论文部分内容阅读
目的 构建健康管理队列慢性阻塞性肺疾病(COPD)的风险预测模型,对模型预测效果进行评价,为COPD的防治提供理论依据.方法 模型队列的建立基于“山东多中心健康管理纵向观察大数据队列”,共有33383人进入队列.通过对慢性阻塞性肺疾病发生的危险因素进行变量筛选,应用Cox比例风险回归建立COPD的预测模型,十折交叉验证法判别模型准确性,受试者工作特征曲线下面积(AUC)衡量模型的辨别能力.结果 队列观察期间,共发生慢性阻塞性肺疾病136例,发病密度为118.08/10万人年.最终纳入模型的变量为年龄、性别、吸烟、白蛋白、血压和血白细胞计数.模型ROC曲线下面积为0.872(95％CI:0.810～0.934),十折交叉验证后ROC曲线下面积为0.866(95％CI:0.809～0.923).结论 构建的慢性阻塞性肺疾病预测模型在健康管理队列中有较好的预测能力.“,”Objective To establish a risk prediction model of chronic obstructive pulmonary disease ( COPD) among health management Chinese population, and to evaluate its effects in order to provide theoretical basis for the prevention and treatment of COPD. Methods The model was established based on “Shandong Multicenter Health Management Longitudinal Cohort of Observation Large Data”. A total of 33383 people were included. Cox proportional hazards re-gression model for COPD was established after variable screening of the influencing factors of COPD. The stability of the model was tested with ten-fold cross validation. The discriminatory ability of the model was determined with the area under the receiver operating characteristic curve (AUC). Results Altogether 136 COPD cases were observed over the study, resulting in a cumulative incidence of 118.08/100000 person-year. The risk factors included age, gender, smoke, albu-min, blood pressure and white blood cell count. The estimated AUC for the model was 0.872 (95％CI:0.810-0.930). Af-ter internal verification by ten-fold cross validation, the AUC was 0.866 (95％CI:0.809-0.923). Conclusion We have constructed a risk model that can be useful in identifying individuals at high risk of COPD in our cohort.