Population-Specific Glucose Prediction in Diabetes Care With Transformer-Based Deep Learning on the Edge
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.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:18 |
|---|---|
| Enthalten in: |
IEEE transactions on biomedical circuits and systems - 18(2024), 2 vom: 30. Apr., Seite 236-246 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Zhu, Taiyu [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 03.04.2024 Date Revised 03.04.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1109/TBCAS.2023.3348844 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM366539396 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM366539396 | ||
| 003 | DE-627 | ||
| 005 | 20240403235156.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240108s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TBCAS.2023.3348844 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1363.xml |
| 035 | |a (DE-627)NLM366539396 | ||
| 035 | |a (NLM)38163299 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Zhu, Taiyu |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Population-Specific Glucose Prediction in Diabetes Care With Transformer-Based Deep Learning on the Edge |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 03.04.2024 | ||
| 500 | |a Date Revised 03.04.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a 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 | ||
| 650 | 4 | |a Journal Article | |
| 650 | 7 | |a Glucose |2 NLM | |
| 650 | 7 | |a IY9XDZ35W2 |2 NLM | |
| 650 | 7 | |a Blood Glucose |2 NLM | |
| 700 | 1 | |a Kuang, Lei |e verfasserin |4 aut | |
| 700 | 1 | |a Piao, Chengzhe |e verfasserin |4 aut | |
| 700 | 1 | |a Zeng, Junming |e verfasserin |4 aut | |
| 700 | 1 | |a Li, Kezhi |e verfasserin |4 aut | |
| 700 | 1 | |a Georgiou, Pantelis |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on biomedical circuits and systems |d 2007 |g 18(2024), 2 vom: 30. Apr., Seite 236-246 |w (DE-627)NLM192068652 |x 1940-9990 |7 nnns |
| 773 | 1 | 8 | |g volume:18 |g year:2024 |g number:2 |g day:30 |g month:04 |g pages:236-246 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TBCAS.2023.3348844 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 18 |j 2024 |e 2 |b 30 |c 04 |h 236-246 | ||