Advertisement

A Logic-Based Learning Approach to Explore Diabetes Patient Behaviors

  • Josephine LampEmail author
  • Simone Silvetti
  • Marc Breton
  • Laura Nenzi
  • Lu Feng
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11773)

Abstract

Type I Diabetes (T1D) is a chronic disease in which the body’s ability to synthesize insulin is destroyed. It can be difficult for patients to manage their T1D, as they must control a variety of behavioral factors that affect glycemic control outcomes. In this paper, we explore T1D patient behaviors using a Signal Temporal Logic (STL) based learning approach. STL formulas learned from real patient data characterize behavior patterns that may result in varying glycemic control. Such logical characterizations can provide feedback to clinicians and their patients about behavioral changes that patients may implement to improve T1D control. We present both individual- and population-level behavior patterns learned from a clinical dataset of 21 T1D patients.

Keywords

Signal Temporal Logic Learning Type I Diabetes 

Notes

Acknowledgements

The authors would like to graciously thank the UVA Center for Diabetes Technology for providing the clinical datasets and Basak Ozaslan, Jack Corbett, Jonathan Hughes and Dr. José García-Tirado for their clinical insights and valuable discussions. Research partially supported by the Austrian National Research Networks RiSE/ShiNE (S11405) and ADynNet (P28182) of the Austrian Science Fund (FWF).

