The association between cigarette smoking and health care service utilization among middle-aged and elderly adults in China

Split household and smoking behaviour of rural migrants in China

OBJECTIVES

This study aimed to address the direct impact of split households on smoking behaviour. Three types of spilt households (sole migration, couple migration, and family migration) were incorporated to explore the concise effect of different split household forms. This study also examined factors that contributed to the narrowing gap in smoking prevalence between 2008 and 2018.

STUDY DESIGN

Retrospective observational study.

METHODS

Data were obtained from the Rural Urban Migration (RUMiC-2009) and China Household Income Project (CHIP2018). Analyses were conducted using chi-squared tests/analysis of variance tests and multiple logit regression. The order probit model with sample selection was conducted to correct for selection bias. Fairlie decomposition was used to quantify the contribution of individual variables to the observed differences in smoking prevalence.

RESULTS

Smoking prevalence for all migrants decreased by 5.79% between 2008 and 2018. The results in 2008 reveal the positive and significant contribution of couple migration (coefficient = -0.4608; 95% CI = [-0.6453, -0.2762]) and family migration (coefficient = -0.3705; 95% CI = [-0.5959, -0.1452]) on the reduction of smoking; the finding for family migration remained robust in 2018. Measurable factors partially explain the decline in smoking disparity. The migration of families, working in the construction and manufacturing industries, and educational attainment were the largest contributing factors to the declining gap in smoking prevalence.

CONCLUSIONS

The increase in family migration and education, and decrease in the number of workers in the construction and manufacturing industries, contributed to a decrease in smoking prevalence. Public policies should target sole migrants, couple migrants, individuals with lower education levels, and those working in the construction and manufacturing industries.

Prediction of Hemorrhagic Complication after Thrombolytic Therapy Based on Multimodal Data from Multiple Centers: An Approach to Machine Learning and System Implementation

Hemorrhagic complication (HC) is the most severe complication of intravenous thrombolysis (IVT) in patients with acute ischemic stroke (AIS). This study aimed to build a machine learning (ML) prediction model and an application system for a personalized analysis of the risk of HC in patients undergoing IVT therapy. We included patients from Chongqing, Hainan and other centers, including Computed Tomography (CT) images, demographics, and other data, before the occurrence of HC. After feature engineering, a better feature subset was obtained, which was used to build a machine learning (ML) prediction model (Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGB)), and then evaluated with relevant indicators. Finally, a prediction model with better performance was obtained. Based on this, an application system was built using the Flask framework. A total of 517 patients were included, of which 332 were in the training cohort, 83 were in the internal validation cohort, and 102 were in the external validation cohort. After evaluation, the performance of the XGB model is better, with an AUC of 0.9454 and ACC of 0.8554 on the internal validation cohort, and 0.9142 and ACC of 0.8431 on the external validation cohort. A total of 18 features were used to construct the model, including hemoglobin and fasting blood sugar. Furthermore, the validity of the model is demonstrated through decision curves. Subsequently, a system prototype is developed to verify the test prediction effect. The clinical decision support system (CDSS) embedded with the XGB model based on clinical data and image features can better carry out personalized analysis of the risk of HC in intravenous injection patients.