ABSTRACT
This study investigates how to improve the predictions of glucose values obtained with genetic programming models. A set of statistical techniques are used to discover glucose profiles that identify similar situations in patients with type 1 diabetes mellitus, and incorporate this knowledge to the models. Glucose time series are divided into 4-hour non-overlapping slots and clustered using the technique based on decision trees called chi-square automatic interaction detection, to classify glucose profiles into groups using two decision variables: day of the week and time slot of the day. The objective is to customize models for different glucose profiles that appear in the patient's day-to-day. Genetic programming models created with glucose values from the original data-set are compared to those of models created with classified glucose values. Significant differences (p-value < 0.05) and associations are observed between the glucose profiles. In general, using classified glucose values in models created with genetic programming, the accuracy of the predictions improves in comparison with those of models created with the original data-set. We concluded that the classification process can be useful to correct and improve habits or clinical therapies in patients, and obtain more accurate models through automatic learning techniques and artificial intelligence.
- Hirotogu Akaike. 1998. Information Theory and an Extension of the Maximum Likelihood Principle. Springer New York, New York, NY, 199--213.Google Scholar
- American Diabetes Association. 2016. Intensive Diabetes Treatment and Cardiovascular Outcomes in Type 1 Diabetes: The DCCT/EDIC Study 30-Year Follow-up. Diabetes Care (2016).Google Scholar
- Carlos Cervigon, J. Ignacio Hidalgo, Marta Botella, and Rafael-J Villanueva. 2017. A genetic algorithm approach to customizing a glucose model based on usual therapeutic parameters. Progress in Artificial Intelligence 6, 3 (2017), 255--261.Google ScholarCross Ref
- W. Clarke, D. Cox, L. Gonder-Frederick, W. Carter, and S. Pohl. 1987. Evaluating clinical accuracy of systems for self-monitoring of blood glucose. Diabetes Care 10, 5 (1987), 622--628.Google ScholarCross Ref
- M. Hurvich Clifford and Chih Ling Tsai. 1989. Regression and time series model selection in small samples. Biometrika 76, 2 (1989), 297--307.Google ScholarCross Ref
- Ivanoe De Falco, Antonio Delia Cioppa, Tomas Koutny, Michal Krcma, Um-berto Scafuri, and Ernesto Tarantino. 2018. Genetic Programming-based induction of a glucose-dynamics model for telemedicine. Journal of Network and Computer Applications 119 (2018), 1--13.Google ScholarDigital Library
- OrganizaciÃČÂŞn Mundial de la Salud. 2016. Informe Mundial Sobre la Diabetes. World Health Organization 2016 (2016).Google Scholar
- Ya-Xiong Tao (Eds.). 2014. Glucose Homeostatis and the Pathogenesis of Diabetes Mellitus (1 ed.). Academic Press.Google Scholar
- F.H. El-Khatib, S.J. Russell, D.M. Nathan, R.G. Sutherlin, and E.R. Damiano. 2010. A bihormonal closed-loop artificial pancreas for type 1 diabetes. Sci Transl Med. 2 (27) (2010).Google Scholar
- J. Ignacio Hidalgo, Esther Maqueda, Jose L. Risco-Martan, Alfredo Cuesta-Infante, J. Manuel Colmenar, and Javier Nobel. 2014. glUCModel: A monitoring and modeling system for chronic diseases applied to diabetes. Journal of Biomedical Informatics 48 (2014), 183 -- 192. Google ScholarDigital Library
- Jose Ignacio Hidalgo, Jose Manuel Velasco, Juan Lanchares, Sergio Contador, and Oscar Garnica. 2018. An analysis of solutions based on Genetic Programming to solve problems of symbolic regression of data from continuous glucose monitoring.XVIII Conferencia AEPIA (2018), 764--771. https://sci2s.ugr.es/caepia18/proceedings/proceedings.phpGoogle Scholar
- Roman Hovorka, Janet M Allen, Daniela Elleri, Ludovic J Chassin, Julie Harris, Dongyuan Xing, Craig Kollman, Tomas Hovorka, Anne Mette F Larsen, Mari-anna Nodale, Alessandra De Palma, Malgorzata E Wilinska, Carlo L Acerini, and David B Dunger. 2010. Manual closed-loop insulin delivery in children and adolescents with type 1 diabetes: a phase 2 randomised crossover trial. The Lancet 375 (2010), 743 -- 751.Google ScholarCross Ref
- George Kaplan, Debbie E Goldberg, Susan Everson-Rose, Richard D Cohen, Riitta Salonen, Jaakko Tuomilehto, and Jukka Salonen. 1996. Perceived Health Status and Morbidity and Mortality: Evidence from the Kuopio Ischaemic Heart Disease Risk Factor Study. 25 (05 1996).Google Scholar
- G. V. Kass. 1980. An Exploratory Technique for Investigating Large Quantities of Categorical Data. Journal of the Royal Statistical Society. Series C (Applied Statistics) 29, 2 (1980), 119--127. http://www.jstor.org/stable/2986296Google ScholarCross Ref
