The long-term objective of this research project is to develop new statistical methodology for the design and analysis of cancer screening trials. Our major efforts will be directed toward the development of statistical tools to better understand the dynamic nature of screening for chronic diseases, to assess the survival benefit due to screening, and to explore the relationship between important qualities specifically, screening modality and disease progression, and age at diagnosis. Early detection of cancer or other chronic diseases has become one of the most effective ways for disease control. However, statistical methods for the design and analysis of cancer screening and related studies are inadequate to explore the full potential of screening programs and to provide satisfactory solutions to many important problems. In the current proposal, we will address the following issues pertaining to early detection trials: (1) Model the effect of age at diagnosis on screening sensitivity; (2) Development methods for quantifying the age effect in the distribution of pre-clinical duration; (3) Construct a non-parametric procedure for estimating the pre-clinical sojourn time distribution; (4) Assess the dependence between two screening modalities in order to design more cost-effective early detection programs; (5) Construct a class of versatile weighted test statistics to assess the survival benefit between screening and control groups with potential gains in power for a wide range of alternatives. The preliminary studies have shown important advantages of the proposed methods which are easy to implement and flexible enough to take into account various practical considerations. Several accessible data sets on breast cancer early detection trials will be utilized to guide the development of, and illustrate, the new methodologies. The operating characteristics of the proposed estimators and test statistics will be verified by simulations. User-friendly computer programs will be developed and made available to the research community. In summary, the proposed research has the potential to increase the efficiency and reduce the cost of future periodic screening trials.
Showing the most recent 10 out of 43 publications
