基于分类回归树模型的兰渝线陇南段铁路职工血脂异常流行现状及影响因素分析

Analysis on the Epidemiological Characteristics and Influencing Factors of Dyslipidemia among Rail way Workers of Lanzhou-Chongqing Line by Classi fication Regression Tree Model

目的:基于兰渝线陇南段铁路职工健康体检数据,建立血脂异常发生风险的预测模型。方法:选取2016—2021年参加健康体检的兰渝线陇南段铁路职工作为研究对象,评估并比较血脂正常与血脂异常人群的体检指标。共纳入3970人,其中男性3625人(91.31%)、女性345人(8.69%)。建立分类回归树模型预测血脂异常发生风险。结果:血脂正常人群为2794人(70.38%),血脂异常人群为1176人(29.62%)。同年度比较,血脂异常人群平均年龄、身体质量指数(BMI)均显著高于血脂正常人群,且以男性和超重肥胖者居多;血脂异常人群甘油三酯、总胆固醇、低密度脂蛋白显著高于血脂正常人群,高密度脂蛋白显著低于血脂正常人群;血脂异常人群收缩压(除2016年外)和舒张压均显著高于血脂正常人群。2020年和2021年血脂异常人群的血糖值显著高于血脂正常人群。2019—2021年血脂异常伴高血压或糖代谢异常的人群占比也显著升高。分类回归树模型分析结果显示,BMI是脂代谢异常重要的预测因素,当BMI超过22.78 kg/m^(2)时脂代谢异常占比上升至43.40%;当BMI超过26.46 kg/m^(2)时脂代谢异常占比上升至57.50%。结论:兰渝线陇南段铁路职工血脂异常检出率为29.62%,BMI是血脂异常重要的预测因素。

OBJECTIVE It aimed to establish a prediction model of dyslipidemia based on the health examination data of railway workers in Lanzhou-Chongqing railway.METHODS Focusing on railway workers,health examination was conducted in hospital from January 2016 to December 2021.The level of blood lipids,blood pressure and blood glucose were evaluated among these railway workers.Then,categorical regression tree model was established to predict the risk of dyslipidemia.RESULTS A total of 3970 workers were included,including 3625 males(91.31%)and 345 females(8.69%).There were 1176 cases(29.62%)and 2794 cases(70.38%)with dyslipidemia,respectively.Compared with the normal group in the same year,the mean age and BMI of workers were significantly increased in the dyslipidemia group.Meanwhile,the workers were mostly male,and overweight or obese in the dyslipidemia group.The level of triglyceride,total-cholesterol,and low-density lipoprotein were significantly increased,whereas high density lipoprotein was significantly decreased in dyslipidemia group.Also,the mean of systolic blood pressure(except 2016),diastolic blood pressure and blood glucosewere significantly increased from 2020 to 2021,as well as the rate of hypertension and abnormal glucose metabolism from 2019 to 2021.In classification regression tree model,BMI was an important predictor of dyslipidemia in railway workers.When BMI exceeded 22.78 kg/m^(2),the rate of dyslipidemia increased to 43.40%.When BMI exceeded 26.46 kg/m^(2),the rate of dyslipidemia increased to 57.50%.CONCLUSION The rate of dyslipidemia is 29.62%among railway workers in Lanzhou—Keywords:Chongqing Line,and BMI is an important predictor of dyslipidemia.