基于logistic回归与决策树模型的南京市居民代谢综合征影响因素分析

【目的】分析南京市成年居民代谢综合征的患病率并探讨其影响因素，以期为预防代谢综合征提供依据。【方法】使用2018年南京市成人慢性病专题调查资料，分析南京市代谢综合征的流行病学分布特征，使用决策树模型和多因素logistic回归模型分析代谢综合征的影响因素。【结果】南京市18岁及以上人群代谢综合征的加权患病率为16.14%(95%CI:16.12%～16.16%)，不同人口学特征的调查对象间代谢综合征患病率均有统计学差异（P<0.05）。logistic回归模型分析显示：年龄、性别、婚姻状况、吸烟状况、饮酒状况、体重状况、文化程度、体力活动水平、糖尿病和高血压家族史是代谢综合征患病率的影响因素（P<0.05）。决策树模型分析显示体重状况是代谢综合征最主要的影响因素，其次是年龄、性别、糖尿病家族史和吸烟状况。【结论】代谢综合征在南京市成年人群当中患病率较高，应特别关注超重肥胖，有糖尿病家族史、吸烟的男性中老年人群。

Influencing factors of metabolic syndrome among adults in Nanjing， China: an analysis based on decision tree and logistic regress models

ObjectiveWe analyzed the prevalence of metabolic syndrome in adult residents of Nanjing and explored its influencing factors in order to provide technical references for the prevention of metabolic syndrome.MethodsBased on the data of the Nanjing adult chronic disease thematic survey from January 2017 to June 2018， the influencing factors of metabolic syndrome were analyzed using multifactorial logistic regression model and decision tree model.ResultsThe weighted prevalence of metabolic syndrome among people aged 18 years and over in Nanjing was 16.14%（95%CI:16.12%?16.16%）. Prevalence of metabolic syndrome was statistically different（P<0.05）among respondents with different demographic characteristics. Logistic regression model analysis showed that age， gender， education， physical activity level， marriage status， smoking status， drinking status， weight status， diabetes and hypertension family history were the influencing factors for the prevalence of metabolic syndrome（P<0.05）. The results of the decision tree model showed that weight status was the most influential factor for metabolic syndrome， followed by age， gender， diabetes family history and smoking status.ConclusionThe prevalence of metabolic syndrome is high among the adult population in Nanjing， and special attention should be paid to middle-aged and elderly men who are overweight and obese， have a family history of diabetes and smoking.