- Christina-Maria Kastorini, George Papadakis, Haralampos J. Milionis, Kallirroi Kalantzi, Paolo-Emilio Puddu, Vassilios Nikolaou, Konstantinos N. Vemmos, John A. Goudevenos, and Demosthenes B. Panagiotakos. 2013. Comparative analysis of a-priori and a-posteriori dietary patterns using state-of-the-art classification algorithms: A case/case-control study. Artificial Intelligence in Medicine 59, 3 (2013), 175 -- 183. Google ScholarDigital Library
- Maarten Keijzer. 2003. Improving Symbolic Regression with Interval Arithmetic and Linear Scaling. (2003), 70--82. Google ScholarDigital Library
- B. Kovatchev, C. Cobelli, E. Renard, S. Anderson, M. Breton, S. Patek, W. Clarke, D. Bruttomesso, A. Maran, S. Costa, A. Avogaro, C. Dalla Man, A. Facchinetti, L. Magni, G. De Nicolao, J. Place, and A. Farret. 2010. Multinational study of subcutaneous model-predictive closed loop control in type 1 diabetes mellitus: Summary of the results. Diabetes Sci Technol 4 (2010), 1374--1381.Google ScholarCross Ref
- John R. Koza. 1992. Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge, MA, USA. Google ScholarDigital Library
- Sean Luke. 2000. Two fast tree-creation algorithms for genetic programming. IEEE Trans. Evolutionary Computation 4 (2000), 274--283. Google ScholarDigital Library
- Lalo Magni, Marco Forgione, Chiara Toffanin, Chiara Dalla Man, Boris Kovatchev, Giuseppe De Nicolao, and Claudio Cobelli. 2009. Run-to-Run Tuning of Model Predictive Control for Type 1 Diabetes Subjects: In Silico Trial. Journal of Diabetes Science and Technology 3, 5 (2009), 1091--1098.Google ScholarCross Ref
- Lucy Mays. 2015. Diabetes Mellitus Standards of Care. Nursing Clinics of North America 50, 4 (2015), 703 -- 711. Pathophysiology and Care Protocols for Nursing Management.Google ScholarCross Ref
- Mirko Messori, Chiara Toffanin, Simone Del Favero, Giuseppe De Nicolao, Claudio Cobelli, and Lalo Magni. 2016. Model individualization for artificial pancreas. Computer Methods and Programs in Biomedicine (2016), -.Google Scholar
- J. L. Parkes, S. L. Slatin, S. Pardo, and B. H. Ginsberg. 2000. A new consensus error grid to evaluate the clinical significance of inaccuracies in the measurement of blood glucose. Diabetes Care 23, 8 (2000), 1143--1148. arXiv:http://care.diabetesjournals.org/content/23/8/1143.full.pdfGoogle ScholarCross Ref
- Andreas Pfützne, David C. Klonoff, Scott Pardo, and Joan L. Parkes. 2013. Technical Aspects of the Parkes Error Grid. Journal of Diabetes Science and Technology 7, 5 (2013), 1275--1281. PMID: 24124954.Google ScholarCross Ref
- Thierry Prud'Homme, Alain Bock, Gregory Francois, and Denis Gillet. 2011. Preclinically assessed optimal control of postprandial glucose excursions for type 1 patients with diabetes. In Automation Science and Engineering (CASE), 2011 IEEE Conference on. IEEE, 702--707.Google ScholarCross Ref
- G.M. Steil, K. Rebrin, F. Hariri, S. Jinagonda, S. Tadros, C. Darwin, and M.F. Saad. 2005. Interstitial fluid glucose dynamics during insulin-induced hypoglycaemia. Diabetologia 48, 9 (2005), 1833--1840.Google ScholarCross Ref
- Jose Manuel Velasco, Oscar Garnica, Juan Lanchares, Marta Botella, and J. Ignacio Hidalgo. 2018. Combining data augmentation, EDAs and grammatical evolution for blood glucose forecasting. Memetic Computing (22 Jun 2018).Google Scholar
- S. Wagner and M. Affenzeller. 2005. HeuristicLab: A Generic and Extensible Optimization Environment. (2005), 538--541.Google Scholar
Index Terms
- Can clustering improve glucose forecasting with genetic programming models?
Recommendations
Profiled glucose forecasting using genetic programming and clustering
SAC '20: Proceedings of the 35th Annual ACM Symposium on Applied ComputingThis paper proposes a method to obtain accurate forecastings of the subcutaneous glucose values from diabetic patients. Statistical techniques are applied to identify everyday situations of glucose behaviors and discover glucose profiles. This knowledge ...
A method to early detect blood glucose variations using continuous glucose monitoring system
SMO'09: Proceedings of the 9th WSEAS international conference on Simulation, modelling and optimizationThe modern research in the field of the treatment for type I diabetes mellitus include the artificial pancreas. In this paper the authors have used the mathematical analysis of the blood glucose time series recorded through continuous glucose monitoring ...
Glucose forecasting using genetic programming and latent glucose variability features
AbstractThis paper investigates a set of genetic programming methods to obtain accurate predictions of subcutaneous glucose values from diabetic patients. We explore the usefulness of different features that identify the latent glucose ...
Graphical abstractDisplay Omitted
Highlights- A methodology for glucose prediction is developed.
- We propose the use of ...
Comments