A Complete AI-Based System for Dietary Assessment and Personalized Insulin Adjustment in Type 1 Diabetes Self-management

Maria Panagiotou; Ioannis Papathanail; Lubnaa Abdur Rahman; Lorenzo Brigato; Natalie S. Bez; Maria F. Vasiloglou; Thomai Stathopoulou; Bastiaan E. de Galan; Ulrik Pedersen-Bjergaard; Klazine van der Horst; Stavroula Mougiakakou

doi:10.1007/978-3-031-44240-7_8

A Complete AI-Based System for Dietary Assessment and Personalized Insulin Adjustment in Type 1 Diabetes Self-management

Maria Panagiotou, Ioannis Papathanail, Lubnaa Abdur Rahman, Lorenzo Brigato, Natalie S. Bez, Maria F. Vasiloglou, Thomai Stathopoulou, Bastiaan E. de Galan, Ulrik Pedersen-Bjergaard, Klazine van der Horst, Stavroula Mougiakakou^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

People living with type 1 diabetes (PwT1D) face multiple challenges in self-managing their blood glucose levels, including the need for accurate carbohydrate counting, and the requirements of adjusting insulin dosage. Our paper aims to alleviate the demands of diabetes self-management by developing a complete system that employs computer vision to estimate the carbohydrate content of meals and utilizes reinforcement learning to personalize insulin dosing. Our findings demonstrate that this system results in a significantly greater percentage of time spent in the target glucose range compared to the combined standard bolus calculator treatment and carbohydrate counting. This approach could potentially improve glycaemic control for PwT1D and reduce the burden of carbohydrate and insulin dosage estimations.

Original language	English
Title of host publication	Computer Analysis of Images and Patterns - 20th International Conference, CAIP 2023, Proceedings
Editors	Nicolas Tsapatsoulis, Andreas Lanitis, Marios Pattichis, Constantinos Pattichis, Christos Kyrkou, Efthyvoulos Kyriacou, Zenonas Theodosiou, Andreas Panayides
Publisher	Springer
Publication date	2023
Pages	77-86
ISBN (Print)	978-3-031-44239-1
ISBN (Electronic)	978-3-031-44240-7
DOIs	https://doi.org/10.1007/978-3-031-44240-7_8
Publication status	Published - 2023
Event	20th International Conference on Computer Analysis of Images and Patterns, CAIP 2023 - Limassol, Cyprus Duration: 25 Sep 2023 → 28 Sep 2023

Conference

Conference	20th International Conference on Computer Analysis of Images and Patterns, CAIP 2023
Country/Territory	Cyprus
City	Limassol
Period	25/09/2023 → 28/09/2023

Series	Lecture Notes in Computer Science
Volume	14185
ISSN	0302-9743

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

Keywords

Computer Vision
Deep Learning
Diabetes
Dietary Assessment
Reinforcement Learning

Access to Document

10.1007/978-3-031-44240-7_8

Cite this

Panagiotou, M., Papathanail, I., Rahman, L. A., Brigato, L., Bez, N. S., Vasiloglou, M. F., Stathopoulou, T., de Galan, B. E., Pedersen-Bjergaard, U., van der Horst, K., & Mougiakakou, S. (2023). A Complete AI-Based System for Dietary Assessment and Personalized Insulin Adjustment in Type 1 Diabetes Self-management. In N. Tsapatsoulis, A. Lanitis, M. Pattichis, C. Pattichis, C. Kyrkou, E. Kyriacou, Z. Theodosiou, & A. Panayides (Eds.), Computer Analysis of Images and Patterns - 20th International Conference, CAIP 2023, Proceedings (pp. 77-86). Springer. Lecture Notes in Computer Science Vol. 14185 https://doi.org/10.1007/978-3-031-44240-7_8

A Complete AI-Based System for Dietary Assessment and Personalized Insulin Adjustment in Type 1 Diabetes Self-management. / Panagiotou, Maria; Papathanail, Ioannis; Rahman, Lubnaa Abdur; Brigato, Lorenzo; Bez, Natalie S.; Vasiloglou, Maria F.; Stathopoulou, Thomai; de Galan, Bastiaan E.; Pedersen-Bjergaard, Ulrik; van der Horst, Klazine; Mougiakakou, Stavroula.

