Geographical Disparities in Mortality Rates: Spatial Data Mining and Bayesian Hierarchical Modeling

  • Massimo Bilancia
  • Giusi Graziano
  • Giacomo Demarinis
Part of the Contributions to Statistics book series (CONTRIB.STAT.)


Achieving health equity has been identified as a major international challenge since the 1978 declaration of Alma Ata. Disease risk maps provide important clues concerning many aspects of health equity, such as etiology risk factors involved by occupational and environmental exposures, as well as gender-related and socioeconomic inequalities. This explains why epidemiological disease investigation should always include an assessment of the spatial variation of disease risk, with the objective of producing a representation of important spatial effects while removing any noise. Bearing in mind this goal, this review covers basic and more advanced aspects of Bayesian models for disease mapping, and methods to analyze whether the spatial distribution of the disease risk closely follows that of underlying population at risk, or there exist some nonrandom local patterns (disease clusters) which may suggest a further explanation for disease etiology. We provide a practical illustration by analyzing the spatial distribution of liver cancer mortality in Apulia, Italy, during the 2000–2005 quinquennial. (Massimo Bilancia wrote Sects. 1.1.2, 1.1.4, 1.1.6, 1.2.1, 1.2.3, 1.2.5. Giusi Graziano wrote Sects. 1.1.1, 1.1.3, 1.1.5, 1.2.2, 1.2.4, 1.2.6. Giacomo Demarinis wrote the software for data analysis. Section 1.3 was written jointly. The three authors read and approved the final manuscript. We wish to thank Maria Rosa Debellis, Department of Neuroscience and Sense Organs, University of Bari, Italy, and Claudia Monte PhD, Department of Physics, University of Bari, Italy, for their valuable support.)


Bayesian statistics Besag–York–Mollié model Disease cluster detection Disease mapping Spatial scan statistic 


