Jian-Lun Xu

NCI, DCP, BRG

PLCO (Learn more about this study)

2010-0077

Oct 22, 2010

Estimation of Mean Sojourn and Lead Time and Sensitivity in the Ovarian Component of the PLCO Trial

Early indicators of the effectiveness of a screening test for cancers such as ovarian cancer are the length of time the diagnosis is advanced by screening, the lead time, and the sensitivity of the screening test. Cancer antigen CA-125 (CA-125) and transvaginal ultrasound (TVU) have been employed as screening tests in the PLCO cancer screening trial. Little, however, is known about the amount of time the diagnosis of ovarian cancer is advanced and the accuracy of CA-125 and TVU tests. To investigate this issue, one possibility is to use the available methods in the literature (Auvinen, A. et al. 2009, Cong, Shen and Miller 2005, Shen and Zelen 1999, Shen and Huang 2005, Straatman et al. 1997). However, these methods are largely based on certain distributional assumptions on sojourn time or lead time and 100% specificity, equivalently, the zero false positive rate. It is clear that the data from PLCO cancer screening trial do not support a zero false positive rate. Therefore, it would be interesting to generalize these commonly used methods by considering specificity also a parameter and to estimate mean sojourn time/mean lead time, sensitivity and specificity simultaneously. In this project, we first generalize the method developed by Shen and Huang (2005) without assuming 100% specificity and then apply the new method to ovarian component of PLCO cancer screening trial. For the sake of comparison, we also use Shen and Huang's (2005) method to the same data set.