Traditional statistical methods for evaluating prediction models are uninformative as to clinical value: towards a decision analytic framework.
Traditional statistical methods for evaluating prediction models are uninformative as to clinical value: towards a decision analytic framework.
复制标题
DOI：
10.1053/j.seminoncol.2009.12.004
复制
发表时间：
2010-02
影响因子：
4
通讯作者：
Cronin AM
中科院分区：
文献类型：
--
作者：
Vickers AJ;Cronin AM
癌症预测模型正变得无处不在，但我们通常不知道它们是否利大于弊。这是因为目前用于评估预测模型的统计方法对其临床价值缺乏信息。预测模型通常在判别或校准方面进行评估。然而，普遍不清楚的是，歧视需要达到多高才能被认为是“足够高”；类似地，没有基本原理的指导方针，不校正的程度，将折扣临床使用的模型。分类表确实以临床相关的术语展示了模型的结果，但在特定分类表的基础上，两种模型中哪一种更可取，甚至是否应该使用这两种模型都不清楚。近年来已经看到了直接的决策分析技术的发展，这些技术根据预测模型的结果来评估预测模型。这取决于对真阳性和假阳性进行不同加权的简单方法，以反映出，例如，延迟癌症的诊断比不必要的活组织检查更有害。这种决策分析技术有望确定预测模型的临床实施是否利大于弊。
Cancer prediction models are becoming ubiquitous, yet we generally have no idea whether they do more good than harm. This is because current statistical methods for evaluating prediction models are uninformative as to their clinical value. Prediction models are typically evaluated in terms of discrimination or calibration. However, it is generally unclear how high discrimination needs to be before it is considered “high enough”; similarly, there are no rationale guidelines as to the degree of miscalibration that would discount clinical use of a model. Classification tables do present the results of models in more clinically relevant terms, but it is not always clear which of two models is preferable on the basis of a particular classification table, or even whether either model should be used at all. Recent years have seen the development of straightforward decision analytic techniques that evaluate prediction models in terms of their consequences. This depends on the simple approach of weighting true and false positives differently, to reflect that, for example, delaying the diagnosis of a cancer is more harmful than an unnecessary biopsy. Such decision analytic techniques hold the promise of determining whether clinical implementation of prediction models would do more good than harm.
登录
查看更多内容
影响因子：
39.2
作者：
Janes H;Pepe MS;Gu W
通讯作者：
Gu W
影响因子：
10.3
作者：
Kattan, MW;Eastham, JA;Scardino, PT
通讯作者：
Scardino, PT
影响因子：
7.1
作者：
Law, L. W.;Leung, T. Y.;Lau, T. K.
通讯作者：
Lau, T. K.
影响因子：
3.2
作者：
Lin, Chien-Lin;Lin, Pao-Hsuan;Wu, Hong-Dar Isaac
通讯作者：
Wu, Hong-Dar Isaac
影响因子：
6.2
作者：
Massicotte, Luc;Capitanio, Umberto;Karakiewicz, Pierre I.
通讯作者：
Karakiewicz, Pierre I.