Feature selection for outcome prediction in oesophageal cancer using genetic algorithm and random forest classifier
Feature selection for outcome prediction in oesophageal cancer using genetic algorithm and random forest classifier
复制标题
DOI：
10.1016/j.compmedimag.2016.12.002
复制
发表时间：
2017-09-01
影响因子：
5.7
通讯作者：
Isabelle, Gardin
中科院分区：
文献类型：
--
作者：
Paul, Desbordes;Su, Ruan;Isabelle, Gardin
患者的预后预测可以极大地帮助个性化癌症治疗。大量的定量特征（临床检查、成像等）可能有助于评估患者的预后。挑战在于选择最具预测性的特征子集。在本文中，我们提出了一种新的特征选择策略，称为GARF（遗传算法的基础上随机森林）提取的正电子发射断层扫描（PET）图像和临床数据。使用GARF对65例适合放化疗的局部晚期食管癌患者队列选择最相关的特征，预测治疗反应或治疗结束后3年患者生存率。使用9个特征的子集获得最相关的预测结果，导致随机森林误分类率为18 +/- 4%，受试者工作特征（ROC）曲线下面积（AUC）为0.823 +/- 0.032。获得了最相关的预后结果，其中8个特征导致错误率为20 +/- 7%，AUC为0.750 +/- 0.108。预测和预后结果显示使用GARF比使用其他4种研究方法更好的性能。(C)2016爱思唯尔有限公司版权所有
The outcome prediction of patients can greatly help to personalize cancer treatment. A large amount of quantitative features (clinical exams, imaging,...) are potentially useful to assess the patient outcome. The challenge is to choose the most predictive subset of features. In this paper, we propose a new feature selection strategy called GARF (genetic algorithm based on random forest) extracted from positron emission tomography (PET) images and clinical data. The most relevant features, predictive of the therapeutic response or which are prognoses of the patient survival 3 years after the end of treatment, were selected using 'GARF on a cohort of 65 patients with a local advanced oesophageal cancer eligible for chemoradiation therapy. The most relevant predictive results were obtained with a subset of 9 features leading to a random forest misclassification rate of 18 +/- 4% and an areas under the of receiver operating characteristic (ROC) curves (AUC) of 0.823 +/- 0.032. The most relevant prognostic results were obtained with 8 features leading to an error rate of 20 +/- 7% and an AUC of 0.750 +/- 0.108. Both predictive and prognostic results show better performances using GARF than using 4 other studied methods. (C) 2016 Elsevier Ltd. All rights reserved.