PROVIDED.Cancer surveillance plays an essential role in cancer prevention and intervention. This proposal developsnew statistical methods that deal with complex data-related issues in cancer surveillance studies. Inparticular, the specific aims are motivated by problems encountered in surveillance studies that monitorcancer mortality and geographical patterns, and that study disproportionate disease burden on particularpopulations and important risk factors. We plan to(1) develop new methods to analyze the cross-relationship matrix of the change trends [e.g. the annual ratechanges (ARC)] in mortality or incidence on multiple cancer sites for the period of 1969-2004;(2) propose disease clustering/surveillance methods for outcomes subject to censoring;(3) propose a new test statistic for spatial clustering detection that incorporates latency distributions thatare associated with cancer, and studies whether disease clustering patterns differ according to geneticcharacteristics;(4) develop and evaluate a spatio-temporal hidden Markov model for disease surveillance based on regionspecificcounts of disease incidence;(5) develop efficient algorithms and user-friendly statistical software that implement these methods with thegoal of disseminating them to health science researchers.The proposed methods will be applied to several cancer and environmental health projects that theinvestigators have been involved in, namely, the SEER cancer mortality data, the SEER prostate cancerincidence data and the Taiwan Leukemia data. The methods will allow practitioners as well as health carepolicy makers to better understand the change trends of cancer deaths/incidence and the cross-relationshipof these trends for the purpose of planning and resource allocation. The methods will also help revealdisproportionate disease burden on at-risk populations and identify important risk factors, including geneticsusceptibility. The surveillance methods proposed in this project are linked to the spatio-temporal methodsproposed in Project 1, and the regularized regression models proposed in this project are related to thevariable selection methods proposed in Project 3. In addition, all three projects have a common theme of theanalysis of high-dimensional observational study data, and all projects will generate statistical methods andcomputational approaches that will inform those developed in the others.
Showing the most recent 10 out of 192 publications