Quantifying the predictive accuracy of time-to-event models in the presence of competing risks
Quantifying the predictive accuracy of time-to-event models in the presence of competing risks
复制标题
DOI：
10.1002/bimj.201000073
复制
发表时间：
2011-02-01
影响因子：
1.7
通讯作者：
Binder, Harald
中科院分区：
文献类型：
--
作者：
Schoop, Rotraut;Beyersmann, Jan;Binder, Harald
事件发生时间数据的预后模型在治疗分配、风险分层和院内质量保证中发挥着重要作用。对其预后价值的评估不仅对于负责任的资源分配至关重要，而且对于其广泛接受也至关重要。感兴趣的事件还存在额外的竞争风险，不仅需要在模型构建方面进行适当的处理，而且还需要在评估过程中进行适当的处理。仍然需要对评估竞争风险模型的预后潜力的方法进行研究，因为大多数提出的方法要么测量它们的辨别力，要么测量校准，但不会同时检查两者。我们采用 Graf 等人的预测误差建议。 (Statistics in Medicine 1999, 18, 2529-2545) 和 Gerds and Schumacher (Biometrical Journal 2006, 48, 1029-1040) 处理具有竞争风险的模型，即不止一种可能的事件类型，并引入一致的估计量。接下来是一项模拟研究，调查估计器在小样本量情况下和不同级别的审查下的行为以及实际数据应用。
Prognostic models for time-to-event data play a prominent role in therapy assignment, risk stratification and inter-hospital quality assurance. The assessment of their prognostic value is vital not only for responsible resource allocation, but also for their widespread acceptance. The additional presence of competing risks to the event of interest requires proper handling not only on the model building side, but also during assessment. Research into methods for the evaluation of the prognostic potential of models accounting for competing risks is still needed, as most proposed methods measure either their discrimination or calibration, but do not examine both simultaneously. We adapt the prediction error proposal of Graf et al. (Statistics in Medicine 1999, 18, 2529-2545) and Gerds and Schumacher (Biometrical Journal 2006, 48, 1029-1040) to handle models with competing risks, i.e. more than one possible event type, and introduce a consistent estimator. A simulation study investigating the behaviour of the estimator in small sample size situations and for different levels of censoring together with a real data application follows.