Threshold Regression Methodology for Cancer Risk Assessment

点击翻译按钮获取中文摘要

DESCRIPTION (provided by applicant): Building on preliminary work, we propose to develop a new statistical methodology for epidemiologic studies, called Threshold Regression (TR), that will facilitate and enrich the assessment of health risks associated with occupational exposures. Threshold regression is based on the plausible hypothesis that the latent health status of a subject is a random process that is affected by disease and ultimately results in death or another adverse endpoint when the subject's latent health status falls below a critical threshold value. The methodology captures effects of occupational exposure in a disease progression scale that acts as a modified time scale for the health status process. The advantages of our proposed methodology over existing analytic methods used to assess disease risk associated with occupational exposures are (a) it can be applied to both quantitative and semi-quantitative exposure data; (b) unlike traditional survival methods that depend heavily on the assumption of proportional hazards, the proposed model does not depend on this assumption; (c) it can take account of multiple competing health risks in a natural manner; (d) it provides new types of graphs that display survival trends from new perspectives. This application addresses Risk Assessment Methods listed in the "Research Tools and Approache's category of NIOSH/NORA Priority Research Areas. This project is aimed at contributing to applied quantitative methods and statistical research that can model the stochastic relationship between work-related environmental exposure and cancer risk, The model can be used for elucidation of susceptibility factors associated with cancer risk in individuals and population subgroups. Specific aims are: 1. Develop threshold regression into a sound practical tool for occupational risk assessment. 2. Quantify hazards and the dose-response relationship. 3. Apply the methodology to two large occupational studies. 4. Develop requisite computational software tools.