Continuous Glucose Monitoring in Diabetes Patients: An LSTM-Based Predictive Approach
Meriem, Lefkir; Lamya, Fergani; Mourad, Oussalah (2024-12-12)
IEEE
12.12.2024
L. Meriem, F. Lamya and O. Mourad, "Continuous Glucose Monitoring in Diabetes Patients: An LSTM-Based Predictive Approach," 2024 3rd International Conference on Advanced Electrical Engineering (ICAEE), Sidi-Bel-Abbes, Algeria, 2024, pp. 1-6, doi: 10.1109/ICAEE61760.2024.10783291.
https://rightsstatements.org/vocab/InC/1.0/
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202501281365
https://urn.fi/URN:NBN:fi:oulu-202501281365
Tiivistelmä
Abstract
Managing blood glucose levels is critically essential in the care of individuals with type 1 diabetes mellitus (T1DM), through appropriate medication, physical activities, and continuous glucose monitoring(CGM). The development of wearable technologies has emerged to monitor glucose continuously and administer insulin when necessary, allowing patients to tracktheir glucose levels easily, with swift intervention, and avoiding hospitalization. This work explores a novel deep-learning model to predict future blood glucose levels at different prediction horizons 5, 15, 30, and 60 minutes. We've proposed a bloodglucose prediction systems based on Long Short Term Memory (LSTM) networks, and we compare its performance to a baseline model (Simple Recurrent Neural Network).Our experimental results on D1NAMO dataset containing CGM data showed that the proposed LSTM model leads to improved blood glucose prediction accuracy measures compared to the baseline model.
Managing blood glucose levels is critically essential in the care of individuals with type 1 diabetes mellitus (T1DM), through appropriate medication, physical activities, and continuous glucose monitoring(CGM). The development of wearable technologies has emerged to monitor glucose continuously and administer insulin when necessary, allowing patients to tracktheir glucose levels easily, with swift intervention, and avoiding hospitalization. This work explores a novel deep-learning model to predict future blood glucose levels at different prediction horizons 5, 15, 30, and 60 minutes. We've proposed a bloodglucose prediction systems based on Long Short Term Memory (LSTM) networks, and we compare its performance to a baseline model (Simple Recurrent Neural Network).Our experimental results on D1NAMO dataset containing CGM data showed that the proposed LSTM model leads to improved blood glucose prediction accuracy measures compared to the baseline model.
Kokoelmat
- Avoin saatavuus [38824]