Individualized Prediction of Blood Glucose Outcomes Using Compositional Data Analysis

Alvis Cabrera, Ernesto Estremera, Aleix Beneyto, Lyvia Biagi, Iván Contreras, Josep Antoni Martín-Fernández and Josep Vehí ()
Additional contact information
Alvis Cabrera: Department of Electrical, Electronic and Automatic Engineering, University of Girona, 17003 Girona, Spain
Ernesto Estremera: Department of Electrical, Electronic and Automatic Engineering, University of Girona, 17003 Girona, Spain
Aleix Beneyto: Department of Electrical, Electronic and Automatic Engineering, University of Girona, 17003 Girona, Spain
Lyvia Biagi: Campus Guarapuava, Federal University of Technology–Paraná (UTFPR), Guarapuava 85053-525, Brazil
Iván Contreras: Department of Electrical, Electronic and Automatic Engineering, University of Girona, 17003 Girona, Spain
Josep Antoni Martín-Fernández: Department of Computer Science, Applied Mathematics and Statistics, University of Girona, 17003 Girona, Spain
Josep Vehí: Department of Electrical, Electronic and Automatic Engineering, University of Girona, 17003 Girona, Spain

Mathematics, 2023, vol. 11, issue 21, 1-17

Abstract: This paper presents an individualized multiple linear regression model based on compositional data where we predict the mean and coefficient of variation of blood glucose in individuals with type 1 diabetes for the long-term (2 and 4 h). From these predictions, we estimate the minimum and maximum glucose values to provide future glycemic status. The proposed methodology has been validated using a dataset of 226 real adult patients with type 1 diabetes (Replace BG (NCT02258373)). The obtained results show a median balanced accuracy and sensitivity of over 90% and 80%, respectively. A information system has been implemented and validated to update patients on their glycemic status and associated risks for the next few hours.

Keywords: compositional data; decision support system; diabetes type 1; blood glucose prediction (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/21/4517/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/21/4517/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:21:p:4517-:d:1272768

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().