Multivariate Prediction of Subcutaneous Glucose Concentration in Type 1 Diabetes Patients Based on Support Vector Regression

• Published in: IEEE journal of biomedical and health informatics Vol. 17; no. 1; pp. 71 - 81
• Main Authors: Georga, E. I., Protopappas, V. C., Ardigo, Diego, Marina, M., Zavaroni, I., Polyzos, D., Fotiadis, D. I.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2013
• Subjects: Adult; Aged; Blood; Blood Glucose - analysis; Blood Glucose Self-Monitoring - methods; Diabetes; Diabetes Mellitus, Type 1 - blood; Diabetes Mellitus, Type 1 - drug therapy; Diabetes Mellitus, Type 1 - metabolism; Female; Humans; Input variables; Insulin; Insulin - pharmacokinetics; Insulin - therapeutic use; Male; Middle Aged; Models, Statistical; Multivariate Analysis; Plasmas; Predictive models; Reproducibility of Results; Subcutaneous (s.c.) glucose concentration; Subcutaneous Tissue - chemistry; Sugar; Support Vector Machine; support vector machines; type 1 diabetes; Young Adult
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/TITB.2012.2219876

Data-driven techniques have recently drawn significant interest in the predictive modeling of subcutaneous (s.c.) glucose concentration in type 1 diabetes. In this study, the s.c. glucose prediction is treated as a multivariate regression problem, which is addressed using support vector regression (SVR). The proposed method is based on variables concerning: 1) the s.c. glucose profile; 2) the plasma insulin concentration; 3) the appearance of meal-derived glucose in the systemic circulation; and 4) the energy expenditure during physical activities. Six cases corresponding to different combinations of the aforementioned variables are used to investigate the influence of the input on the daily glucose prediction. The proposed method is evaluated using a dataset of 27 patients in free-living conditions. Tenfold cross validation is applied to each dataset individually to both optimize and test the SVR model. In the case, where all the input variables are considered, the average prediction errors are 5.21, 6.03, 7.14, and 7.62 mg/dl for 15-, 30-, 60-, and 120-min prediction horizons, respectively. The results clearly indicate that the availability of multivariable data and their effective combination can significantly increase the accuracy of both short-term and long-term predictions.