CMStatistics 2022: Start Registration
View Submission - CMStatistics
Title: A mixture model for estimating the risk of prostate cancer progression in active surveillance Authors:  Yibai Zhao - Fred Hutch Cancer Center (United States) [presenting]
Abstract: Active surveillance has become a widely accepted management strategy to reduce overtreatment for low-risk prostate cancer patients. Prostate cancer is monitored through biopsies at scheduled visits to detect cancer progression to high risk, and the time to progression is left-censored. Because of biopsy misclassification, there are additional challenges to address. Individuals with high-grade cancer at the time of diagnosis (i.e., prevalent cases) may undergo active surveillance due to the imperfect sensitivity of biopsy, and some low-risk cancers may remain indolent indefinitely. In addition to the heterogeneity of cancers, observed data are subject to misclassification at each visit. We assume a mixture model for progressive and indolent cancers as well as the prevalent cases where the proportional hazards model incorporates the effect of either time-independent or time-varying covariates on cancer progression. We propose a semiparametric likelihood-based approach to handle interval-censored observations while accounting for the misclassification rates of biopsy. We conduct simulation studies to investigate the performance of the proposed approach under various settings. We apply the proposed approach to the Canary Prostate Active Surveillance Study to evaluate potential risk factors for cancer progression and to estimate the indolent fraction under a range of biopsy sensitivity rates.