  1. 1.
    Banerjee, S., Carlin, B.P., Gelfand, A.E.: Hierarchical Modeling and Analysis for Spatial Data. Chapman & Hall/CRC, Boca Raton (2004). ISBN 978-0-203-48780-8MATHGoogle Scholar
  2. 2.
    Besag, J.E., York, J.C., Mollié, A.: Bayesian image restoration with two applications in spatial statistics (with discussion). Ann. Inst. Stat. Math. 43, 1–59 (1991). doi: 10.1007/BF00116466 MATHCrossRefGoogle Scholar
  3. 3.
    Bernardinelli, L., Pascutto, C., Best, N.G., Gilks, W.R.: Disease mapping with errors in covariates. Stat. Med. 16, 741–752 (1997). doi:10.1002/(SICI)1097-0258(19970415)16:7<741::AID-SIM501>3.0.CO;2-1CrossRefGoogle Scholar
  4. 4.
    Besag, J., Kooperberg, C.: On conditional and intrinsic autoregression. Biometrika 82, 733–746 (1995). MathSciNetMATHGoogle Scholar
  5. 5.
    Bilancia, M., Demarinis, G.: Bayesian scanning of spatial disease rates with INLA (submitted)Google Scholar
  6. 6.
    Browne, W., Draper, D.: A comparison of Bayesian and likelihood-based methods for fitting multilevel models. Bayesian Anal. 1(3), 473–514 (2006). doi: 10.1214/06-BA117 MathSciNetGoogle Scholar
  7. 7.
    Caranci, N., Costa, G.: Un indice di deprivazione a livello aggregato da utilizzare su scala nazionale: giustificazioni e composizione dell”indice. In: Costa, G., Cislaghi, C., Caranci, N. (eds) Disuguaglianze sociali di salute. Problemi di definizione e di misura. “Salute e Società” VIII, 1 (2009). doi: 10.3280/SES2009-001006
  8. 8.
    Carlin, B.P., Louis, T.A.: Bayesian Methods for Data Analysis. Chapman & Hall/CRC, Boca Raton (2008). ISBN 978-1-58488-697-6MATHGoogle Scholar
  9. 9.
    Clayton, D., Kaldor, J.: Empirical Bayes estimates of age-standardized relative risks for use in disease mapping. Biometrics 43(3), 671–681 (1987). CrossRefGoogle Scholar
  10. 10.
    Cowles, M.K., Carlin, B.P.: Markov Chain Monte Carlo convergence diagnostics: a comparative review. J. Am. Stat. Assoc. 91, 883–904 (1996). MathSciNetMATHCrossRefGoogle Scholar
  11. 11.
    Cramb, S., Mengersen, K.L., Baade, P.: Developing the atlas of cancer in Queensland: methodological issues. Int. J. Health Geogr. 10, 9 (2011). doi: 10.1186/1476-072X-10-9 CrossRefGoogle Scholar
  12. 12.
    Dabney, A.R., Wakefiled, J.C.: Issues in the mapping of two disease. Stat. Methods Med. Res. 14, 1–30 (2005). doi: 10.1191/0962280205sm340oa CrossRefGoogle Scholar
  13. 13.
    Gelfand, A.E., Sahu, S.K.: Identifiability, improper priors and Gibbs sampling for generalized linear models. JASA 94, 247–253 (1999). MathSciNetMATHGoogle Scholar
  14. 14.
    Gelman, A.: Prior distributions for variance parameters in hierarchical models (comment on article by Browne and Draper). Bayesian Anal. 1(3), 515–534 (2006). doi: 10.1214/06-BA117A MathSciNetGoogle Scholar
  15. 15.
    Ghosh, M., Natarajan, K., Waller, L.A., Kin, D.: Hierarchical Bayes GLMs for the analysis of spatial data: an application to disease mapping. J. Stat. Plan. Inference 75(2), 305–318 (1999). doi: 10.1016/S0378-3758(98)00150-5 MATHCrossRefGoogle Scholar
  16. 16.
    Gómez-Rubio, V., Ferrándiz-Ferragud, J., López-Quílez, A.: Detecting clusters of disease with R. J. Geogr. Syst. 7, 189–206 (2005). doi: 10.1007/s10109-005-0156-5 CrossRefGoogle Scholar
  17. 17.
    Kulldorff, M., Nagarwalla, N.: Spatial disease clusters: detection and inference. Stat. Med. 14, 799–810 (1995). doi: 10.1002/sim.4780140809 CrossRefGoogle Scholar
  18. 18.
    Kulldorff, M.: A spatial scan statistic. Commun. Stat. Theory Methods 26(6), 1481–1496 (1997). doi: 10.1080/03610929708831995 MathSciNetMATHCrossRefGoogle Scholar
  19. 19.
    La Vecchia, C., Negri, E., Decarli, A., et al.: Risk factors for hepatocellular carcinoma in Northern Italy. Int. J. Cancer 42, 872–876 (1988)CrossRefGoogle Scholar
  20. 20.
    Levi, F., Lucchini, F., Negri, E., Boyle, P., La Vecchia, C.: Cancer mortality in Europe, 1995–1999, and an overview of trends since 1960. Int. J. Cancer 110, 155–169 (2004). doi: 10.1002/ijc.20097 CrossRefGoogle Scholar
  21. 21.
    Loh, J.M., Zhu, Z.: Accounting for spatial correlation in the scan statistics. Ann. Appl. Stat. 1(2), 560–584 (2007). doi: 10.1214/07-AOAS129 MathSciNetMATHCrossRefGoogle Scholar
  22. 22.
    Marshall, R.J.: Mapping disease and mortality rates using empirical Bayes estimators. J. R. Stat. Soc. C Appl. Stat. 40(2), 283–294 (1991). MATHGoogle Scholar
  23. 23.
    McGlynn, K.A., Tsao, L., Hsing, A.W., Devesa, S.S., Fraumeni Jr., J.F.: International trends and patterns of primary liver cancer. Int. J. Cancer 94, 290–296 (2001). doi: 10.1002/ijc.1456 CrossRefGoogle Scholar
  24. 24.
    Mollié, A.: Bayesian mapping of Hodgkin’s disease in France. In: Elliot, P., Wakefield, J., Best, N., Briggs, D. (eds.) Spatial Epidemiology Methods and Applications, pp. 267–285. Oxford University Press, Oxford (2001). ISBN 978-0198515326CrossRefGoogle Scholar
  25. 25.
    Ocaña-Riola, R.: Common errors in disease mapping. Geospat. Health 4(2), 139–154 (2010). Google Scholar
