Mixed Time Series Neural Network Glycemic Prediction for Patients with Diabetes Mellitus with the Prospect of Being Used as Part of an Intelligent Insulin Pump

Abstract

The paper considers the prospect of using a neural network self-learning algorithm for personalizing insulin therapy within the software and hardware complex of an intelligent insulin pump (IIP). IIP is an autonomous automatic insulin control system that can completely simulate the secretion of insulin by the pancreas of a healthy person. The required dose calculation is carried out on the basis of biological data from sensors installed on the patient's body. The algorithm for calculating the dose is an intelligent self-learning neural network unit that allows you to achieve fine personalization of therapy with the possibility of flexible readjustment in accordance with the dynamically changing biological parameters of the patient in real time. The article discusses several possible neural network paradigms for predicting blood sugar in the short-term (3 minutes) and medium-term (30 minutes) periods based on a mixed time series that includes measurements of blood glucose, active insulin and active carbohydrates at intervals of 3 minutes. The advantage of using MLP (multilayer perceptron) networks over other paradigms, in particular, LSTM networks (long short-term memory networks), is shown. The results of computational experiments using a neural network model on real data of two volunteers with different degrees of insulin sensitivity are presented. The impossibility of unifying the model for patients with different sensitivities has been proven, which confirms the need to personalize therapy for insulin-dependent diabetes. On the basis of the results of the experiments, recommendations are given on the construction and training of neural network models for predicting blood glucose levels in patients, as well as prospects and directions for further research.

Author Biographies

Svetlana Vladimirovna Novikova, Kazan National Research Technical University named after A. N. Tupolev - KAI

Professor of the Department for Applied Mathematics and Informatics, Institute for Computer Technologies and Information Protection, Dr.Sci. (Technology)

Zaid Zulfatovich Mingaliev, Kazan National Research Technical University named after A. N. Tupolev - KAI

Master's student of the Department of Information Security Systems, Institute for Computer Technologies and Information Protection

