A hybrid Transformer-LSTM model apply to glucose prediction
PLOS ONE · 11.09.2024 · 19 (9) · e0310084
DOI: 10.1371/journal.pone.0310084 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 11.09.2024. Verfasst von QingXiang Bian und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical and Manufacturing Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang, Malaysia. Hauptthemen laut MEDLINE: Blood Glucose. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Malaysia Fundamental Research Grant Scheme, Malaysian Ministry of Higher Education, Universiti Putra Malaysia.
Abstract (Originalsprache)
The global prevalence of diabetes is escalating, with estimates indicating that over 536.6 million individuals were afflicted by 2021, accounting for approximately 10.5% of the world’s population. Effective management of diabetes, particularly monitoring and prediction of blood glucose levels, remains a significant challenge due to the severe health risks associated with inaccuracies, such as hypoglycemia and hyperglycemia. This study addresses this critical issue by employing a hybrid Transformer-LSTM (Long Short-Term Memory) model designed to enhance the accuracy of future glucose level predictions based on data from Continuous Glucose Monitoring (CGM) systems. This innovative approach aims to reduce the risk of diabetic complications and improve patient outcomes. We utilized a dataset which contain more than 32000 data points comprising CGM data from eight patients collected by Suzhou Municipal Hospital in Jiangsu Province, China. This dataset includes historical glucose readings and equipment calibration values, making it highly suitable for developing predictive models due to its richness and real-time applicability. Our findings demonstrate that the hybrid Transformer-LSTM model significantly outperforms the standard LSTM model, achieving Mean Square Error (MSE) values of 1.18, 1.70, and 2.00 at forecasting intervals of 15, 30, and 45 minutes, respectively. This research underscores the potential of advanced machine learning techniques in the proactive management of diabetes, a critical step toward mitigating its impact.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Mechanical and Manufacturing Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang, Malaysia.
- Department of Endocrinology, Suzhou Municipal Hospital, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou, China.
- Department of Electric and Electronics Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang, Malaysia.
ORCID-Profile: QingXiang Bian, Azizan As'arry, XiangGuo Cong, Raja Mohd Kamil Bin Raja Ahmad
Förderung
- Malaysia Fundamental Research Grant Scheme
- Malaysian Ministry of Higher Education
- Universiti Putra Malaysia
- Suzhou Municipal Hospital
Zitieren
APA
Bian, Q., As'arry, A., Cong, X., Rezali, K. A. B. M., & Raja Ahmad, R. M. K. B. (2024). A hybrid Transformer-LSTM model apply to glucose prediction. PLOS ONE, 19(9), e0310084. https://doi.org/10.1371/journal.pone.0310084
Vancouver
Bian Q, As'arry A, Cong X, Rezali KABM, Raja Ahmad RMKB. A hybrid Transformer-LSTM model apply to glucose prediction. PLOS ONE. 2024;19(9):e0310084. doi:10.1371/journal.pone.0310084
BibTeX
@article{Bian2024,
author = {Bian, QingXiang and As'arry, Azizan and Cong, XiangGuo and Rezali, Khairil Anas Bin Md and Raja Ahmad, Raja Mohd Kamil Bin},
title = {A hybrid Transformer-LSTM model apply to glucose prediction},
journal = {PLOS ONE},
year = {2024},
volume = {19},
number = {9},
pages = {e0310084},
doi = {10.1371/journal.pone.0310084}
}
EUVIMED