Cox比例风险回归模型C统计量的计算方法及其SAS实现

严若华; 李卫; 谷鸿秋; 王杨

doi:10.16462/j.cnki.zhjbkz.2016.09.023

Cox比例风险回归模型C统计量的计算方法及其SAS实现

doi: 10.16462/j.cnki.zhjbkz.2016.09.023

中国医学科学院北京协和医学院国家心血管病中心阜外医院心血管疾病国家重点实验室医学统计部, 北京 100037

详细信息

作者简介:
严若华(1994-),女,上海人,在读博士研究生。主要研究方向:临床研究方法学。

中图分类号: R195.1;R181
计量
- 文章访问数: 1390
- HTML全文浏览量: 214
- PDF下载量: 166
- 被引次数: 0
出版历程
- 收稿日期: 2016-04-30
- 修回日期: 2016-07-26

Calculation of C statistics for the Cox proportional hazards regression models and its implementation in SAS

State Key Laboratory of Cardiovascular Disease, Fu Wai Hospital, National Center for Cardiovascular Diseases, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100037, China

摘要

摘要: 目的 C统计量是评价Cox比例风险回归模型区分度的常见指标，然而，目前对C统计量的算法仍存在争议。本文将探讨C统计量的计算方法及其SAS实现，为编程输出Cox模型的C统计量提供参考。方法运用PHREG过程估计研究观察期末的累积生存概率，判断实际生存时间与预期生存函数是否同趋势，并以此计算C统计量及其95%置信区间。以某注册登记研究为例，评价年龄、血压和心率对急性心衰患者出院后30 d死亡率的预测区分度。结果研究共纳入2 836例急性心衰患者，年龄、基线收缩压和基线心率对出院后30 d死亡的影响差异都具有统计学意义（均有P<0.05），其中年龄（单位：岁；风险比（hazard ratio, HR）：1.029；95%置信区间（confidence interval, CI）：1.022～1.037）和心率（单位：次/分；HR：1.011；95% CI：1.007～1.014）为危险因素，收缩压（单位：mmHg；HR：0.992；95% CI：0.989～0.995）为保护因素。模型C统计量达到0.638（95%CI：0.570～0.704），可见模型具有一定的区分度，使用SAS程序能够得到所需结果。结论 C统计量是评价模型区分度的良好手段，并可以通过SAS程序求得。
- 统计学,非参数 /
- 模型,统计学 /
- 流行病学方法
Abstract: Objective C statistics is one of the most widely-used indexes in accessing the discrimination of the Cox proportional hazards regression models. However, the calculation methods for C statistics have been controversial. Our study aims to investigate the calculation of C statistics and its implementation in SAS. Methods To calculate C statistics and its 95% confidence interval (CI), we used PROC PHREG to predict the survival function, and decided whether the predicted survival probabilities was consistent with the actual survival times. Taking a registry study as an example, we evaluated the discrimination of a Cox regression model which predicted the 30-day mortality after discharge in patients with acute heart failure. Results A total of 2 836 patients were included in the final analysis. Older age (Unit: years; hazard ratio (HR): 1.029; 95% CI: 1.022-1.037), lower systolic blood pressure (Unit: mmHg; HR: 0.992; 95% CI: 0.989-0.995) and increased pulse rate (Unit: beats/min; HR: 1.011; 95% CI: 1.007-1.014) were all statistically significant predictors for 30-day post-discharge death. The C statistics of the model was 0.638 (95% CI: 0.570-0.704), indicating a certain degree of discrimination. Conclusions C statistics is a good index for accessing the discrimination of Cox regression models, and it can be calculated by SAS programs.
- Statistics, the parameters /
- Models, statistical /
- Epidemiologic methods

HTML全文

参考文献(15)

Harrell FE Jr, Kee KL, Mark DB. Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors [J]. Stat Med, 1996,15(4):361-387.

姜晶梅. 医学实用多元统计学 [M]. 北京:科学出版社,2014.

Hosmer DW, Lemeshow S. Applied Logistic Regression [M]. 2nd Edition New York: John Wiley & Sons, 2000.

何帅, 李海朋, 黄水平. 徐州地区缺血性脑卒中患者的电话综合干预研究 [J]. 中华疾病控制杂志, 2015,19(3):229-232.

黄彬鋆,肖静,吴桂云,等. 214例肺腺癌患者预后因素分析 [J]. 中华疾病控制杂志, 2015,19(8):806-810.

高月霞,黄彬鋆,吴桂云,等. 610例Ⅲ、Ⅳ期非小细胞肺癌患者预后生存分析 [J]. 中华疾病控制杂志, 2015,19(1):74-77.

于瀚卿,李笑秋,黄亚玮,等. 血小板增多与肺癌患者临床病理特征及其预后的相关性分析 [J]. 中华疾病控制杂志, 2015,19(1):78-81.

DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach [J]. Biometrics, 1988,44(3):837-845.

Pencina MJ, D'Agostino RB. Overall C as a measure of discrimination in survival analysis: model specific population value and confidence interval estimation [J]. Stat Med, 2004,23(13):2109-2123.

Breslow N. Covariance Analysis of Censored Survival Data [J]. Biometrics, 1974,30(1): 89-99.

Eagle KA, Lim MJ, Dabbous OH, et al. A validated prediction model for all forms of acute coronary syndrome: estimating the risk of 6-month postdischarge death in an international registry [J]. JAMA, 2004,291(22):2727-2733.

Fox KA, Fitzgerald G, Puymirat E, et al. Should patients with acute coronary disease be stratified for management according to their risk? Derivation, external validation and outcomes using the updated GRACE risk score [J]. BMJ Open, 2014,4(2): e004425.

Liu L, Forman S, Barton B. Fitting Cox Model Using PROC PHREG and Beyond in SAS [Z]. SAS Global Forum, 2009.

Yan G, Greene T. Investigating the effects of ties on measures of concordance [J]. Stat Med, 2008,27(21):4190-4206.

Uno H, Cai T, Pencina MJ, et al. On the C-statistics for evaluating overall adequacy of risk prediction procedures with censored survival data [J]. Stat Med, 2011,30(10):1105-1117.

施引文献

资源附件(0)

访问统计