A multiobjective Bayesian networks approach for joint prediction of tumor local control and radiation pneumonitis in nonsmall-cell lung cancer (NSCLC) for response-adapted radiotherapy.
A multiobjective Bayesian networks approach for joint prediction of tumor local control and radiation pneumonitis in nonsmall-cell lung cancer (NSCLC) for response-adapted radiotherapy.
复制标题
DOI：
10.1002/mp.13029
复制
发表时间：
2018-06-04
期刊：
影响因子：
3.8
通讯作者：
El Naqa I
中科院分区：
文献类型：
--
作者：
Luo Y;McShan DL;Matuszak MM;Ray D;Lawrence TS;Jolly S;Kong FM;Ten Haken RK;El Naqa I
非小细胞肺癌放射治疗的个体化治疗结果可能会因影响肿瘤局部控制（LC）和放射性肺炎（RP）等副作用的生物物理因素缺乏适当的平衡而受到影响，而这些因素可能是相互交织的。在这里，我们比较了针对适应反应的个性化治疗计划的单独和联合结果预测的性能。研究人员对 118 名接受前瞻性方案治疗的 NSCLC 患者进行了研究，其中 32 例出现局部进展，20 例出现 RP 二级或更高级别 (RP2)。放射治疗前和放射治疗期间的 68 名患者（具有 297 个特征）被用于发现，50 名患者被保留用于独立测试。开发了多目标贝叶斯网络 (MO-BN) 方法来识别联合 LC/RP2 预测的重要特征，使用扩展马尔可夫毯子作为输入来开发 BN 预测结构。交叉验证（CV）用于指导 MO-BN 结构学习。自由反应受试者工作特征（AU-FROC）曲线下的面积用于评估联合预测性能。选择了重要特征，包括单核苷酸多态性 (SNP)、微小 RNA、治疗前细胞因子、治疗前 PET 放射组学以及肺和肿瘤 gEUD，并在治疗前 MO-BN 中确定了它们与放射结果（LC 和 RP2）的生物物理相互关系。根据内部 CV，联合 LC/RP2 预测得出的 AU-FROC 为 0.80（95% CI：0.70-0.86）。在治疗期间 MO-BN 的放射治疗过程中，通过额外的两个 SNP、一种细胞因子的变化和两种放射组学 PET 图像特征，该值提高到 0.85 (0.75-0.91)。该 MO-BN 模型在治疗期间优于组合单目标贝叶斯网络 (SO-BN) (0.78 (0.67-0.84))。测试数据集上的 MO-BN 和单个 SO-BN 评估中的 AU-FROC 值在治疗前分别为 0.77 和 0.68，在治疗期间分别为 0.79 和 0.71。 MO-BN 可以揭示竞争性放射治疗临床终点之间可能存在的生物物理串扰。通过提供额外的治疗期间信息来改进预测。开发的 MO-BN 可以成为个性化响应适应放射治疗决策支持系统的重要组成部分。
Individualization of therapeutic outcomes in NSCLC radiotherapy is likely to be compromised by the lack of proper balance of biophysical factors affecting both tumor local control (LC) and side effects such as radiation pneumonitis (RP), which are likely to be intertwined. Here, we compare the performance of separate and joint outcomes predictions for response-adapted personalized treatment planning. 118 NSCLC patients treated on prospective protocols with 32 cases of local progression and 20 cases of RP grade two or higher (RP2) were studied. 68 patients with 297 features before and during radiotherapy were used for discovery and 50 patients were reserved for independent testing. A multi-objective Bayesian network (MO-BN) approach was developed to identify important features for joint LC/RP2 prediction using extended Markov blankets as inputs to develop a BN predictive structure. Cross-validation (CV) was used to guide the MO-BN structure learning. Area under the free-response receiver operating characteristic (AU-FROC) curve was used to evaluate joint prediction performance. Important features including single nucleotide polymorphisms (SNPs), micro RNAs, pre-treatment cytokines, pre-treatment PET radiomics together with lung and tumor gEUDs were selected and their biophysical inter-relationships with radiation outcomes (LC and RP2) were identified in a pre-treatment MO-BN. The joint LC/RP2 prediction yielded an AU-FROC of 0.80 (95% CI: 0.70-0.86) upon internal CV. This improved to 0.85 (0.75-0.91) with additional two SNPs, changes in one cytokine and two radiomics PET image features through the course of radiotherapy in a during-treatment MO-BN. This MO-BN model outperformed combined single-objective Bayesian networks (SO-BNs) during-treatment (0.78 (0.67-0.84)). AU-FROC values in the evaluation of the MO-BN and individual SO-BNs on the testing dataset were 0.77 and 0.68 for pre-treatment, and 0.79 and 0.71 for during-treatment, respectively. MO-BNs can reveal possible biophysical cross-talks between competing radiotherapy clinical endpoints. The prediction is improved by providing additional during-treatment information. The developed MO-BNs can be an important component of decision support systems for personalized response-adapted radiotherapy.
登录
查看更多内容
DOI：
10.1016/j.ijrobp.2009.06.091
发表时间：
2010-03-01
影响因子：
7
作者：
Marks, Lawrence B.;Bentzen, Soren M.;Deasy, Joseph O.;Kong, Feng-Ming (Spring);Bradley, Jeffrey D.;Vogelius, Ivan S.;El Naqa, Issam;Hubbs, Jessica L.;Lebesque, Joos V.;Timmerman, Robert D.;Martel, Mary K.;Jackson, Andrew
通讯作者：
Jackson, Andrew
DOI：
10.1016/j.ijrobp.2005.02.010
发表时间：
2005-10-01
影响因子：
7
作者：
Kong, FM;Ten Haken, RK;Hayman, JA
通讯作者：
Hayman, JA
DOI：
10.1038/nrclinonc.2012.196
发表时间：
2013-01
期刊：
Nature reviews. Clinical oncology
影响因子：
--
作者：
Lambin P;van Stiphout RG;Starmans MH;Rios-Velazquez E;Nalbantov G;Aerts HJ;Roelofs E;van Elmpt W;Boutros PC;Granone P;Valentini V;Begg AC;De Ruysscher D;Dekker A
通讯作者：
Dekker A
影响因子：
3.7
作者：
Cheng NM;Fang YH;Tsan DL;Hsu CH;Yen TC
通讯作者：
Yen TC
影响因子：
1.9
作者：
Bandos, Andriy I.;Rockette, Howard E.;Gur, David
通讯作者：
Gur, David