Our current area of work entails spatial and spatio-temporal modelling for data driven problems in environmental epidemiology; in particular:
Environment and health
Methods for spatially misaligned environmental data
We work on statistical methods to improve the characterisation of air pollution. In particular, we are developing Bayesian models to integrate data sources coming from measurements as well as numerical model outputs or satellites and accounting for misalignment that naturally occur when dealing with separate sources. We are also extending the framework to a multi-pollutant approach.
Forlani C., Bhatt S., Cameletti M., Krainski E., Blangiardo M., A Joint Bayesian Space-Time Model to Integrate Spatially Misaligned Air Pollution Data in R-INLA, under review.
Cameletti M., Gomez-Rubio V., Blangiardo M., 2019, Bayesian modeling for spatially misaligned health and air pollution data through the INLA-SPDE approach, Spatial Statistics, Vol: 31, ISSN: 2211-6753.
Blangiardo M., Finazzi F., Cameletti M., 2016, Two-stage Bayesian model to evaluate the effect of air pollution on chronic respiratory diseases using drug prescriptions, Spatial and Spatio-temporal Epidemiology, Vol: 18, Pages: 1-12, ISSN: 1877-5853.
Methods to investigate the effects of multiple air pollution constituents
We are focusing on several methodological aspects related to the link between multiple metrics of air pollution and health.
Source apportionment of ambient particle matter, which uses Bayesian nonparametric processes with dependence on dynamic factors (e.g. wind speed and direction) to model the underlying spatial or temporal structure and the distribution of contaminants to identify sources. We then assess the link between the apportioned sources and health outcomes in order to move from the standard epidemiological models where total PM is considered to a source-contribution evaluation, which is more relevant for decision making.
Two-component Bayesian hierarchical model for multiple air pollutants, where the pollutant model to estimate the "true" concentrations is linked to the health outcome in a time-series perspective.
Source apportionment of daily airborne particulate matter components in London (2011-2012) via kernel stick breaking process: the clustering solution describes different aerosol types.
Blangiardo M, Pirani M, Kanapka L, Hansell A, Fuller G., 2019, A hierarchical modelling approach to assess multi pollutant effects in time-series studies, PLoS ONE, Vol: 14, ISSN: 1932-6203.
Pirani M, Gulliver J, Fuller GW, Blangiardo M., 2013, Bayesian spatiotemporal modelling for the assessment of short-term exposure to particle pollution in urban areas, Journal of Exposure Science and Environmental Epidemiology, Vol: 24, Pages: 319-327, ISSN: 1559-064X.
Pirani M, Best N, Blangiardo M, Liverani S, Atkinson RW, Fuller GW., 2015, Analysing the health effects of simultaneous exposure to physical and chemical properties of airborne particles, Environment International, Vol: 79, Pages: 56-64, ISSN: 1873-6750.
Methods for residual confounding adjustment in small area studies
Within a Bayesian hierarchical framework, we work on integration techniques to combine individual- and ecological-level data to adjust for residual confounding in an area-referenced environmental health studies through summary indexes such as the propensity score.
Wang Y, Pirani M, Hansell A, Richardson S, Blangiardo M., 2019, Using ecological propensity score to adjust for missing confounders in small area studies, Biostatistics, Vol: 20, Pages: 1-16, ISSN: 1465-4644
Pirani M., Mason A., Hansell A., Richardson S., Blangiardo M., A flexible hierarchical framework for improving inference in area-referenced environmental health studies, Biometrical Journal, Vol:62, Pages: 1650-1669
Temperature and Climate Change
We are developing spatiotemporal models to quantify the temperature related respiratory disease burden in England and Wales. In particular, we are running simulation studies and comparing commonly used approaches for disease mapping and spatial regression to quantify the effect of temperature in respiratory hospital admissions. We are extending these models to incorporate hospitalisation and drug prescription costs, while propagating the uncertainty across the models. The main goal of this project is to use the different temperature trajectories, based on the different representative concentration pathways, and project the future temperature related respiratory disease burden in England and Wales. We will fully integrate our results in a Web application. The entire modelling framework will be available online and easily extended to other drivers of global disease burden.
Within a collaborative project with the University of São Paulo (School of Public Health) and the contribution of the University of Toronto (Dep. of Statistical Sciences), we are developing spatio-temporal methods for understanding the interrelations between climate change, local environmental conditions and arboviral disease dynamics in Brazil and the synchrony that these systems express.
Bennett J., Blangiardo M., Fecht D., Elliott P., Ezzati M., 2014, Vulnerability to the mortality effects of warm temperature in the districts of England and Wales, Nature Climate Change, Vol: 4, Pages: 269-273, ISSN: 1758-678X.
Surveillance and Clustering
We develop spatio-temporal disease mapping and surveillance models for chronic disease epidemiology, focusing on the detection of areas characterised by unusual trends.
Recently we have been focusing on life expectancy trends at the local authority level, in collaboration with Public Health England.
Blangiardo M., Boulieri A., Diggle P., Piel F., Shaddick G., Elliott P, Advances in spatio-temporal models for non-communicable disease surveillance, International Journal of Epidemiology, ISSN: 1464-3685.
Boulieri A., Bennett J., Blangiardo M., 2018, A Bayesian mixture modelling approach for public health surveillance, Biostatistics, ISSN: 1465-4644.
Boulieri A., Blangiardo M., Hansell A., 2016, Investigating trends in asthma and COPD through multiple data sources: a small area study, Spatial and Spatio-temporal Epidemiology, Vol: 19, Pages: 28-36, ISSN: 1877-5853.