Exploring Uncertainty in Canine Cancer Data Sources Through Dasymetric Refinement

Abstract

In spite of the potentially groundbreaking environmental sentinel applications, studies of canine cancer data sources are often limited due to undercounting of cancer cases. This source of uncertainty might be further amplified through the process of spatial data aggregation, manifested as part of the modifiable areal unit problem (MAUP). In this study, we explore potential explanatory factors for canine cancer incidence retrieved from the Swiss Canine Cancer Registry (SCCR) in a regression modeling framework. In doing so, we also evaluate differences in statistical performance and associations resulting from a dasymetric refinement of municipal units to their portion of residential land. Our findings document severe underascertainment of cancer cases in the SCCR, which we linked to specific demographic characteristics and reduced use of veterinary care. These explanatory factors result in improved statistical performance when computed using dasymetrically refined units. This suggests that dasymetric mapping should be further tested in geographic correlation studies of canine cancer incidence and in future comparative studies involving human cancers.

Keywords: cancer underascertainment; canine cancer incidence; dasymetric refinement; geographic correlation studies; spatial data aggregation.

Figure 1

A framework for dasymetric refinement of population data within residential land. Example of binary dasymetric refinement of population data within residential land — (A) population density computed within administrative units is refined based on (B) the location of residential land to recompute (C) population density within dasymetrically refined units.

Figure 2

Effects of dasymetric refinement of the municipal units — changes of spatial extent (part of residential land) and centroid displacements (shift to the centroid of the residential land). The data is classified according to the fixed classes classification method.

Figure 3

Human population density indicators resulting from the two enumeration types — (A) municipal units and (B) dasymetrically refined units. For better visual comparison, the indicator recomputed after dasymetric refinement is also presented in a choropleth fashion. The data is classified according to the quantile classification method applied to the dasymetrically refined units.

Figure 4

Distance to veterinary care indicators resulting from the two enumeration types — (A) municipal units and (B) dasymetrically refined units. For better visual comparison, the indicator recomputed after dasymetric refinement is also presented in a choropleth fashion. The data is classified according to the quantile classification method applied to the dasymetrically refined units.

Figure 5

Observed canine cancer incidence rates across Swiss municipalities in 2008. The data is classified according to the quantile classification method and mapped using dasymetrically refined units.