References

1.Partridge H., Perkins B., Mathieu S., Nicholls A., Adeniji K. Clinical recommendations in the management of the patient with type 1 diabetes on insulin pump therapy in the perioperative period: a primer for the anaesthetist. British Journal of Anaesthesia. 2016; 116(1):18-26. (In Eng.) DOI: https://doi.org/10.1093/bja/aev347
2.Shestakova M.V., Mayorov A.Yu., Philippov Yu.I., Ibragimova L.I., Pekareva E.V., Laptev D.N., Glazunova A.M. Russian national guidelines on insulin pump therapy and continuous glucose monitoring for diabetes mellitus patients. DRAFT. Problems of Endocrinology. 2015; 61(6):55-78. (In Russ., abstract in Eng.) DOI: https://doi.org/10.14341/probl201561655-78
3.Tutubalin P.I., Novikova S.V., Kirpichnikov A.P. O rabote po sozdaniyu prototipa obraztsa iskusstvennoy podzheludochnoy zhelezy [On working at developing a prototype of an artificial pancreas sample]. Bulletin of the Technological University. 2019; 22(9):147-152. Available at: https://www.elibrary.ru/item.asp?id=41328152 (accessed 13.02.2021). (In Russ., abstract in Eng.)
4.Girsh Ya.V. Struktura oslozhneniy sakharnogo diabeta 1 tipa u detey i podrostkov srednego Priob'ya [The structure of complications of type 1 diabetes mellitus in children and adolescents in the middle Ob region]. Mother and Baby in Kuzbass. 2005; (2):40-42. Available at: https://www.elibrary.ru/item.asp?id=12989863 (accessed 13.02.2021). (In Russ., abstract in Eng.)
5.Emelyanov A.O., Kuraeva T.L., Laptev D.N., Peterkova V.A. Prospektivnoe nabljudenie jeffektivnosti i bezopasnosti pompovoj insulinoterapii u detej i podrostkov [Prospective study of efficacy and safety of insulin pump therapy in children and adolescents]. Diabetes Mellitus. 2010; (3):143-146. Available at: https://www.elibrary.ru/item.asp?id=15600486 (accessed 13.02.2021). (In Russ., abstract in Eng.)
6.Kurbanov B.A., Novikova S.V., Kirpichnikov A.P. O sostoyanii realizatsii idei sozdaniya apparatno-programmnogo kompleksa avtomaticheskogo regulirovaniya podachi insulina [On the progress of insulin delivery automatic hardware-software complex concept development]. Bulletin of the Technological University. 2018; 21(8):116-123. Available at: https://www.elibrary.ru/item.asp?id=36351320 (accessed 13.02.2021). (In Russ., abstract in Eng.)
7.Palumbo P., Pepe P., Panunzi S., De Gaetano A. Time-Delay Model-Based Control of the Glucose-Insulin System, by Means of a State Observer. European Journal of Control. 2012; 18(6):591-606. (In Eng.) DOI: https://doi.org/10.3166/EJC.18.591-606
8.Haahr H., Heise T. Fast-Acting Insulin Aspart: A Review of its Pharmacokinetic and Pharmacodynamic Properties and the Clinical Consequences. Clinical Pharmacokinetics. 2020; 59(2):155-172. (In Eng.) DOI: https://doi.org/10.1007/s40262-019-00834-5
9.Wichern D.W. Modeling and forecasting discrete univariate time series with applications. Information Sciences. 1973; 6:247-264. (In Eng.) DOI: https://doi.org/10.1016/0020-0255(73)90041-8
10.Elleri D., Allen J.M., Harris J. et al. Absorption patterns of meals containing complex carbohydrates in type 1 diabetes. Diabetologia. 2013; 56(5):1108-1117. (In Eng.) DOI: https://doi.org/10.1007/s00125-013-2852-x
11.Toffanin Ch. et al. Dynamic insulin on board: incorporation of circadian insulin sensitivity variation. Journal of Diabetes Science and Technology. 2013; 7(4):928-940. (In Eng.) DOI: https://doi.org/10.1177/193229681300700415
12.Tutubalin P., Novikova S., et al. Status of creation of hardware-software complex of automatic control of the insulin delivery. Journal of Physics: Conference Series. 2019; 1368:042006. (In Eng.) DOI: https://doi.org/10.1088/1742-6596/1368/4/042006
13.Tunakova Yu., Novikova S., Ragimov A., Faizullin R., Valiev V. A method for assessing the retention of trace elements in human body using neural network technology. Journal of Healthcare Engineering. 2017; 2017:3471616. (In Eng.) DOI: https://doi.org/10.1155/2017/3471616