References

  1. 1.
    American Diabetes Association: 13. children and adolescents: standards of medical care in diabetes–2019. Diab. Care 42(Suppl. 1), S148–S164 (2019)Google Scholar
  2. 2.
    Bartocci, E., Bortolussi, L., Sanguinetti, G.: Data-driven statistical learning of temporal logic properties. In: Legay, A., Bozga, M. (eds.) FORMATS 2014. LNCS, vol. 8711, pp. 23–37. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10512-3_3CrossRefzbMATHGoogle Scholar
  3. 3.
    Bombara, G., Vasile, C.I., Penedo, F.: A decision tree approach to data classification using signal temporal logic, pp. 1–10 (2016)Google Scholar
  4. 4.
    Bufo, S., Bartocci, E., Sanguinetti, G., Borelli, M., Lucangelo, U., Bortolussi, L.: Temporal logic based monitoring of assisted ventilation in intensive care patients. In: Margaria, T., Steffen, B. (eds.) ISoLA 2014. LNCS, vol. 8803, pp. 391–403. Springer, Heidelberg (2014).  https://doi.org/10.1007/978-3-662-45231-8_30CrossRefGoogle Scholar
  5. 5.
    Bumgardner, W.: The average steps per minute for different exercises. https://www.verywellfit.com/pedometer-step-equivalents-for-exercises-and-activities-3435742
  6. 6.
    Cameron, F., Niemeyer, G., Bequette, B.W.: Extended multiple model prediction with application to blood glucose regulation. J. Process Control 22(8), 1422–1432 (2012)CrossRefGoogle Scholar
  7. 7.
    Chatterjee, S., Byun, J., Dutta, K., Pedersen, R.U., Pottathil, A., Xie, H.: Designing an Internet-of-Things (IoT) and sensor-based in-home monitoring system for assisting diabetes patients: iterative learning from two case studies. Eur. J. Inf. Syst. 27(6), 670–685 (2018)CrossRefGoogle Scholar
  8. 8.
    Chen, S., Feng, L., Rickels, M.R., Peleckis, A., Sokolsky, O., Lee, I.: A Data-Driven Behavior Modeling and Analysis Framework for Diabetic Patients on Insulin Pumps Recommended Citation, Technical report (2015). http://repository.upenn.edu/cis_papersrepository.upenn.edu/cis_papers/791
  9. 9.
    Deshmukh, J., Donzé, A., Ghosh, S., Jin, X., Juniwal, G., Seshia, S.: Robust online monitoring of signal temporal logic, pp. 1–26, July 2017Google Scholar
  10. 10.
    Prevention: Type 1 diabetes for Disease Control, C.C., August 2018. https://www.cdc.gov/diabetes/basics/type1.html
  11. 11.
    Donzé, A., Maler, O.: Robust satisfaction of temporal logic over real-valued signals. In: Chatterjee, K., Henzinger, T.A. (eds.) FORMATS 2010. LNCS, vol. 6246, pp. 92–106. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15297-9_9CrossRefzbMATHGoogle Scholar
  12. 12.
    Fabris, C., Patek, S.D., Breton, M.D.: Are risk indices derived from CGM interchangeable with SMBG-based indices? J. Diab. Sci. Technol. 10(1), 50–59 (2016)CrossRefGoogle Scholar
  13. 13.
    Fainekos, G.E., Pappas, G.J.: Robustness of temporal logic specifications for continuous-time signals. Theor. Comput. Sci. 410(42), 4262 – 4291 (2009).  https://doi.org/10.1016/j.tcs.2009.06.021. http://www.sciencedirect.com/science/article/pii/S0304397509004149MathSciNetCrossRefGoogle Scholar
  14. 14.
    Hoyos, J.D., Bolanos, F., Vallejo, M., Rivadeneira, P.S.: Population-based incremental learning algorithm for identification of blood glucose dynamics model for type-1 diabetic patients. In: Proceedings on the International Conference on Artificial Intelligence (ICAI), pp. 29–35. The Steering Committee of The World Congress in Computer Science, Computer (2018)Google Scholar
  15. 15.
    IDF: IDF diabetes atlas 8th edition 2017 (2017). https://diabetesatlas.org/
  16. 16.
    Klimek, R.: Behavior recognition and analysis in smart environments for context-aware applications, October 2015 (2016).  https://doi.org/10.1109/SMC.2015.340
  17. 17.
    Kong, Z., Jones, A., Belta, C.: Temporal logics for learning and detection of anomalous behavior. IEEE Trans. Autom. Control 62(3), 1210–1222 (2017).  https://doi.org/10.1109/TAC.2016.2585083MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Kovatchev, B.P.: Metrics for glycaemic control-from HbA 1c to continuous glucose monitoring. Nat. Rev. Endocrinol. 13(7), 425 (2017)CrossRefGoogle Scholar
  19. 19.
    Maler, O., Nickovic, D.: Monitoring temporal properties of continuous signals. In: Lakhnech, Y., Yovine, S. (eds.) FORMATS/FTRTFT -2004. LNCS, vol. 3253, pp. 152–166. Springer, Heidelberg (2004).  https://doi.org/10.1007/978-3-540-30206-3_12CrossRefzbMATHGoogle Scholar
  20. 20.
    Marshall, S.J., et al.: Translating physical activity recommendations into a pedometer-based step goal: 3000 steps in 30 minutes. Am. J. Prev. Med. 36(5), 410–415 (2009)CrossRefGoogle Scholar
  21. 21.
    Nenzi, L., Silvetti, S., Bartocci, E., Bortolussi, L.: A robust genetic algorithm for learning temporal specifications from data. In: McIver, A., Horvath, A. (eds.) QEST 2018. LNCS, vol. 11024, pp. 323–338. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-99154-2_20CrossRefGoogle Scholar
  22. 22.
    Paoletti, N., Liu, K.S., Smolka, S.A., Lin, S.: Data-driven robust control for type 1 diabetes under meal and exercise uncertainties. In: Feret, J., Koeppl, H. (eds.) CMSB 2017. LNCS, vol. 10545, pp. 214–232. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67471-1_13CrossRefGoogle Scholar
  23. 23.
    Riddell, M.C., et al.: Exercise management in type 1 diabetes: a consensus statement. Lancet Diab. Endocrinol. 5(5), 377–390 (2017).  https://doi.org/10.1016/S2213-8587(17)30014-1CrossRefGoogle Scholar
  24. 24.
    Young, W., Corbett, J., Gerber, M.S., Patek, S., Feng, L.: DAMON: a data authenticity monitoring system for diabetes management. In: 2018 IEEE/ACM Third International Conference on Internet-of-Things Design and Implementation (IoTDI), pp. 25–36. IEEE (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Josephine Lamp
    • 1
    Email author
  • Simone Silvetti
    • 3
  • Marc Breton
    • 2
  • Laura Nenzi
    • 4
  • Lu Feng
    • 1
  1. 1.Department of Computer ScienceUniversity of VirginiaCharlottesvilleUSA
  2. 2.Center for Diabetes TechnologyUniversity of VirginiaCharlottesvilleUSA
  3. 3.Esteco S.p.A.TriesteItaly
  4. 4.University of TriesteTriesteItaly

Personalised recommendations