the correlation didn't exist(P＞0.05).After adjusting for age,education,smoking status,drinking status,work strength,body mass index,history of cough,his-tory of hypertension,history of diabetes,history of dyslipidemia,white blood cells and blood albumin,the airflow obstruction in women was more likely to exist with the serum uric acid elevated(OR=1.12,95％CI:1.02-1.22,P＜0.05).The results showed that women with hyperuricemia were more likely to have airflow obstruction than those without hyperuricemia(OR=1.36,95％CI:1.06-1.75,P＜0.05).There was no correlation between serum uric acid concentration and airflow obstruction in men(OR=1.04,95％CI:0.96-1.13,P＞0.05),also the hyperuricemia and airflow obstruction(OR=1.12,95％CI:0.89-1.39,P＞0.05).Conclusion:There is a negative correlation between serum uric acid and FEV1 and FVC in relatively healthy women,and there is an association between elevated serum uric acid and airflow obstruction in women,but not in men.Further prospective studies are needed to explore whether high serum uric acid level can increase the risk of airflow obstruction.

Objective:To compare the consistency of lymphoma multigene detection panels based on next-generation sequencing (NGS) with FISH detection of B-cell lymphoma gene rearrangement.Methods:From January 2019 to May 2023, fusion genes detected by lymphoma-related 413 genes that targeted capture sequencing of 489 B-cell lymphoma tissues embedded in paraffin were collected from Henan Cancer Hospital, and the results were compared with simultaneous FISH detection of four break/fusion genes: BCL2, BCL6, MYC, and CCND1. Consistency was defined as both methods yielding positive or negative results for the same sample. The relationship between fusion mutation abundance in NGS and the positivity rate of cells in FISH was also analyzed.Results:Kappa consistency analysis revealed high consistency between NGS and FISH in detecting the four B-cell lymphoma-related gene rearrangement ( P<0.001 for all) ; however, the detection rates of positive individuals differed for the four genes. Compared with FISH, NGS demonstrated a higher detection rate for BCL2 rearrangement, a lower detection rate for BCL6 and MYC rearrangement, and a similar detection rate for CCND1 rearrangement. No correlation was found between fusion mutation abundance in NGS and the positivity rate of cells in FISH. Conclusions:NGS and FISH detection of B-cell lymphoma gene rearrangement demonstrate overall good consistency. NGS is superior to FISH in detecting BCL2 rearrangement, inferior in detecting MYC rearrangement, and comparable in detecting CCND1 rearrangement.

Pulmonary blast injury has become the main type of trauma in modern warfare, characterized by externally mild injuries but internally severe injuries, rapid disease progression, and a high rate of early death. The injury is complicated in clinical practice, often with multiple and compound injuries. Currently, there is a lack of effective protective materials, accurate injury detection instrument and portable monitoring and transportation equipment, standardized clinical treatment guidelines in various medical centers, and evidence-based guidelines at home and abroad, resulting in a high mortality in clinlcal practice. Therefore, the Trauma Branch of Chinese Medical Association and the Editorial Committee of Chinese Journal of Trauma organized military and civilian experts in related fields such as thoracic surgery and traumatic surgery to jointly develop the Clinical treatment guideline for pulmonary blast injury ( version 2023) by combining evidence for effectiveness and clinical first-line treatment experience. This guideline provided 16 recommended opinions surrounding definition, characteristics, pre-hospital diagnosis and treatment, and in-hospital treatment of pulmonary blast injury, hoping to provide a basis for the clinical treatment in hospitals at different levels.

Objective To determine the epidemic characteristics of forty-two coronavirus disease 2019 （COVID-19） cluster outbreaks in Hangzhou city and provide scientific evidence for further prevention and control measures. Methods Data of the COVID-19 cluster outbreaks in Hangzhou were obtained from the National Public Health Emergency Management Information System. Epidemic characteristics were summarized by reviewing the epidemiological investigation reports. Results A total of forty-two COVID-19 cluster outbreaks were documented in Hangzhou in 2020， including 130 confirmed cases and 7 cases with asymptomatic infection. The majority occurred from January to February， 2020. Moreover， 92.86% （39/42） of the cluster outbreaks were familial transmission. The proportion of the cluster outbreaks involving 2 cases accounted for 54.7% （23/42）. In the secondary cases， family members accounted for 84.15% （69/82）. Conclusion The COVID-19 cluster outbreaks in Hangzhou mainly occur in families， and the majority of the secondary cases is family members.

Objective:To learn about the knowledge and practice of iodine deficiency disorders (IDD) prevention and control among main caregivers of pregnant women in trimester and its related influencing factors, so as to provide a scientific basis for effectively improving the iodine nutrition level of pregnant women.Methods:In April 2020, using the stratified sampling method, 2 districts and counties were selected in the urban, suburban and rural areas of Hangzhou City, respectively, and 5 maternal and child health care institutions were selected as the survey sites in each district and county according to the five directions of East, West, South, North and Middle. A face-to-face questionnaire investigation was used to investigate the knowledge and practice of IDD prevention and control among main caregivers of pregnant women.Results:Totally 601 caregivers of pregnant women were investigated. Among them, 68.9% (414/601) knew that eating iodized salt was the best way to prevent IDD. However, 15.0% (90/601) thought that eating seafood was the best way to prevent IDD. And 41.9% (252/601) caregivers of pregnant women would actively purchase iodine-rich food for cooking, and 63.6% (382/601) would choose iodized salt. There were statistically significant differences in the knowledge and practice of IDD prevention and control among caregivers of pregnant women in urban, suburban and rural areas ( P < 0.05). And 50.3% (87/173) male caregivers would actively purchase iodine-rich food for cooking, which was higher than that of female caregivers [38.6% (165/428)], the difference was statistically significant (χ 2 = 6.97, P = 0.008). There was a statistically significant difference between the caregivers of pregnant women of different ages in actively purchasing iodine-rich food for cooking (χ 2 = 12.61, P = 0.013). And there were statistically significant differences between the caregivers of pregnant women with different educational levels in actively purchasing iodine-rich food for cooking and choosing iodized salt (χ 2 = 29.34, 39.42, P < 0.001). Conclusions:The awareness of knowledge about IDD prevention and control and the formation of prevention and control behavior among caregivers of pregnant women in Hangzhou City are poor. Active education of caregivers of pregnant women should be strengthened to promote maternal and infant health.