Advertisement

Modelling Time-Series of Glucose Measurements from Diabetes Patients Using Predictive Clustering Trees

  • Mate Beštek
  • Dragi Kocev
  • Sašo Džeroski
  • Andrej Brodnik
  • Rade Iljaž
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10259)

Abstract

In this paper, we presented the results of data analysis of 1-year measurements from diabetes patients within the Slovenian healthcare project eCare. We focused on looking for groups/clusters of patients with the similar time profile of the glucose values and describe those patients with their clinical status. We treated in a similar way the WONCA scores (i.e., patients’ functional status). Considering the complexity of the data at hand (time series with a different number of measurements and different time intervals), we used predictive clustering trees with dynamic time warping as the distance between time series. The obtained PCTs identified several groups of patients that exhibit similar behavior. More specifically, we described groups of patients that are able to keep under control their disease, and groups that are less successful in that. Furthermore, we identified and described groups of patients that have similar functional status.

Keywords

eCare Diabetes patients Time series prediction Predictive clustering WONCA scores 

References

  1. 1.
    Abraham, C., Michie, S.: A taxonomy of behavior change techniques used in interventions. Health Psychol.: Off. J. Div. Health Psychol. Am. Psychol. Assoc. 27(3), 379–387 (2008)CrossRefGoogle Scholar
  2. 2.
    Beštek, M., Brodnik, A.: Interoperability and mHealth precondition for successful eCare. In: Adibi, S. (ed.) Mobile Health (mHeath) The Technology Road Map. Springer Series in Bio-/Neuroinformatics. Springer, Switzerland (2014). doi: 10.1007/978-3-319-12817-7_16 Google Scholar
  3. 3.
    Beštek, M., Brodnik, A.: Preconditions for successful eCare. Inform. Med. Slov. 20(1–2), 17–29 (2015)Google Scholar
  4. 4.
    Blockeel, H.: Top-down induction of first order logical decision trees. Ph.D. thesis, Katholieke Universiteit Leuven, Leuven, Belgium (1998)Google Scholar
  5. 5.
    Breiman, L., Friedman, J., Olshen, R., Stone, C.J.: Classification and Regression Trees. Chapman & Hall/CRC, Boca Raton (1984)zbMATHGoogle Scholar
  6. 6.
    Debeljak, M., Squire, G.R., Kocev, D., Hawes, C., Young, M.W., Džeroski, S.: Analysis of time series data on agroecosystem vegetation using predictive clustering trees. Ecol. Model. 222(14), 2524–2529 (2011)CrossRefGoogle Scholar
  7. 7.
    Džeroski, S.: Introduction: the challenges for data mining. In: 5th International Workshop Knowledge Discovery in Inductive Databases, KDID 2006, pp. 259–300 (2007)Google Scholar
  8. 8.
    Eljil, K.A.A.S.: Predicting hypoglycemia. In: Diabetic Patients Using Machine Learning Techniques, pp. 1–92. Faculty of the American University of Sharjah College of Engineering, UAE (2014)Google Scholar
  9. 9.
    Georga, E., Protopappas, V.C.: Short-term vs. long-term analysis of diabetes data: application of machine learning and data mining techniques. In: IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE) (2013)Google Scholar
  10. 10.
    Gjorgjioski, V.: Distance-based learning from structured data. Ph.D. thesis, International postgraduate school Jožef Stefan, Ljubljana, Slovenia (2015)Google Scholar
  11. 11.