Computer Analysis of Images and Patterns - 20th International Conference, CAIP 2023, Proceedings. ed. / Nicolas Tsapatsoulis; Andreas Lanitis; Marios Pattichis; Constantinos Pattichis; Christos Kyrkou; Efthyvoulos Kyriacou; Zenonas Theodosiou; Andreas Panayides. Springer, 2023. p. 77-86 (Lecture Notes in Computer Science, Vol. 14185).

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Panagiotou, M, Papathanail, I, Rahman, LA, Brigato, L, Bez, NS, Vasiloglou, MF, Stathopoulou, T, de Galan, BE, Pedersen-Bjergaard, U, van der Horst, K & Mougiakakou, S 2023, A Complete AI-Based System for Dietary Assessment and Personalized Insulin Adjustment in Type 1 Diabetes Self-management. in N Tsapatsoulis, A Lanitis, M Pattichis, C Pattichis, C Kyrkou, E Kyriacou, Z Theodosiou & A Panayides (eds), Computer Analysis of Images and Patterns - 20th International Conference, CAIP 2023, Proceedings. Springer, Lecture Notes in Computer Science, vol. 14185, pp. 77-86, 20th International Conference on Computer Analysis of Images and Patterns, CAIP 2023, Limassol, Cyprus, 25/09/2023. https://doi.org/10.1007/978-3-031-44240-7_8

Panagiotou M, Papathanail I, Rahman LA, Brigato L, Bez NS, Vasiloglou MF et al. A Complete AI-Based System for Dietary Assessment and Personalized Insulin Adjustment in Type 1 Diabetes Self-management. In Tsapatsoulis N, Lanitis A, Pattichis M, Pattichis C, Kyrkou C, Kyriacou E, Theodosiou Z, Panayides A, editors, Computer Analysis of Images and Patterns - 20th International Conference, CAIP 2023, Proceedings. Springer. 2023. p. 77-86. (Lecture Notes in Computer Science, Vol. 14185). https://doi.org/10.1007/978-3-031-44240-7_8

Panagiotou, Maria ; Papathanail, Ioannis ; Rahman, Lubnaa Abdur ; Brigato, Lorenzo ; Bez, Natalie S. ; Vasiloglou, Maria F. ; Stathopoulou, Thomai ; de Galan, Bastiaan E. ; Pedersen-Bjergaard, Ulrik ; van der Horst, Klazine ; Mougiakakou, Stavroula. / A Complete AI-Based System for Dietary Assessment and Personalized Insulin Adjustment in Type 1 Diabetes Self-management. Computer Analysis of Images and Patterns - 20th International Conference, CAIP 2023, Proceedings. editor / Nicolas Tsapatsoulis ; Andreas Lanitis ; Marios Pattichis ; Constantinos Pattichis ; Christos Kyrkou ; Efthyvoulos Kyriacou ; Zenonas Theodosiou ; Andreas Panayides. Springer, 2023. pp. 77-86 (Lecture Notes in Computer Science, Vol. 14185).

@inproceedings{2b3069a6ca484159a7765e31d03b70f7,

title = "A Complete AI-Based System for Dietary Assessment and Personalized Insulin Adjustment in Type 1 Diabetes Self-management",

abstract = "People living with type 1 diabetes (PwT1D) face multiple challenges in self-managing their blood glucose levels, including the need for accurate carbohydrate counting, and the requirements of adjusting insulin dosage. Our paper aims to alleviate the demands of diabetes self-management by developing a complete system that employs computer vision to estimate the carbohydrate content of meals and utilizes reinforcement learning to personalize insulin dosing. Our findings demonstrate that this system results in a significantly greater percentage of time spent in the target glucose range compared to the combined standard bolus calculator treatment and carbohydrate counting. This approach could potentially improve glycaemic control for PwT1D and reduce the burden of carbohydrate and insulin dosage estimations.",

keywords = "Computer Vision, Deep Learning, Diabetes, Dietary Assessment, Reinforcement Learning",

