A0706
Title: Latent archetypes of the spatial patterns of cancer
Authors: Marcos Prates - Universidade Federal de Minas Gerais (Brazil) [presenting]
Thais Pacheco - University College Dublin (Ireland)
Renato Assuncao - Universidade Federal de Minas Gerais (Brazil)
Abstract: The cancer atlas edited by several countries is the main resource for the analysis of the geographic variation of cancer risk. Correlating the observed spatial patterns with known or hypothesized risk factors is time-consuming work for epidemiologists who need to deal with each cancer separately, breaking down the patterns according to sex and race. The recent literature has proposed studying more than one cancer simultaneously while looking for common spatial risk factors. However, this previous study has two constraints: they consider only a very small (2-4) number of cancers previously known to share risk factors. An exploratory method is proposed to search for latent spatial risk factors of a large number of supposedly unrelated cancers. The method is based on the singular value decomposition and non-negative matrix factorization; it is computationally efficient, scaling easily with the number of regions and cancers. A simulation study is carried out to evaluate the method's performance, and it is applied to cancer atlas from the USA, England, France, Australia, Spain, and Brazil. It is concluded that with very few latent maps, which can represent a reduction of up to 90\% of atlas maps, most of the spatial variability is conserved. The hope is that by concentrating on the epidemiological analysis of these few latent maps, a substantial amount of work is saved, and, at the same time, high-level explanations affecting many cancers can be simultaneously reached.