    Karpel’ev, V.A., Filippov, Y., Tarasov, Y., Boyarsky, M.D., Mayorov, A., Shestakova, M.V., Dedov, I.I.: Mathematical modeling of the blood glucose regulation system in diabetes mellitus patients. Vestn. Ross. Akad. Med. Nauk 70(5), 549–560 (2015). https://www.scopus.com/inward/record.uri?eid=2-s2.0-84948981003&doi=10.15690%2Fvramn.v70.i5.1441&partnerID=40&md5=b578cbe1711a9bee957a656eb681c1c2 CrossRefGoogle Scholar
  12. 12.
    Kavakiotis, I., Tsave, O., Salifoglou, A., Maglaveras, N., Vlahavas, I., Chouvarda, I.: Machine learning and data mining methods in diabetes research. Comput. Struct. Biotechnol. J. 15, 104–116 (2017). http://dx.doi.org/10.1016/j.csbj.2016.12.005 CrossRefGoogle Scholar
  13. 13.
    Kocev, D., Vens, C., Struyf, J., Džeroski, S.: Tree ensembles for predicting structured outputs. Pattern Recognit. 46(3), 817–833 (2013)CrossRefGoogle Scholar
  14. 14.
    Lenert, L., Norman, G.J., Mailhot, M., Patrick, K.: A framework for modeling health behavior protocols and their linkage to behavioral theory. J. Biomed. Inform. 38(4), 270–280 (2005)CrossRefGoogle Scholar
  15. 15.
    Marinov, M., Mosa, A.S.M., Yoo, I., Boren, S.A.: Data-mining technologies for diabetes: a systematic review. J. Diabetes Sci. Technol. 5(6), 1549–1556 (2011). http://dst.sagepub.com/lookup/doi/10.1177/193229681100500631 CrossRefGoogle Scholar
  16. 16.
    Reifman, J., Rajaraman, S., Gribok, A., Ward, W.K.: Predictive monitoring for improved management of glucose levels. J. Diabetes Sci. Technol. 1(4), 478–486 (2007). https://www.scopus.com/inward/record.uri?eid=2-s2.0-52449101078&partnerID=40&md5=07e50cc16ed4d23ac38ba713efed205a CrossRefGoogle Scholar
  17. 17.
    Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spokenword recognition. IEEE Trans. Acoust. Speech Signal Process. ASSP–26, 43–49 (1978)CrossRefzbMATHGoogle Scholar
  18. 18.
    Shivakumar, B.L.: A survey on data-mining technologies for prediction and diagnosis of diabetes (2014)Google Scholar
  19. 19.
    Slavkov, I., Gjorgjioski, V., Struyf, J., Džeroski, S.: Finding explained groups of time-course gene expression profiles with predictive clustering trees. Mol. BioSyst. 6(4), 729–740 (2010)CrossRefGoogle Scholar
  20. 20.
    Sowjanya, K., Singhal, A., Choudhary, C.: MobDBTest: a machine learning based system for predicting diabetes risk using mobile devices. In: 2015 IEEE International Advance Computing Conference (IACC), pp. 397–402 (2015)Google Scholar
  21. 21.
    Sumalatha, G., Muniraj, N.J.R.: Survey on medical diagnosis using data mining techniques. In: 2013 International Conference on Optical Imaging Sensor and Security (ICOSS), pp. 1–8 (2013). http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6678433
  22. 22.
    Zecchin, C., Facchinetti, A., Sparacino, G., Cobelli, C.: Reduction of number and duration of hypoglycemic events by glucose prediction methods: a proof-of-concept in silico study. Diabetes Technol. Therapeutics 15(1), 66–77 (2013)CrossRefGoogle Scholar
  23. 23.
    Zhao, C., Yu, C.: Rapid model identification for online subcutaneous glucose concentration prediction for new subjects with type i diabetes. IEEE Trans. Biomed. Eng. 62(5), 1333–1344 (2015). https://www.scopus.com/inward/record.uri?eid=2-s2.0-84929075114&doi=10.1109%2FTBME.2014.2387293&partnerID=40&md5=e23db851493020e4f51367ce89f66dcb CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Mate Beštek
    • 1
  • Dragi Kocev
    • 2
  • Sašo Džeroski
    • 2
  • Andrej Brodnik
    • 3
  • Rade Iljaž
    • 4
  1. 1.National Institute of Public HealthLjubljanaSlovenia
  2. 2.Jožef Stefan InstituteLjubljanaSlovenia
  3. 3.Faculty of Computer and Information ScienceLjubljanaSlovenia
  4. 4.Faculty of MedicineLjubljanaSlovenia

Personalised recommendations