Flexible Bayesian P-splines for smoothing age-specific spatio-temporal mortality patterns.

In this paper age-space-time models based on one and two-dimensional P-splines with B-spline bases are proposed for smoothing mortality rates, where both fixed relative scale and scale invariant two-dimensional penalties are examined. Model fitting and inference are carried out using integrated nested Laplace approximations, a recent Bayesian technique that speeds up computations compared to McMC methods. The models will be illustrated with Spanish breast cancer mortality data during the period 1985-2010, where a general decline in breast cancer mortality has been observed in Spanish provinces in the last decades. The results reveal that mortality rates for the oldest age groups do not decrease in all provinces.

Age-space-time CAR models in Bayesian disease mapping.

Mortality counts are usually aggregated over age groups assuming similar effects of both time and region, yet the spatio-temporal evolution of cancer mortality rates may depend on changing age structures. In this paper, mortality rates are analyzed by region, time period and age group, and models including space-time, space-age, and age-time interactions are considered. The integrated nested Laplace approximation method, known as INLA, is adopted for model fitting and inference in order to reduce computing time in comparison with Markov chain Monte Carlo (McMC) methods. The methodology provides full posterior distributions of the quantities of interest while avoiding complex simulation techniques. The proposed models are used to analyze prostate cancer mortality data in 50 Spanish provinces over the period 1986-2010. The results reveal a decline in mortality since the late 1990s, particularly in the age group [65,70), probably because of the inclusion of the PSA (prostate-specific antigen) test and better treatment of early-stage disease. The decline is not clearly observed in the oldest age groups. Copyright © 2016 John Wiley & Sons, Ltd.

Projections of cancer mortality risks using spatio-temporal P-spline models.

Cancer mortality risk estimates are essential for planning resource allocation and designing and evaluating cancer prevention and management strategies. However, mortality figures generally become available after a few years, making necessary to develop reliable procedures to provide current and near future mortality risks. In this work, a spatio-temporal P-spline model is used to provide predictions of mortality/incidence counts. The model is appropriate to capture smooth temporal trends and to predict cancer mortality/incidence counts in different regions for future years. The prediction mean squared error of the forecast values as well as an appropriate estimator are derived. Spanish prostate cancer mortality data in the period 1975-2008 will be used to illustrate results with a focus on cancer mortality forecasting in 2009-2011.

[Incidence rate trends for colorectal cancer in Navarre (North of Spain) in the 1990-2005 period]. / Tendencias en las tasas de incidencia de cáncer colorrectal en Navarra en el periodo 1990-2005.

BACKGROUND: In Spain, an increase in the incidence of colorectal cancer (CRC) has been observed in both sexes in recent years, probably due to an improved diagnostic, the westernization of dietary habits, and worse obesity levels, among others factors. In this work, the CRC incidence rate trends in different health areas in Navarre (northern Spain) are studied during the 1990-2005 period. METHODS: An estimated incidence trend curve for each health area and the corresponding confidence bands were obtained for each gender using P-spline models. RESULTS: These results show an increasing trend of CRC in most of the areas in both sexes, being less pronounced in women than in men. In the central area of Pamplona (the capital) a decreasing trend has been observed for men during the period studied. CONCLUSIONS: Primary prevention is the best strategy to change the increasing trend observed in most areas of the province of Navarre. However, a healthy lifestyle has long-term results, so it is important to have an early detection program that would serve as a short-term prevention strategy.

Modelling risks in disease mapping.

In this article, we propose a strategy of analysis of mortality data with the aim of providing a guideline for epidemiologists and public health researchers to choose a reasonable model for estimating mortality (or incidence) risks. Maps displaying the crude mortality rates or ratios are usually misleading because of the instability of the estimators in low populated areas. As an alternative, many smoothing methods have been presented in the literature based on Poisson inference. They account for the extra-Poisson variation (overdispersion), frequently present in the homogeneous Poisson model, by incorporating random effects. Here, we recommend to test for the potential sources of extra-Poisson variation because, depending on them, the models which fit better the data may be different. Overdispersion can be mainly due to spatial autocorrelation, unstructured heterogeneity or to a combination of these two, and also, when studying very rare diseases, it can be due to an excess of zeros in the data. In this article, different situations the analyst may encounter are detailed and appropriate procedures for each case are presented. The alternative models are illustrated using mortality data provided by the Statistical Institute of Navarra, Spain.

The use of mixture models for identifying high risks in disease mapping.

Conventional approaches for estimating risks in disease mapping or mortality studies are based on Poisson inference. Frequently, overdispersion is present and this extra variability is modelled by introducing random effects. In this paper we compare two computationally simple approaches for incorporating random effects: one based on a non-parametric mixture model assuming that the population arises from a discrete mixture of Poisson distributions, and the second using a Poisson-normal mixture model which allows for spatial autocorrelation. The comparison is focused on how well each of these methods identify the regions which have high risks. Such identification is important because policy makers may wish to target regions associated with such extreme risks for financial assistance while epidemiologists may wish to target such regions for further study. The Poisson-normal mixture model is presented from both a frequentist, or empirical Bayes, and a fully Bayesian point of view. We compare results obtained with the parametric and non-parametric models specifically in terms of detecting extreme mortality risks, using infant mortality data of British Columbia, Canada, for the period 1981-1985, breast cancer data from Sardinia, for the period 1983-1987, and Scottish lip cancer data for 1975-1980. However, we also investigate the performance of these models in a simulation study. The key finding is that discrete mixture models seem to be able to locate regions which experience high risks; normal mixture models also work well in this regard, and perform substantially better when spatial autocorrelation is present.

Detecting interaction between random region and fixed age effects in disease mapping.

The purpose of this article is to draw attention to the possible need for inclusion of interaction effects between regions and age groups in mapping studies. We propose a simple model for including such an interaction in order to develop a test for its significance. The assumption of an absence of such interaction effects is a helpful simplifying one. The measure of relative risk related to a particular region becomes easily and neatly summarized. Indeed, such a test seems warranted because it is anticipated that the simple model, which ignores such interaction, as is in common use, may at times be adequate. The test proposed is a score test and hence only requires fitting the simpler model. We illustrate our approaches using mortality data from British Columbia, Canada, over the 5-year period 1985-1989. For this data, the interaction effect between age groups and regions is quite large and significant.