Personalized Glucose Prediction Model for Patients With Type I Diabetes
DOI:
https://doi.org/10.30837/csitic52021231817Keywords:
prediction model, diabetes self-management, neural networks, self-organized mapsAbstract
This paper represents an attempt to use machine learning techniques to personalize glucose predictions for patients with type I diabetes (T1D). The study aims at proposing a personalized model, capable to provide real-time blood glucose estimations, taking into consideration patient’s health preconditions. The proposed model represents a neural network based on the use of Self-Organized Maps (SOM). It was elaborated using data from 5 patients with T1D, collected with help of a specially created for these purposes support system and pre-trained using a clinical dataset. The study lasted for 3 months.
References
The DCCT Research Group, “The effect of intensive treatment of diabetes on the development and progression of long-term complications in insulin dependent diabetes mellitus,” New England J. Med., vol. 329, (no. 14), 1993, pp. 977–986.
J. Clerk Maxwell, “A Treatise on Electricity and Magnetism”, 3rd ed., vol. 2, Oxford: Clarendon, 1892, pp.68–73.
V.W. Bolie, “Coefficients of normal blood glucose regulation”, J Appl Physiol, vol. 16, (no. 5), 1961, pp. 783-788.
R. Hovorka et al., "Nonlinear model predictive control of glucose concentration in subjects with type 1 diabetes" Physiol. Meas., vol. 25, 2004, pp. 905-920.
Cobelli, C.; Mari, “A. Validation of mathematical models ofcomplex endocrine-metabolic systems. A case study on a model of glucose regulation”, Med. Biol. Eng. Comput., vol. 21, (no. 4), 1983, pp. 390–399.
K. Zarkogianni, A. Vazeou, S.G. Mougiakakou, A. Prountzou, and K.S. Nikita, “An Insulin Infusion Advisory System Based on Autotuning Nonlinear Model-Predictive Control,” Biomedical Engineering, IEEE Transactions, vol. 58, (no. 9), 2011, pp. 2467-2477.
https://archive.ics.uci.edu/ml/datasets/diabetes (clinical dataset)
M. Berger, D. Rodbard, “Computer simulation of plasma insulin and glucose dynamics after subcutaneous insulin injection”, Diabetes Care, vol. 12, 1989, pp. 725–736.
K. Zarkogianni, E. Litsa, A. Vazeou, K. S. Nikita, ”Personalized Glucose- Insulin Metabolism Model based on SelfOrganizing Maps for Patients with Type 1 Diabetes Mellitus”, Biomedical Engineering, IEEE Transactions, vol. 1, 2013, pp. 1-4.
