Chen Jin-hong, Wu Hai-yun, He Kun-lun, He Yao, Qin Yin-he
The General Hospital of CAPF, Beijing 100039, China.
Zhonghua Liu Xing Bing Xue Za Zhi. 2010 Oct;31(10):1166-9.
To establish and verify the prediction model for ischemic cardiovascular disease (ICVD) among the elderly population who were under the current health care programs.
Statistical analysis on data from physical examination, hospitalization of the past years, from questionnaire and telephone interview was carried out in May, 2003. Data was from a hospital which implementing a health care program. Baseline population with a proportion of 4:1 was randomly selected to generate both module group and verification group. Baseline data was induced to make the verification group into regression model of module group and to generate the predictive value. Distinguished ability with area under ROC curve and the predictive veracity were verified through comparing the predictive incidence rate and actual incidence rate of every deciles group by Hosmer-Lemeshow test. Predictive veracity of the prediction model at population level was verified through comparing the predictive 6-year incidence rates of ICVD with actual 6-year accumulative incidence rates of ICVD with error rate calculated.
The samples included 2271 males over the age of 65 with 1817 people for modeling population and 454 for verified population. All of the samples were stratified into two layers to establish hierarchical Cox proportional hazard regression model, including one advanced age group (greater than or equal to 75 years old), and another elderly group (less than 75 years old). Data from the statically analysis showed that the risk factors in aged group were age, systolic blood pressure, serum creatinine level, fasting blood glucose level, while protective factor was high density lipoprotein;in advanced age group, the risk factors were body weight index, systolic blood pressure, serum total cholesterol level, serum creatinine level, fasting blood glucose level, while protective factor was HDL-C. The area under the ROC curve (AUC) and 95%CI were 0.723 and 0.687 - 0.759 respectively. Discriminating power was good. All individual predictive ICVD cumulative incidence and actual incidence were analyzed using Hosmer-Lemeshow test, χ(2) = 1.43, P = 0.786, showing that the predictive veracity was good.
The stratified Cox Hazards Regression model was used to establish prediction model of the aged male population under a certain health care program. The common prediction factor of the two age groups were: systolic blood pressure, serum creatinine level, fasting blood glucose level and HDL-C. The area under the ROC curve of the verification group was 0.723, showing that the distinguished ability was good and the predict ability at the individual level and at the group level were also satisfactory. It was feasible to using Cox Proportional Hazards Regression Model for predicting the population groups.
建立并验证针对当前医保项目覆盖下老年人群的缺血性心血管疾病（ICVD）预测模型。
于2003年5月对来自体检、过去数年住院病历、问卷调查及电话访谈的数据进行统计分析。数据源自一家实施医保项目的医院。按4:1的比例随机抽取基线人群，形成建模组和验证组。将基线数据导入，使验证组进入建模组的回归模型并生成预测值。通过Hosmer-Lemeshow检验比较各十分位数组的预测发病率与实际发病率，以验证模型的区分能力（ROC曲线下面积）及预测准确性。通过比较ICVD的预测6年发病率与实际6年累积发病率并计算误差率，验证预测模型在人群水平的预测准确性。
样本包括2271名65岁以上男性，其中1817人作为建模人群，454人作为验证人群。所有样本分为两层，建立分层Cox比例风险回归模型，包括一个高龄组（大于或等于75岁）和另一个老年组（小于75岁）。统计分析数据显示，老年组的危险因素为年龄、收缩压、血清肌酐水平、空腹血糖水平，保护因素为高密度脂蛋白；高龄组的危险因素为体重指数、收缩压、血清总胆固醇水平、血清肌酐水平、空腹血糖水平，保护因素为HDL-C。ROC曲线下面积（AUC）及95%可信区间分别为0.723和0.687 - 0.759。区分能力良好。使用Hosmer-Lemeshow检验分析所有个体预测的ICVD累积发病率与实际发病率，χ(2)=1.43，P = 0.786，表明预测准确性良好。
采用分层Cox风险回归模型建立了特定医保项目下老年男性人群的预测模型。两个年龄组的共同预测因素为：收缩压、血清肌酐水平、空腹血糖水平及HDL-C。验证组的ROC曲线下面积为0.723，表明区分能力良好，个体水平和群体水平的预测能力也令人满意。使用Cox比例风险回归模型对人群进行预测是可行的。