  26. 26.
    Osservatorio Epidemiologico Regionale Puglia: Atlante delle cause di Morte della Regione Puglia. Anni 2000–2005 (2008).
  27. 27.
    Parkin, D.M., Bray, F., Ferlay, J., Pisani, P.: Estimating the world cancer burden: Globocan 2000. Int. J. Cancer 94, 153–156 (2001). doi: 10.1002/ijc.1440 CrossRefGoogle Scholar
  28. 28.
    Pericchi, L.R.: Model selection and hypothesis testing based on objective probabilities and Bayes factors. In: Dey, D.K., Rao, C.R. (eds.) Handbook of Statistics 25. Bayesian Thinking: Modeling and Computation, pp. 115–149. Amsterdam, Elsevier (2005). ISBN 9780444515391CrossRefGoogle Scholar
  29. 29.
    Pfeiffer, D.U., Robinson, T.U., Stevenson, M., Stevens, K.B., Rogers, D.J., Clements, A.C.A.: Spatial Analysis in Epidemiology. Oxford University Press, Oxford (2008). ISBN 978-0-19-85098-82MATHCrossRefGoogle Scholar
  30. 30.
    Potthoff, R.F., Whittinghill, M.: Testing for homogeneity: I. The binomial and multinomial distribution. Biometrika 53, 167–182 (1966). MathSciNetGoogle Scholar
  31. 31.
    Potthoff, R.F., Whittinghill, M.: Testing for homogeneity: II. The Poisson distribution. Biometrika 53, 183–190 (1966). MathSciNetGoogle Scholar
  32. 32.
    Rao, C.R.: Advanced Statistical Methods in Biometric Research. Wiley, New York (1952)MATHGoogle Scholar
  33. 33.
    Rue, H., Held, L.: Gaussian Markov Random Fields. Theory and Applications. Chapman & Hall/CRC, Boca Raton (2005). ISBN 978-1-58488-432-3MATHCrossRefGoogle Scholar
  34. 34.
    Rue, H., Martino, S., Chopin, N.: Approximate Bayesian inference for latent Gaussian models using Integrated Nested Laplace approximations (with discussion). J. R. Stat. Soc. B 71, 319–392 (2009). doi: 10.1111/j.1467-9868.2008.00700.x MathSciNetMATHCrossRefGoogle Scholar
  35. 35.
    Richardson, S., Guihenneuc, C., Lasserre, V.: Spatial linear models with autocorrelated error structure. Statistician 41, 539–557 (1992). CrossRefGoogle Scholar
  36. 36.
    Rogerson, P.A.: The detection of clusters using a spatial version of the chi-square goodness-of-fit statistic. Geogr. Anal. 31(1), 130–147 (1999). doi: 10.1111/j.1538-4632.1999.tb00973.x Google Scholar
  37. 37.
    Spiegelhalter, D.J., Best, N.G., Carlin, B.P., Linde, A.: Bayesian measures of model complexity and fit (with discussion). J. R. Stat. Soc. B 64, 583–639 (2002). doi: 10.1111/1467-9868.00353 MATHCrossRefGoogle Scholar
  38. 38.
    Strachan, R.W., van Dijk, H.K.: Divergent priors with well defined Bayes factors. Tinbergen Institute Discussion Paper, TI 2011-006/4 (2011).
  39. 39.
    Tabor, E., Kobayashi, K.: Hepatitis C virus, a causative infectious agent of non-A, non-B hepatitis: prevalence and structure – summary of a Conference on Hepatitis C virus as a cause of hepatocellular carcinoma. J. Natl. Cancer Inst. 84, 86–90 (1992). doi: 10.1093/jnci/84.2.86 CrossRefGoogle Scholar
  40. 40.
    Tango, T.: A class of test for detecting ‘general’ and ‘focused’ clustering of rare diseases. Stat. Med. 14, 2323–2334 (1995). doi: 10.1002/sim.4780142105 CrossRefGoogle Scholar
  41. 41.
    Tango, T.: A test for spatial disease clustering adjusted for multiple testing. Stat. Med. 19, 191–204 (1995). doi:10.1002/(SICI)1097-0258(20000130)19:2<191::AID-SIM281>3.0.CO;2-QCrossRefGoogle Scholar
  42. 42.
    Vidal Roidero, C.L., Lawson, A.B..: An evaluation of edge effects in disease map modeling. Comput. Stat. Data Anal. 49, 45–62 (2005). doi: 10.1016/j.csda.2004.05.012 CrossRefGoogle Scholar
  43. 43.
    Wakefield, J.: Disease mapping and spatial regression with count data. Biostatistics 8(2), 158–183 (2007). doi: 10.1093/biostatistics/kxl008 MathSciNetMATHCrossRefGoogle Scholar
  44. 44.
    Waller, L.A., Carlin, B.P., Xia, H., Gelfand, A.E.: Hierarchical spatiotemporal mapping of disease rates. J. Am. Stat. Assoc. 92, 607–617 (1997). MATHCrossRefGoogle Scholar
  45. 45.
    Waller, L.A., Gotway, C.A.: Applied Spatial Statistics for Public Health Data. Wiley, New Jersey (2004). ISBN 0-471-38771-1MATHCrossRefGoogle Scholar
  46. 46.
    Yiannakoulias, N., Rosychuk, R.J., Hodgson, J.: Adaptations for finding irregularly shaped disease clusters. Int. J. Health Geogr. 6, 28 (2007). doi: 10.1186/1476-072X-6-28 CrossRefGoogle Scholar
  47. 47.
    Yu, M.C., Mack, T., Hanisch, R., et al.: Hepatitis, alcohol consumption, cigarette smoking, and hepatocellular carcinoma in Los Angeles. Cancer Res. 43, 6077–6079 (1983). Google Scholar
  48. 48.
    Zhang, T., Zhang, Z., Lin, G.: Spatial scan statistics with overdispersion. Stat. Med. 13;31(8):762–774 (2012). doi: 10.1002/sim.4404 Google Scholar

Copyright information

© Springer-Verlag Italia 2013

Authors and Affiliations

  • Massimo Bilancia
    • 1
  • Giusi Graziano
    • 2
  • Giacomo Demarinis
    • 1
  1. 1.Dipartimento di Scienze Statistiche “Carlo Cecchi”University of Bari “Aldo Moro”BariItaly
  2. 2.Laboratory of Lipid Metabolism and CancerConsorzio Mario Negri SudSanta Maria Imbaro (CH)Italy

Personalised recommendations