Bayesian analysis of spatio-temporal patterns in colorectal cancer mortality in Chile: a study linking national quality of life and mortality data

Colorectal cancer (CRC) is the second leading cause of cancer death globally, surpassed only by lung cancer, representing a significant public health challenge in Chile due to its biopsychosocial impact. This study analyzed standardized mortality ratios (SMR) for CRC using mortality data and the National Quality of Life Survey (ENCAVI) for the years 2000, 2006, and 2015. Bayesian spatio-temporal models were developed employing the Integrated Nested Laplace Approximation (INLA) approach to identify regions with unusual relative risks and associated quality of life factors. The results reveal marked spatio-temporal heterogeneity in CRC mortality across Chile. As part of the modelling approach, breakfast consumption, marital status, educational attainment, overall life satisfaction, dietary and employment-related contributed to explaining variation in SMR levels, and to characterising spatio-temporal patterns in CRC mortality. Spatially, residual variation is dominated by region-specific heterogeneity rather than structured spatial dependence, with persistently elevated CRC mortality observed in regions such as Valparaíso and time-varying increases in northern and southern areas.