Background The prevalence of chronic diseases among the Chinese occupational population is rising steadily, with hypertension and diabetes becoming important health concerns. Occupational health examinations (OHE) provide stable population coverage, standardized protocols, and fixed follow-up intervals, offering a robust data foundation for risk assessment. However, most existing hypertension prediction studies rely on cross-sectional data and mainly focus on clinic onset, failing to capture the dynamic progression and cumulation of individual risk. Objective To construct a machine learning-based risk prediction model for blood pressure abnormality in occupational populations, providing a reference for health risk stratification and targeted health interventions. Methods Longitudinal data from 2020 to 2023 were extracted from the occupational health examination database of an institution in Shanghai. After excluding individuals with hypertension in any of the first three years, 3710 workers who participated 4 consecutive years of OHE were included. Six categories of blood pressure-related indicators from 2020 to 2022 were selected, including basic information, lifestyles, occupational exposures, cardiovascular indicators, routine blood tests, and biochemical markers, comprising 30 variables in total. For feature engineering, continuous variables were processed to reflect three-year dynamic characteristics: level (mean), variability (variance), and temporal trend (slope). Categorical variables were incorporated using 2022 values. Least absolute shrinkage and selection operator regression was applied to identify variables for inclusion in the machine learning models. Five models (decision tree, logistic regression, random forest, support vector machine, and XGBoost) were employed to predict blood pressure abnormality risk in 2023. And then sensitive analysis was conducted. The optimal model was selected based on the area under the curve (AUC) of receiver operating characteristic. Feature importance and SHAP analyses were applied to interpret the final model. Results Feature engineering transformed 17 continuous variables into 51 secondary variables, combined with 13 baseline variables, resulted in 24 variables screened out by LASSO regression. The logistic regression model achieved the best performance. Feature importance analysis indicated that the dynamic trajectory of blood pressure played a central role in the model, complemented by other biochemical and lifestyle indicators. SHAP analysis further showed that the model’s ability to not only identify risks of high-normal blood pressure and hypertension but also quantify the specific contribution of individual examination indicators to predicted risk, supporting risk-stratified population management in occupational health management. Conclusion Based on an existing occupational health examination database and routinely collected data, this study has developed a risk prediction model for blood pressure abnormalities in occupational populations. By incorporating dynamic change characteristics from longitudinal examinations, the study demonstrates the feasibility of using routine health data for early risk identification and stratified management. However, its applicability is limited by the availability of repeated examination data and the focus on specific occupational groups, requiring further validation across broader populations and diverse clinic scenarios.

As a primary approach to safeguarding workers' occupational health in China, the work-related injury insurance still has insufficient preventive measures for occupational groups. By reviewing the preventive measures embedded in Germany’s statutory accident insurance (Gesetzliche Unfallversicherung) and Japan’s workers’ accident compensation insurance, this study summarized their best practices and then proposed the following policy directions based on China’s specific context: strengthening the prevention-oriented institutional framework, increasing financial investment in occupational injury prevention, improving the incentive mechanisms of floating premium rate, and promoting data integration and intelligent applications in occupational health management. These measures are expected to shift China’s work-related injury insurance system from a compensation-oriented model to one that emphasizes comprehensive prevention and health promotion, thereby providing useful insights for better safeguarding the health of Chinese workers.

As the prevalence of chronic diseases increases among occupational populations in China, the focus of occupational health management has shifted from ″occupational disease prevention and control″ to ″occupational disease and chronic disease prevention and control″. At present, occupational medical examinations (OME) are mainly focused on occupational disease prevention and control, and generally lack of chronic disease indicators such as blood lipids and blood glucose, limiting the role of OME in life-cycle health management of workers. To address this gap, it is necessary to incorporate chronic disease screening indicators into OME. Integrating OME and chronic disease screening faces bottlenecks, including concerns about increased operating costs in small- and medium-sized enterprises, and the risk of employment discrimination caused by the leakage of employee health privacy. A tiered strategy is recommended. Incorporating low-cost indicators such as blood lipids, waist circumference into routine examinations, and customizing advanced screening for elder or high-risk position workers. The prioritization of screening indicators can be determined by expert consultation and employer-employee discussions. Meanwhile, the results of chronic disease screening indicators should not be included in occupational health surveillance records to protect workers′ privacy. In summary, expanding OME to cover more chronic disease indicators provides valuable economic and social benefits. In the long run, common chronic disease screening indicators should be included in the regular medical examination indicators of OME, thereby reducing the burden of chronic diseases on occupational populations and promoting the health management of occupational populations.

This study， anchored in the traditional Chinese medicine （TCM） syndrome differentiation and treatment principles alongside the clinical characteristics of sepsis in Western medicine， extensively gathers and meticulously dissects the latest research findings on sepsis animal models from both Chinese and international sources. Adhering strictly to TCM syndrome diagnostic criteria for sepsis， the study conducts a thorough evaluation of various animal models across multiple dimensions， including clinical manifestations， pathological changes， and biomarker expressions， so as to reflect the degree of resemblance these models have to human sepsis TCM syndromes. The results reveal that the colon stent implantation model exhibits a higher degree of congruence with both TCM and Western medicine standards， particularly aligning with the diagnosis of the "Fu-Qi obstruction syndrome". Conversely， the extraperitoneal sepsis model shows a higher degree of congruence with TCM， fitting more closely with the diagnosis of "acute deficiency syndrome" and emphasizing the core pathogenesis of Qi deficiency in sepsis. These findings not only augment the diversity of sepsis animal models but also highlight the necessity and potential of integrated TCM and western medicine research. Current sepsis animal models predominantly focus on western pathophysiological mechanisms， with limited direct incorporation of TCM syndrome differentiation elements. This underscores the need， in future study designs， to actively explore integrating TCM syndrome classification and intervention principles into model development. This could be achieved by manipulating model-inducing factors and observing more TCM-specific symptoms and signs among other strategies， so as to establish sepsis models that more closely resemble clinical reality and incorporate both TCM and western medical perspectives.