Variables with time-varying effects and the Cox model: some statistical concepts illustrated with a prognostic factor study in breast cancer.
Variables with time-varying effects and the Cox model: some statistical concepts illustrated with a prognostic factor study in breast cancer.
复制标题
DOI：
10.1186/1471-2288-10-20
复制
发表时间：
2010-03-16
影响因子：
4
通讯作者：
Mathoulin-Pélissier S
中科院分区：
文献类型：
--
作者：
Bellera CA;MacGrogan G;Debled M;de Lara CT;Brouste V;Mathoulin-Pélissier S
考克斯模型依赖于比例风险（PH）假设，这意味着研究的因素随着时间的推移对风险或风险具有恒定的影响。我们强调这一假设的重要性，以及如果违反这一假设，可能推断出的误导性结论;这一点在长期后续行动的情况下尤其重要。我们通过分析979例手术治疗乳腺癌的妇女转移的预后因素来说明我们的讨论。年龄、肿瘤大小和分级、淋巴结受累、瘤周血管浸润（PVI）、激素受体（HRec）、Her 2和Mib 1的状态均被考虑在内。中位随访时间为14年; 264名女性发生转移。传统的考克斯模型表明，所有因素，但HRec，Her 2，Mib 1状态是转移的强预后因素。其他检验表明，模型的某些变量不满足PH假设。肿瘤等级具有显著的随时间变化的影响，但尽管其影响随着时间的推移而减弱，但仍然很强。有趣的是，虽然传统的考克斯模型没有显示出HRec状态的任何显著影响，但检验提供了强有力的证据，表明该变量随时间推移具有非恒定的影响。阴性HRec状态增加了早期转移的风险，但此后变得具有保护性。这种效应逆转可能解释了在长期随访的研究中，以前的传统考克斯分析提供的非显著风险比。研究随时间变化的效应应该是考克斯生存分析的一个组成部分。检测和说明随时间变化的影响提供了一些特定的时间模式，以及有价值的生物信息，否则可能会错过的见解。
The Cox model relies on the proportional hazards (PH) assumption, implying that the factors investigated have a constant impact on the hazard - or risk - over time. We emphasize the importance of this assumption and the misleading conclusions that can be inferred if it is violated; this is particularly essential in the presence of long follow-ups. We illustrate our discussion by analyzing prognostic factors of metastases in 979 women treated for breast cancer with surgery. Age, tumour size and grade, lymph node involvement, peritumoral vascular invasion (PVI), status of hormone receptors (HRec), Her2, and Mib1 were considered. Median follow-up was 14 years; 264 women developed metastases. The conventional Cox model suggested that all factors but HRec, Her2, and Mib1 status were strong prognostic factors of metastases. Additional tests indicated that the PH assumption was not satisfied for some variables of the model. Tumour grade had a significant time-varying effect, but although its effect diminished over time, it remained strong. Interestingly, while the conventional Cox model did not show any significant effect of the HRec status, tests provided strong evidence that this variable had a non-constant effect over time. Negative HRec status increased the risk of metastases early but became protective thereafter. This reversal of effect may explain non-significant hazard ratios provided by previous conventional Cox analyses in studies with long follow-ups. Investigating time-varying effects should be an integral part of Cox survival analyses. Detecting and accounting for time-varying effects provide insights on some specific time patterns, and on valuable biological information that could be missed otherwise.
登录
查看更多内容
影响因子：
1.9
作者：
LAGAKOS, SW;SCHOENFELD, DA
通讯作者：
SCHOENFELD, DA
影响因子：
3.8
作者：
Anderson, William F.;Chen, Bingshu E.;Rosenberg, Philip S.
通讯作者：
Rosenberg, Philip S.
影响因子：
3.7
作者：
Abrahamowicz, M;MacKenzie, T;Esdaile, JM
通讯作者：
Esdaile, JM
生存分析第二部分：多元数据分析 - 概念和方法简介。
影响因子：
8.8
作者：
通讯作者：
--
在癌症期刊上发表的生存分析的综述。
影响因子：
8.8
作者：
Altman, D G;De Stavola, B L;Love, S B;Stepniewska, K A
通讯作者：
Stepniewska, K A