ABSTRACT
Diabetes mellitus is a disease that affects to hundreds of million of people worldwide. Maintaining a good control of the disease is critical to avoid severe long-term complications. One of the main problems that arise in the (semi) automatic control of diabetes, is to get a model explaining how glucose levels in blood vary with insulin, food intakes and other factors, fitting the characteristics of each individual or patient. In this paper we compare genetic programming techniques with a set of classical identification techniques: classical simple exponential smoothing, Holt's smoothing (linear, exponential and damped), classical Holt and Winters methods and auto regressive integrated moving average modeling. We consider predictions horizons of 30, 60, 90 and 120 minutes. Experimental results shows the difficulty of predicting glucose values for more than 60 minutes and the necessity of adapt GP techniques for those dynamic environments.
- John R Koza. Genetic programming: on the programming of computers by means of natural selection, volume 1. MIT press, 1992. Google ScholarDigital Library
- Stephan M Winkler. Evolutionary system identification: modern concepts and practical applications. Universitätsverlag Rudolf TraunerTrauner, 2008.Google Scholar
- Michael Affenzeller, Stefan Wagner, Stephan Winkler, and Andreas Beham. Genetic algorithms and genetic programming: modern concepts and practical applications. Crc Press, 2009. Google ScholarCross Ref
- Robert J Hyndman and George Athanasopoulos. Forecasting: principles and practice. Online textbook, 2013.Google Scholar
- A.D.A. American-Diabetes-Association. Standards of medical care in diabetes 2010. Diabetes Care, 33(S1):11--61, 2010.Google Scholar
- C. Cobelli, C. Dalla Man, G. Sparacino, L. Magni, G. De Nicolao, and B.P. Kovatchev. Diabetes: Models, signals, and control. Biomedical Engineering, IEEE Reviews in, 2:54 --96, 2009.Google Scholar
- K. van Heusden, E. Dassau, H.C. Zisser, D.E. Seborg, and F.J. Doyle. Control-relevant models for glucose control using a priori patient characteristics. IEEE Transactions on Biomedical Engineering, 59(7):1839--1849, july 2012.Google ScholarCross Ref
- J. Ignacio Hidalgo, Esther Maqueda, José L. Risco-Martín, Alfredo Cuesta-Infante, J. Manuel Colmenar, and Javier Nobel. glucmodel: A monitoring and modeling system for chronic diseases applied to diabetes. Journal of Biomedical Informatics, (0):--, 2014.Google Scholar
- Daniel A. Finan, Cesar C. Palerm, Francis J. Doyle, Dale E. Seborg, Howard Zisser, Wendy C. Bevier, and L. Jovanovic. Effect of input excitation on the quality of empirical dynamic models for type 1 diabetes. AIChE Journal, 55(5):1135--1146, 2009.Google ScholarCross Ref
- E. Dassau, H. Zisser, B. Grosman, W. Bevier, M.W. Percival, L. Jovanovic, and F.J. Doyle. Artificial pancreatic betta-cell protocol for enhanced model identification. Diabetes, pages A105--A106, 2009.Google Scholar
- M. Gevers. Identification for control: From the early achievements to the revival of experiment design. In 44th IEEE Conference on Decision and Control, 2005 and 2005 European Control Conference. CDC-ECC '05, page 12, dec. 2005.Google ScholarCross Ref
- A. Gani, A.V. Gribok, Yinghui Lu, W.K. Ward, R.A. Vigersky, and J. Reifman. Universal glucose models for predicting subcutaneous glucose concentration in humans. Information Technology in Biomedicine, IEEE Transactions on, 14(1):157 --165, jan. 2010. Google ScholarDigital Library
- José Ignacio Hidalgo, J. Manuel Colmenar, José Luis Risco-Martín, Esther Maqueda, Marta Botella, José Antonio Rubio, Alfredo Cuesta-Infante, Oscar Garnica, and Juan Lanchares. Clarke and parkes error grid analysis of diabetic glucose models obtained with evolutionary computation. In Dirk V. Arnold and Enrique Alba, editors, Genetic and Evolutionary Computation Conference, GECCO '14, Vancouver, BC, Canada, July 12-16, 2014, Companion Material Proceedings, pages 1305--1312. ACM, 2014. Google ScholarDigital Library
- S Wagner, G Kronberger, A Beham, M Kommenda, A Scheibenpflug, E Pitzer, S Vonolfen, M Kofler, S Winkler, V Dorfer, et al. Architecture and design of the heuristiclab optimization environment. In Advanced Methods and Applications in Computational Intelligence, pages 197--261. Springer, 2014.Google ScholarCross Ref
- Gerald Kaiser. A Friendly Guide to Wavelets. Birkhauser Boston Inc., Cambridge, MA, USA, 1994. Google ScholarDigital Library
Index Terms
Data-Based Identification of Prediction Models for Glucose
Recommendations
Clarke and parkes error grid analysis of diabetic glucose models obtained with evolutionary computation
GECCO Comp '14: Proceedings of the Companion Publication of the 2014 Annual Conference on Genetic and Evolutionary ComputationDiabetes mellitus is a disease that affects to hundreds of millions of people worldwide. Maintaining a good control of the disease is critical to avoid severe long-term complications. In recent years, a lot of research has been made to improve the ...
Predicting Glycemia in Diabetic Patients By Evolutionary Computation and Continuous Glucose Monitoring
GECCO '16 Companion: Proceedings of the 2016 on Genetic and Evolutionary Computation Conference CompanionDiabetes mellitus is a disease that affects more than three hundreds million people worldwide. Maintaining a good control of the disease is critical to avoid not only severe long-term complications but also dangerous short-term situations. Diabetics ...
Blood Glucose Level Prediction Using Physiological Models and Support Vector Regression
ICMLA '13: Proceedings of the 2013 12th International Conference on Machine Learning and Applications - Volume 01Patients with diabetes must continually monitor their blood glucose levels and adjust insulin doses, striving to keep blood glucose levels as close to normal as possible. Blood glucose levels that deviate from the normal range can lead to serious short-...
Comments