Apports d’une méthode de fouille de données pour la détection des cancers du sein incidents dans les données du programme de médicalisation des systèmes d’information

  • Christophe Goetz
  • Aurélien Zang
  • le groupe ONC-EPI
  • Nicolas JayEmail author
Part of the Informatique et Santé book series (INFORMATIQUE, volume 1)


The objective of this work was to assess the interest of a data mining approach to detect incident breast cancer cases in medico administrative data. Data from the French casemix system (PMSI) were linked with the Isère cancer registry, which was the gold standard to define incident breast cancer. Formal Concept Analysis (FCA) was used to compute combinations of attribute values in the PMSI that could further define algorithm of detection of incident breast cancer. FCA allowed to automatically evaluate any possible combination of attribute values in terms of sensibility and Positive Predictive Value. This method can help experts in quality assessment of medico-economical databases as epidemiological tools.


PMSI Breast cancer Incidence Data mining Formal concept analysis 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Levi F, Bosetti C, Lucchini F, Negri E, La Vecchia C. Monitoring the decrease in breast cancer mortality in Europe. Eur J Cancer Prev 2005; 14: 497–502CrossRefGoogle Scholar
  2. [2]
    Stewart B, Kleihues P. World Cancer Report. Oxford, Oxford University Press: 2003Google Scholar
  3. [3]
    Fetter RB, Shin Y, Freeman JL, Averill RF, Thompson JD. Case mix definition by diagnosis-related groups. Med Care 1980; 18: 1–53Google Scholar
  4. [4]
    Dussaucy A, Viel JF, Mulin B, Euvrard J. The framework Prospective Payment Information Systems: bias, sources of errors and consequences. Rev Epidemiol Sante Publique 1994; 42(4): 345–58Google Scholar
  5. [5]
    Baron JA, Lu-Yao G, Barrett J et al. Internal validation of Medicare claims data. Epidemiology 1994; 5: 541–4CrossRefGoogle Scholar
  6. [6]
    Couris CM, Schott AM, Morgon E, Ecochard R, Colin C. A literature review to assess the use of claims databases in identifying cancer incident cases. Health Services and Outcomes Research Methodology 2003; 4: 49–63CrossRefGoogle Scholar
  7. [7]
    Freeman JL, Zhang D, Freeman DH, Goodwin JS. An approach to identifying incident breast cancer cases using Medicare claims data. J Clin Epidemiol 2000; 53: 605–14CrossRefGoogle Scholar
  8. [8]
    Nattinger AB, Laud PW, Bajorunaite R, Sparapani RA, Freeman JL. An algorithm for the use of Medicare claims data to identify women with incident breast cancer. Health Serv Res 2004; 39: 1733–49CrossRefGoogle Scholar
  9. [9]
    Couris CM, Colin C, Rabilloud M, Schott AM, Ecochard R. Method of correction to assess the number of hospitalized incident breast cancer cases based on claims databases. J Clin Epidemiol 2002; 55: 386–91CrossRefGoogle Scholar
  10. [10]
    Couris CM, Forêt-Dodelin C, Rabilloud M, Colin C, Bobin JY, Dargent D, Raudrant D, Schott AM. Sensitivity and specificity of two methods used to identify incident breast cancer in specialized units using claims databases. Rev Epidemiol Sante Publique 2004; 52: 151–60CrossRefGoogle Scholar
  11. [11]
    Gold HT, Do HT. Evaluation of three algorithms to identify incident breast cancer in Medicare claims data. Health Serv Res 2007; 42: 2056–69CrossRefGoogle Scholar
  12. [12]
    Remontet L, Mitton N, Couris CM, Iwaz J, Gomez F, Olive F, Polazzi S, Schott AM Trombert B, Bossard N, Colonna M. Is it possible to estimate the incidence of breast cancer from medico-administrative databases? Eur J Epidemiol 2008; 23: 681–8CrossRefGoogle Scholar
  13. [13]
    Baldi I, Vicari P, Di Cuonzo D, Zanetti R, Pagano E, Rosato R, Sacerdote C, Segnan N, Merletti F, Ciccone G. A high positive predictive value algorithm using hospital administrative data identified incident cancer cases. J Clin Epidemiol 2008; 61: 373–9CrossRefGoogle Scholar
  14. [14]
    Couris CM, Polazzi S, Olive F, Remontet L, Bossard N, Gomez F, Schott AM, Mitton N, Colonna M, Trombert B. Breast cancer incidence using administrative data: correction with sensitivity and specificity. J Clin Epidemiol 2009; 62: 660–6CrossRefGoogle Scholar
  15. [15]
    Fayyad U, Piatetsky-Shapiro G, Smyth P. The kdd process for extracting useful knowledge from volumes of data. Communications ACM 1996; 39: 27–34CrossRefGoogle Scholar
  16. [16]
    Curtis JR, Cheng H, Delzell E, Fram D, Kilgore M, Saag K, Yun H, Dumouchel W. Adaptation of Bayesian data mining algorithms to longitudinal claims data: coxib safety as an example. Med Care 2008; 46: 969–75CrossRefGoogle Scholar
  17. [17]
    Trifirò G, Pariente A, Coloma PM, Kors JA, Polimeni G, Miremont-Salamé G, Catania MA, Salvo F, David A, Moore N, Caputi AP, Sturkenboom M, Molokhia M, Hippisley-Cox J, Acedo CD, van der Lei J, Fourrier-Reglat A; EU-ADR group. Data mining on electronic health record databases for signal detection in pharmacovigilance: which events to monitor? Pharmacoepidemiol Drug Saf 2009; 18(12): 1176–84CrossRefGoogle Scholar
  18. [18]
    Jay N, Napoli A, Kohler F. Cancer patient flows discovery in DRG databases. Stud Health Technol Inform 2006; 124: 725–30Google Scholar
  19. [19]
    Quantin C, Fassa M, Coatrieux G, Riandey B, Trouessin G, Allaert FA. Linking anonymous databases for national and international multicenter epidemiological studies: a cryptographic algorithm. Rev Epidemiol Sante Publique 2009; 57: 33–9CrossRefGoogle Scholar
  20. [20]
    Wille R. Formal Concept Analysis as Mathematical Theory of Concepts and Concept Hierarchies. LNCS 2005; 3626: 1–33Google Scholar
  21. [21]
    Key TJ, Verkasalo PK, Banks E. Epidemiology of breast cancer. Lancet Oncol 2001; 2: 133–40CrossRefGoogle Scholar
  22. [22]
    Comité national de pilotage. Cahier des charges du programme national de dépistage systématique du cancer du sein. DGS 1994 — mise à jour: janvier 1996Google Scholar

Copyright information

© Springer-Verlag France 2011

Authors and Affiliations

  • Christophe Goetz
    • 1
  • Aurélien Zang
    • 1
  • le groupe ONC-EPI
    • 2
  • Nicolas Jay
    • 1
    • 3
    Email author
  1. 1.Observatoire des cancers en région Rhône-AlpesLyonFrance
  2. 2.Laboratoire SPI-EAOFaculté de médecine de NancyVandœuvre-lès-NancyFrance
  3. 3.Campus scientifiqueOrpailleur, LORIAVandœuvre-lès-Nancy CedexFrance

Personalised recommendations