Richardson B A, Hughes J P
Department of Biostatistics, University of Washington, Seattle 98195, USA.
Biostatistics. 2000 Sep;1(3):341-54. doi: 10.1093/biostatistics/1.3.341.
Low sensitivity and/or specificity of a diagnostic test for outcome results in biased estimates of the time to first event using product limit estimation. For example, if a test has low specificity, estimates of the cumulative distribution function (cdf) are biased towards time zero, while estimates of the cdf are biased away from time zero if a test has low sensitivity. In the context of discrete time survival analysis for infectious disease data, we develop self-consistent algorithms to obtain unbiased estimates of the time to first event when the sensitivity and/or specificity of the diagnostic test for the outcome is less than 100%. Two examples are presented. The first involves estimating time to first detection of HIV-1 infection in infants in a randomized clinical trial, and the second involves estimating time to first Neisseria gonorrhoeae infection in a cohort of Kenyan prostitutes.
诊断测试对结果的低敏感性和/或特异性会导致使用乘积限估计法对首次事件发生时间的估计产生偏差。例如，如果一项测试特异性较低，累积分布函数（cdf）的估计会偏向时间零点；而如果一项测试敏感性较低，cdf的估计则会偏离时间零点。在传染病数据的离散时间生存分析背景下，当诊断测试对结果的敏感性和/或特异性低于100%时，我们开发了自洽算法来获得首次事件发生时间的无偏估计。给出了两个例子。第一个例子涉及在一项随机临床试验中估计婴儿首次检测出HIV-1感染的时间，第二个例子涉及在一组肯尼亚妓女中估计首次感染淋病奈瑟菌的时间。
