Advertisement

Simulation-Based Episodes of Care Data Synthetization for Chronic Disease Patients

  • David RiañoEmail author
  • Alberto Fernández-Pérez
Conference paper
  • 361 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10096)

Abstract

Primary care studies related to chronic diseases and their treatment use to be based on the analysis of large amounts of episodes of care (EoC) in order to check standard’s compliance, improve protocols, or perform quality and cost studies. In these EoC, data related to the patient condition and treatment are registered along the different encounters between the patient and the health care professionals. However, EoC data analysis is subject to some limitations such as data availability, reliability, and appropriateness, aside of multiple legal issues. Several studies exist to surpass these limitations with software technologies that synthesize realistic clinical data. Two are the main approaches: data-driven, or the construction of quantitative models from data about retrospective clinical cases, and knowledge-driven, or the construction of qualitative (semantic) models from the accumulation of medical evidences.

These approaches have some limitations that we aimed to surpass with a computer-based virtual-patient simulation system to synthesize EoC data for chronic diseases that have been applied to generate data about long-term treatment of hypertension cases. Unlike other previous systems, our approach takes advantage of the pros of both, the data- and the knowledge-driven approaches. In this paper we introduce the system, apply it to produce EoC synthetic data about virtual patients with arterial hypertension, and identify a limited number of modifiers of the system that allow adaptation and, therefore, the progressive improvement of the synthesized data generated.

Keywords

Clinical data synthetization Patient modeling Patient simulation 

References

  1. 1.
    Buczak, A.L., Moniz, L.J., Copeland, J., et al.: Data-driven hybrid method for synthetic electronic medical records generation. In: Proceedings of the IDAMAP 2008, pp. 81–86 (2008)Google Scholar
  2. 2.
    Buczak, A.L., Moniz, L.J., Feighner, B.H., Lombardo, J.S.: Mining electronic medical records for patient care patterns. In: Proceedings of the IEEE Symposium CIDM 2009, pp. 146–153 (2009)Google Scholar
  3. 3.
    Moniz, L., Buczak, A.L., Hung, L., et al.: Constuction and validation of synthetic electronic medical records. Online J. Public Health Inform. 1(1), e2 (2009)CrossRefGoogle Scholar
  4. 4.
    Buczac, A.L., Babin, S., Moniz, L.: Data-driven approach for creating synthetic electronic medical records. Med. Inform. Decis. Making 10, 59 (2010)CrossRefGoogle Scholar
  5. 5.
    Dube, K., Gallagher, T.: Approach and method for generating realistic synthetic electronic healthcare records for secondary use. In: Gibbons, J., MacCaull, W. (eds.) FHIES 2013. LNCS, vol. 8315, pp. 69–86. Springer, Heidelberg (2014). doi: 10.1007/978-3-642-53956-5_6 CrossRefGoogle Scholar
  6. 6.
    Huang, Z., Harmelen, F., Teije, A., Dentler, K.: Knowledge-based patient data generation. In: Riaño, D., Lenz, R., Miksch, S., Peleg, M., Reichert, M., Teije, A. (eds.) KR4HC/ProHealth 2013. LNCS (LNAI), vol. 8268, pp. 83–96. Springer, Heidelberg (2013). doi: 10.1007/978-3-319-03916-9_7 CrossRefGoogle Scholar
  7. 7.
    Real, F., Riaño, D., Alonso, J.R.: A patient simulation model based on decision tables for emergency shocks. In: Riaño, D., Lenz, R., Miksch, S., Peleg, M., Reichert, M., Teije, A. (eds.) KR4HC 2015. LNCS (LNAI), vol. 9485, pp. 21–33. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-26585-8_2 CrossRefGoogle Scholar
  8. 8.
    Riaño, D.: A systematic analysis of medical decisions: how to store knowledge and experience in decision tables. In: Riaño, D., Teije, A., Miksch, S. (eds.) KR4HC 2011. LNCS (LNAI), vol. 6924, pp. 23–36. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-27697-2_2 CrossRefGoogle Scholar
  9. 9.
    Talbot, T.B., Sagae, K., John, B., Rizzo, A.A.: Sorting out the virtual patient. Int. J. Gaming Comput. Mediated Simul. 4(3), 1–19 (2012)CrossRefGoogle Scholar
  10. 10.
    Real, F., Riaño, D., Alonso, J.R.: Training residents in the application of clinical guidelines for differential diagnosis of the most frequent causes of arterial hypertension with decision tables. In: Miksch, S., Riaño, D., Teije, A. (eds.) KR4HC 2014. LNCS (LNAI), vol. 8903, pp. 147–159. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-13281-5_11 Google Scholar
  11. 11.
    Real, F.: Use of decision tables to model assistance knowledge to train medical residents. Universitat Rovira i Virgili. Ph.D. dissertation (2016)Google Scholar
  12. 12.
    Riaño, D., Collado, A.: Model-based combination of treatments for the management of chronic comorbid patients. In: Peek, N., Marín Morales, R., Peleg, M. (eds.) AIME 2013. LNCS (LNAI), vol. 7885, pp. 11–16. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-38326-7_2 CrossRefGoogle Scholar
  13. 13.
    Chowdhury HMS. CDML: A Chronic Disease Management. MSc dissertation (2013)Google Scholar
  14. 14.
    Shiffman, R.N.: Representation of clinical practice guidelines in conventional and augmented decision tables. J. Am. Med. Inform. Assoc. 4(5), 382–393 (1997)CrossRefGoogle Scholar
  15. 15.
    Shiffman, R.N., Greenes, R.A.: Use of augmented decision tables to convert probabilistic data into clinical algorithms for the diagnosis of appendicitis. In: Proceedings of the Annual Symposium on Computer Application in Medical Care, pp. 686–690 (1991)Google Scholar
  16. 16.
    Bielza, C., Pozo, Juan, A.,Fernández, Lucas, P.: Finding and explaining optimal treatments. In: Dojat, M., Keravnou, Elpida, T., Barahona, P. (eds.) AIME 2003. LNCS (LNAI), vol. 2780, pp. 299–303. Springer, Heidelberg (2003). doi: 10.1007/978-3-540-39907-0_41 CrossRefGoogle Scholar
  17. 17.
    Chobanian, A.V., et al.: The seventh report of the joint national committee on prevention, detection, evaluation, and treatment of high blood pressure (2003)Google Scholar
  18. 18.
    Bohada, J.A.: Automatic production and integration of knowledge to the support of the decision and planning activities in medical-clinical diagnosis, treatment and prognosis. Ph.D. dissertation (2012)Google Scholar
  19. 19.
    López-Vallverdú, J.A.: Knowledge-based incremental induction of clinical algorithms. Ph.D. dissertation (2012)Google Scholar
  20. 20.
    Riaño, D., Real, F., et al.: An ontology-based personalization of health-care knowledge to support clinical decisions for chronically ill patients. JBI 45(3), 429–446 (2012)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Research Group on Artificial IntelligenceUniversitat Rovira i VirgiliTarragonaSpain

Personalised recommendations