UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Population-Specific Glucose Prediction in Diabetes Care With Transformer-Based Deep Learning on the Edge

Zhu, Taiyu; Kuang, Lei; Piao, Chengzhe; Zeng, Junming; Li, Kezhi; Georgiou, Pantelis; (2024) Population-Specific Glucose Prediction in Diabetes Care With Transformer-Based Deep Learning on the Edge. IEEE Transactions on Biomedical Circuits and Systems pp. 1-12. 10.1109/tbcas.2023.3348844. (In press). Green open access

[thumbnail of Population-Specific_Glucose_Prediction_in_Diabetes_Care_With_Transformer-Based_Deep_Learning_on_the_Edge.pdf]
Preview
Text
Population-Specific_Glucose_Prediction_in_Diabetes_Care_With_Transformer-Based_Deep_Learning_on_the_Edge.pdf - Accepted Version

Download (4MB) | Preview

Abstract

Leveraging continuous glucose monitoring (CGM) systems, real-time blood glucose (BG) forecasting is essential for proactive interventions, playing a crucial role in enhancing the management of type 1 diabetes (T1D) and type 2 diabetes (T2D). However, developing a model generalized to a population and subsequently embedding it within a microchip of a wearable device presents significant technical challenges. Furthermore, the domain of BG prediction in T2D remains under-explored in the literature. In light of this, we propose a population-specific BG prediction model, leveraging the capabilities of the temporal fusion Transformer (TFT) to adjust predictions based on personal demographic data. Then the trained model is embedded within a system-on-chip, integral to our low-power and low-cost customized wearable device. This device seamlessly communicates with CGM systems through Bluetooth and provides timely BG predictions using edge computing. When evaluated on two publicly available clinical datasets with a total of 124 participants with T1D or T2D, the embedded TFT model consistently demonstrated superior performance, achieving the lowest prediction errors when compared with a range of machine learning baseline methods. Executing the TFT model on our wearable device requires minimal memory and power consumption, enabling continuous decision support for more than 51 days on a single Li-Poly battery charge. These findings demonstrate the significant potential of the proposed TFT model and wearable device in enhancing the quality of life for people with diabetes and effectively addressing real-world challenges.

Type: Article
Title: Population-Specific Glucose Prediction in Diabetes Care With Transformer-Based Deep Learning on the Edge
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/tbcas.2023.3348844
Publisher version: http://dx.doi.org/10.1109/tbcas.2023.3348844
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Artificial intelligence, deep learning, diabetes, edge computing, glucose prediction, low power wearable device, Transformer
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Population Health Sciences > Institute of Health Informatics
URI: https://discovery.ucl.ac.uk/id/eprint/10185625
Downloads since deposit
70Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item