A method for spatial analysis of risk in a population-based case-control study

Abstract

Spatial distributions of disease occurrence and risk have traditionally served as a tool for identifying exposures of public health concern. Current software for manipulating geographic data (GIS) now allows many kinds of analyses not feasible before. This paper presents a method for producing a "picture" of disease risks based on residential history data from a population based case-control study. We illustrate the method using geographically coded data on individual-level risk factors, such as age and smoking, from a cancer study of the Upper Cape Cod region of Massachusetts for 1983-1986. Our results show the association between lung cancer and residential location as an indicator of exposure. Crude and adjusted odds ratios were estimated by adaptive rate stabilization and mapped using kriging as an interpolation method to examine the risk of lung cancer in the region. The crude and adjusted surfaces for various smoothing parameters were compared to identify areas of increased lung cancer not explained by standard risk factors. Such spatial patterns of disease risk may provide clues to exposures of importance or confirm associations with previously suspected exposures.