Radespiel-Tröger M, Rabenstein T, Schneider H T, Lausen B
Department of Medical Informatics, Biometry and Epidemiology, Friedrich-Alexander-University, Waldstrasse 6, D-91054 Erlangen, Germany.
Artif Intell Med. 2003 Jul;28(3):323-41. doi: 10.1016/s0933-3657(03)00060-5.
Tree-based methods can be used to generate rules for prognostic classification of patients that are expressed as logical combinations of covariate values. Several splitting algorithms have been proposed for generating trees from survival data. However, the choice of an appropriate algorithm is difficult and may also depend on clinical considerations. By means of a prognostic study of patients with gallbladder stones and of a simulation study, we compare the following splitting algorithms: log-rank statistic adjusted for measurement scale with (AP) and without (AU) pruning, exponential log-likelihood loss (EP), Kaplan-Meier (KP) distance of survival curves, unadjusted log-rank statistic (LP), martingale residuals (MP), and node impurity (ZP). With the exception of the AU algorithm (based on a Bonferroni-adjusted p-value driven stopping rule), trees are pruned using the measure of split-complexity, and optimally-sized trees are selected using cross-validation. The integrated Brier score is used for the evaluation of predictive models. According to the results of our simulation study and of the clinical example, we conclude that the AU, AP, EP, and LP algorithm may yield superior predictive accuracy. The choice among these four algorithms may be based on the required parsimonity and on medical considerations.
基于树的方法可用于生成患者预后分类规则，这些规则以协变量值的逻辑组合形式表示。已经提出了几种从生存数据生成树的分裂算法。然而，选择合适的算法很困难，并且可能还取决于临床考虑因素。通过对胆结石患者的预后研究和模拟研究，我们比较了以下分裂算法：针对测量尺度调整的对数秩统计量（有（AP）和无（AU）剪枝）、指数对数似然损失（EP）、生存曲线的Kaplan-Meier（KP）距离、未调整的对数秩统计量（LP）、鞅残差（MP）和节点杂质（ZP）。除了AU算法（基于Bonferroni调整的p值驱动停止规则）外，使用分裂复杂度度量对树进行剪枝，并使用交叉验证选择最优大小的树。综合Brier评分用于评估预测模型。根据我们模拟研究和临床实例的结果，我们得出结论，AU、AP、EP和LP算法可能产生更高的预测准确性。这四种算法之间的选择可以基于所需的简约性和医学考虑因素。