author = "Maria Panagiotou and Ioannis Papathanail and Rahman, {Lubnaa Abdur} and Lorenzo Brigato and Bez, {Natalie S.} and Vasiloglou, {Maria F.} and Thomai Stathopoulou and {de Galan}, {Bastiaan E.} and Ulrik Pedersen-Bjergaard and {van der Horst}, Klazine and Stavroula Mougiakakou",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.; 20th International Conference on Computer Analysis of Images and Patterns, CAIP 2023 ; Conference date: 25-09-2023 Through 28-09-2023",

year = "2023",

doi = "10.1007/978-3-031-44240-7_8",

language = "English",

isbn = "978-3-031-44239-1",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "77--86",

editor = "Nicolas Tsapatsoulis and Andreas Lanitis and Marios Pattichis and Constantinos Pattichis and Christos Kyrkou and Efthyvoulos Kyriacou and Zenonas Theodosiou and Andreas Panayides",

booktitle = "Computer Analysis of Images and Patterns - 20th International Conference, CAIP 2023, Proceedings",

address = "Switzerland",

}

TY - GEN

T1 - A Complete AI-Based System for Dietary Assessment and Personalized Insulin Adjustment in Type 1 Diabetes Self-management

AU - Panagiotou, Maria

AU - Papathanail, Ioannis

AU - Rahman, Lubnaa Abdur

AU - Brigato, Lorenzo

AU - Bez, Natalie S.

AU - Vasiloglou, Maria F.

AU - Stathopoulou, Thomai

AU - de Galan, Bastiaan E.

AU - Pedersen-Bjergaard, Ulrik

AU - van der Horst, Klazine

AU - Mougiakakou, Stavroula

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

PY - 2023

Y1 - 2023

N2 - People living with type 1 diabetes (PwT1D) face multiple challenges in self-managing their blood glucose levels, including the need for accurate carbohydrate counting, and the requirements of adjusting insulin dosage. Our paper aims to alleviate the demands of diabetes self-management by developing a complete system that employs computer vision to estimate the carbohydrate content of meals and utilizes reinforcement learning to personalize insulin dosing. Our findings demonstrate that this system results in a significantly greater percentage of time spent in the target glucose range compared to the combined standard bolus calculator treatment and carbohydrate counting. This approach could potentially improve glycaemic control for PwT1D and reduce the burden of carbohydrate and insulin dosage estimations.

AB - People living with type 1 diabetes (PwT1D) face multiple challenges in self-managing their blood glucose levels, including the need for accurate carbohydrate counting, and the requirements of adjusting insulin dosage. Our paper aims to alleviate the demands of diabetes self-management by developing a complete system that employs computer vision to estimate the carbohydrate content of meals and utilizes reinforcement learning to personalize insulin dosing. Our findings demonstrate that this system results in a significantly greater percentage of time spent in the target glucose range compared to the combined standard bolus calculator treatment and carbohydrate counting. This approach could potentially improve glycaemic control for PwT1D and reduce the burden of carbohydrate and insulin dosage estimations.

KW - Computer Vision

KW - Deep Learning

KW - Diabetes

KW - Dietary Assessment

KW - Reinforcement Learning

U2 - 10.1007/978-3-031-44240-7_8

DO - 10.1007/978-3-031-44240-7_8

M3 - Article in proceedings

AN - SCOPUS:85174441191

SN - 978-3-031-44239-1

T3 - Lecture Notes in Computer Science

SP - 77

EP - 86

BT - Computer Analysis of Images and Patterns - 20th International Conference, CAIP 2023, Proceedings

A2 - Tsapatsoulis, Nicolas

A2 - Lanitis, Andreas

A2 - Pattichis, Marios

A2 - Pattichis, Constantinos

A2 - Kyrkou, Christos

A2 - Kyriacou, Efthyvoulos

A2 - Theodosiou, Zenonas

A2 - Panayides, Andreas

PB - Springer

T2 - 20th International Conference on Computer Analysis of Images and Patterns, CAIP 2023

Y2 - 25 September 2023 through 28 September 2023

ER -