14.Subbotina I.E., Buevich A.G., Shichkin A.V. et al. Multilayer perceptron, generalized regression neural network, and hybrid model in predicting the spatial distribution of impurity in the topsoil of urbanized area. AIP Conference Proceedings. 2018; 1982(1):20004. (In Eng.) DOI: https://doi.org/10.1063/1.5045410
15.Kumar J., Goomer R., Kumar Singh A. Long Short Term Memory Recurrent Neural Network (LSTM-RNN) Based Workload Forecasting Model For Cloud Datacenters. Procedia Computer Science. 2018; 125:676-682. (In Eng.) DOI: https://doi.org/10.1016/j.procs.2017.12.087.
16.Lee J.M., Hirschfeld E., Wedding J. A Patient-Designed Do-It-Yourself Mobile Technology System for Diabetes: Promise and Challenges for a New Era in Medicine. JAMA. 2016; 315(14):1447-1448. (In Eng.) DOI: https://doi.org/10.1001/jama.2016.1903
17.Mingaliev Z.Z. Mnogofaktornaya neyrosetevaya model' kratkosrochnogo prognozirovaniya glikemii u bol'nykh sakharnym diabetom tipa I [Multi-factor neural network model of short-term prediction of glycemia in patients with type i diabetes]. Information Technology. Problems and Solutions. 2020; (2):67-72. Available at: https://www.elibrary.ru/item.asp?id=44303749 (accessed 13.02.2021). (In Russ., abstract in Eng.)
18.Cheng H., Tan P.N., Gao J., Scripps J. Multistep-Ahead Time Series Prediction. In: Ng W.K., Kitsuregawa M., Li J., Chang K. (Eds.) Advances in Knowledge Discovery and Data Mining. PAKDD 2006. Lecture Notes in Computer Science, vol. 3918. Springer, Berlin, Heidelberg; 2006. p. 765-774. (In Eng.) DOI: https://doi.org/10.1007/11731139_89
19.Kremleva E.Sh., Kirpichnikov A.P., Novikova S.V., Valitova N.L. Algoritm postroyeniya modeli kaskadnoy neyrosetevoy fil'tratsii dannykh s razlichnoy stepen'yu detalizatsii [Algorithm of constructing a neural cascade data filtration model with different detail degrees]. Bulletin of the Technological University. 2018; 21(8):109-115. Available at: https://www.elibrary.ru/item.asp?id=36351319 (accessed 13.02.2021). (In Russ., abstract in Eng.)
20.Novikova S.V., Kremleva E.Sh., Valitova N.L. Kodirovaniye myagkikh tsiklicheskikh dannykh pri pomoshchi psevdo-nechetkoy mery [Soft cyclic data encoding using a quasi-fuzzy measure]. Vestnik TvGU. Seriya: Prikladnaya matematika = Herald of Tver State University. Series: Applied Mathematics. 2019; (3):90-101. (In Russ., abstract in Eng.) DOI: https://doi.org/10.26456/vtpmk542
21.Graupe D. Principles of artificial neural networks. Advanced series of circuits and systems, 2nd Ed. World Scientific Publishing Co, Singapore; 2007. (In Eng.) DOI: https://doi.org/10.1142/6429
22.Liu F., He X., Zhou L. Application of generalized regression neural network residual kriging for terrain surface interpolation. Proceedings SPIE: International Symposium on Spatial Analysis, Spatial-Temporal Data Modeling, and Data Mining. 2009; 7492:74925F. (In Eng.) DOI: https://doi.org/10.1117/12.837425
23.Taneja H., Kapil, Singh A.K. Preserving Privacy of Patients Based on Re-identification Risk. Procedia Computer Science. 2015; 70(C):448- 454. Proc. of the 4th Int. Conference on Eco-friendly Computing and Communication Systems. (In Eng.) DOI: https://doi.org/10.1016/j.procs.2015.10.073
24.Contreras I., Vehi J. Artificial Intelligence for Diabetes Management and Decision Support: Literature Review. Journal of Medical Internet Research. 2018; 20(5):e10775. (In Eng.) DOI: https://doi.org/10.2196/10775
25.Vettoretti M., Cappon G., Facchinetti A., Sparacino G. Advanced Diabetes Management Using Artificial Intelligence and Continuous Glucose Monitoring Sensors. Sensors. 2020; 20(14):3870. (In Eng.) DOI: https://doi.org/10.3390/s20143870
Published
2021-04-15
How to Cite
NOVIKOVA, Svetlana Vladimirovna; MINGALIEV, Zaid Zulfatovich. Mixed Time Series Neural Network Glycemic Prediction for Patients with Diabetes Mellitus with the Prospect of Being Used as Part of an Intelligent Insulin Pump. Modern Information Technologies and IT-Education, [S.l.], v. 17, n. 1, p. 90-98, apr. 2021. ISSN 2411-1473. Available at: <http://sitito.cs.msu.ru/index.php/SITITO/article/view/732>. Date accessed: 18 sep. 2025. doi: https://doi.org/10.25559/SITITO.17.202101.732.
Section
Research and development in the field of new IT and their applications