...
  • 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 >A hybrid model for combining case-control and cohort studies in systematic reviews of diagnostic tests
【24h】

A hybrid model for combining case-control and cohort studies in systematic reviews of diagnostic tests

机译：结合病例对照研究和队列研究，对诊断测试进行系统评价的混合模型

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

Multivariate meta-analysis has gained popularity recently, especially in systematic reviews of diagnostic tests. In research on diagnostic tests, its comparative effectiveness often relies on the systematic reviews of diagnostic accuracy. The article proposes developing a hybrid multivariate random-effects model for study of diagnostic test accuracy. In this regard, the proposed hybrid model that combines case-control and cohort studies is described in detail. Instead of using the standard likelihood-based inference, in this paper, two alternative inference procedures, namely the full likelihood and composite likelihood methods are considered. Simulation studies are conducted to compare these two inference procedures. The proposed approach is applied to a systematic review of the accuracy of contemporary diagnostic imaging modalities for detecting metastases in patients with melanoma. The paper ends by discussing the performance and advantages of both full likelihood and composite likelihood inference methods. (49 refs.)
机译：多元荟萃分析最近变得越来越流行，特别是在诊断测试的系统评价中。在诊断测试的研究中，其相对有效性通常取决于对诊断准确性的系统评价。本文提出了一种用于研究诊断测试准确性的混合多元随机效应模型。在这方面，详细描述了结合病例对照研究和队列研究的混合模型。本文不使用标准的基于似然性的推理，而是考虑了两种替代推理程序，即完全似然法和复合似然法。进行仿真研究以比较这两个推理过程。拟议的方法应用于当代诊断成像模式的准确性的系统评价，以检测黑色素瘤患者的转移情况。本文最后讨论了完全似然和复合似然推理方法的性能和优势。 （49篇）

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