Prognosis of Right Ventricular Failure in Patients With Left Ventricular Assist Device Based on Decision Tree With SMOTE
Prognosis of Right Ventricular Failure in Patients With Left Ventricular Assist Device Based on Decision Tree With SMOTE
复制标题
DOI：
10.1109/titb.2012.2187458
复制
发表时间：
2012-05-01
影响因子：
--
通讯作者：
Antaki, James F.
中科院分区：
文献类型：
--
作者：
Wang, Yajuan;Simon, Marc;Antaki, James F.
右心室衰竭是植入左心室辅助装置 (LVAD) 后的一个严重并发症，会增加发病率和死亡率。因此，研究人员寻找可以识别高危患者的预测因子。然而，它们缺乏敏感性和/或特异性。本研究调查了使用决策树技术来探索术前数据空间，以获得可能更准确和精确的组合关系。我们回顾性分析了 1996 年 5 月至 2009 年 10 月期间在匹兹堡大学医学中心人工心脏项目首次植入 LVAD 的 183 例患者的记录。在这些患者中，27 例后来需要右心室辅助装置 (RVAD+)，156 例一直使用 LVAD (RVAD-)，直到移植或死亡。将合成少数过采样技术（SMOTE）应用于 RVAD+ 组，以补偿样本量的差异。评估了二十一个重采样级别，并为每个级别构建了决策树模型。在这些模型中，需要 RVAD 的前六位预测因素是跨肺压差 (TPG)、年龄、国际标准化比值 (INR)、心率 (HR)、天冬氨酸转氨酶 (AST)、凝血酶原时间和右心室收缩压。在 21 个模型中的 15 个模型中，TPG 被认为是最具预测性的变量，并以 7 mmHg 为断点构成了第一个分裂节点。过采样被证明可以单调地提高模型的灵敏度，尽管是渐近的，但特异性会在较小程度上降低。研究发现，基于 5 倍合成 RVAD+ 过采样构建的模型可在灵敏度和特异性之间提供最佳折衷，包括 TPG（第 1 层）、年龄（第 2 层）、右心房压力（第 3 层）、HR（第 4,7 层）、INR（第 4,7 层）、INR（第 4、9 层）、丙氨酸转氨酶（第 5 层）、白细胞计数（第 5,6 层和第 7 层）、正性肌力药物数量（第 6 层）、肌酐（第 8 层）、AST（第 9、10 层）和心输出量（第 9 层）。它表现出 85% 的敏感性、83% 的特异性和 0.87 的受试者工作特征曲线下面积 (RoC)，与之前发表的研究相比有很大改善。
Right ventricular failure is a significant complication following implantation of a left ventricular assist device (LVAD), which increases morbidity and mortality. Consequently, researchers have sought predictors that may identify patients at risk. However, they have lacked sensitivity and/or specificity. This study investigated the use of a decision tree technology to explore the preoperative data space for combinatorial relationships that may be more accurate and precise. We retrospectively analyzed the records of 183 patients with initial LVAD implantation at the Artificial Heart Program, University of Pittsburgh Medical Center, between May 1996 and October 2009. Among those patients, 27 later required a right ventricular assist device (RVAD+) and 156 remained on LVAD (RVAD-) until the time of transplantation or death. A synthetic minority oversampling technique (SMOTE) was applied to the RVAD+ group to compensate for the disparity of sample size. Twenty-one resampling levels were evaluated, with decision tree model built for each. Among these models, the top six predictors of the need for an RVAD were transpulmonary gradient (TPG), age, international normalized ratio (INR), heart rate (HR), aspartate aminotransferase (AST), prothrombin time, and right ventricular systolic pressure. TPG was identified to be the most predictive variable in 15 out of 21 models, and constituted the first splitting node with 7 mmHg as the breakpoint. Oversampling was shown to improve the senstivity of the models monotonically, although asymptotically, while the specificity was diminished to a lesser degree. The model built upon 5X synthetic RVAD+ oversampling was found to provide the best compromise between sensitivity and specificity, included TPG (layer 1), age (layer 2), right atrial pressure (layer 3), HR (layer 4,7), INR (layer 4, 9), alanine aminotransferase (layer 5), white blood cell count (layer 5,6, & 7), the number of inotrope agents (layer 6), creatinine (layer 8), AST (layer 9, 10), and cardiac output (layer 9). It exhibited 85% sensitivity, 83% specificity, and 0.87 area under the receiver operating characteristic curve (RoC), which was found to be greatly improved compared to previously published studies.