...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Quality Control and Applied Statistics >Nonparametric variable selection for predictive models and subpopulations in clinical trials
【24h】

Nonparametric variable selection for predictive models and subpopulations in clinical trials

机译：用于临床试验中预测模型和亚群的非参数变量选择

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In most of clinical trials, a heterogeneous treatment effect exists among patient individuals. This prompts identifying a patient subpopulation that has a stronger treatment effect than the rest of patients, which in turn, will help researchers to determine who will benefit the most or the least from the treatment and design treatment strategies accordingly. Therefore, identifying such a subpopulation is a challenging task for researchers. In this paper attempts are made to develop a nonparametric variable selection method for predicting clinical response and identifying subpopulations. The proposed method first selects predictors using kernel-based local regression and a forward procedure via F-tests and then defines subpopulations with enhanced treatment effects based on the selected predictors and the nonparametric model of the clinical response. In order to demonstrate the working of the proposed methods and to compare the same with other existing methods, both simulation and real time clinical examples are considered. The proposed method provides an alternative way to define subpopulations and is not limited by parametric models and their possible misspecification for the clinical response. (22 refs.)
机译：在大多数临床试验中，患者个体中存在异质治疗效果。这提示识别具有更强的治疗效果的患者亚贫困，这些患者与其他患者反过来又会帮助研究人员确定谁将受益于最多或最少的治疗和设计治疗策略。因此，识别这样的亚群是研究人员有挑战性的任务。在本文中，尝试开发非参数可变选择方法，用于预测临床响应和识别群体。所提出的方法首先通过F-Tests使用基于内核的本地回归和前向过程选择预测器，然后基于所选预测器和临床反应的非参数模型来定义具有增强的治疗效果的子步骤。为了证明所提出的方法的工作并与其他现有方法进行比较，考虑模拟和实时临床实施例。该方法提供了定义亚步骤的替代方法，并且不受参数模型的限制及其可能的临床反应的误操作。 （22参考文献）

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号