Generalizing CGM Sensor-Based Glucose Prediction across Age Cohorts Using LSTM Models: An In Silico Study with the UVA/Padova T1DMS Simulator.
Saved in:
| Title: | Generalizing CGM Sensor-Based Glucose Prediction across Age Cohorts Using LSTM Models: An In Silico Study with the UVA/Padova T1DMS Simulator. |
|---|---|
| Authors: | Alzahrani, Saleh I.1 sialzahrani@iau.edu.sa |
| Source: | International Journal of Online & Biomedical Engineering. 2026, Vol. 22 Issue 4, p76-93. 18p. |
| Subjects: | Age groups, Recurrent neural networks, Blood sugar analysis, Type 1 diabetes, University of Virginia, Deep learning, Aging, Insulin therapy |
| Abstract: | Accurate glucose prediction is necessary in enhancing insulin therapy and preventing harmful blood-sugar spikes in individuals with type 1 diabetes (T1D). Although deep learning models seem promising for glucose forecasting, it is unclear how they perform across various age groups that exhibit different metabolism profiles. This paper compares the performance of the long short-term memory (LSTM) models across age groups using simulated data from the UVA/Padova T1D Metabolic Simulator (T1DMS). Cohort-specific models achieved high within-cohort performance (MAE < 2 mg/dL, r > 0.99, R² > 0.99), indicating precise modeling of glucose-insulin dynamics within each group. Nevertheless, predictive accuracy decreased when models were applied across cohorts, especially when LSTM networks trained on adults were tested on younger groups, demonstrating physiological variability between ages in insulin sensitivity and glucose kinetics. Models trained on younger groups performed better on older populations, suggesting that a broader range of metabolic variation underlies increased adaptability. This study is the first to use the FDA-approved UVA/Padova T1DMS simulator to systematically assess age-dependent generalization in LSTM-based glucose prediction, offering a unique reproducible framework for developing adaptive e-health and closed-loop insulin systems. Incorporating age-relevant physiological heterogeneity and adaptive modeling paradigms could help develop stronger, patient-specific glucose forecasting systems for safer and more effective diabetes management. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Online & Biomedical Engineering is the property of International Journal of Online Engineering and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 192869160 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Generalizing CGM Sensor-Based Glucose Prediction across Age Cohorts Using LSTM Models: An In Silico Study with the UVA/Padova T1DMS Simulator. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Alzahrani%2C+Saleh+I%2E%22">Alzahrani, Saleh I.</searchLink><relatesTo>1</relatesTo><i> sialzahrani@iau.edu.sa</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Online+%26+Biomedical+Engineering%22">International Journal of Online & Biomedical Engineering</searchLink>. 2026, Vol. 22 Issue 4, p76-93. 18p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Age+groups%22">Age groups</searchLink><br /><searchLink fieldCode="DE" term="%22Recurrent+neural+networks%22">Recurrent neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Blood+sugar+analysis%22">Blood sugar analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Type+1+diabetes%22">Type 1 diabetes</searchLink><br /><searchLink fieldCode="DE" term="%22University+of+Virginia%22">University of Virginia</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Aging%22">Aging</searchLink><br /><searchLink fieldCode="DE" term="%22Insulin+therapy%22">Insulin therapy</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Accurate glucose prediction is necessary in enhancing insulin therapy and preventing harmful blood-sugar spikes in individuals with type 1 diabetes (T1D). Although deep learning models seem promising for glucose forecasting, it is unclear how they perform across various age groups that exhibit different metabolism profiles. This paper compares the performance of the long short-term memory (LSTM) models across age groups using simulated data from the UVA/Padova T1D Metabolic Simulator (T1DMS). Cohort-specific models achieved high within-cohort performance (MAE < 2 mg/dL, r > 0.99, R² > 0.99), indicating precise modeling of glucose-insulin dynamics within each group. Nevertheless, predictive accuracy decreased when models were applied across cohorts, especially when LSTM networks trained on adults were tested on younger groups, demonstrating physiological variability between ages in insulin sensitivity and glucose kinetics. Models trained on younger groups performed better on older populations, suggesting that a broader range of metabolic variation underlies increased adaptability. This study is the first to use the FDA-approved UVA/Padova T1DMS simulator to systematically assess age-dependent generalization in LSTM-based glucose prediction, offering a unique reproducible framework for developing adaptive e-health and closed-loop insulin systems. Incorporating age-relevant physiological heterogeneity and adaptive modeling paradigms could help develop stronger, patient-specific glucose forecasting systems for safer and more effective diabetes management. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of Online & Biomedical Engineering is the property of International Journal of Online Engineering and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192869160 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3991/ijoe.v22i04.60113 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 18 StartPage: 76 Subjects: – SubjectFull: Age groups Type: general – SubjectFull: Recurrent neural networks Type: general – SubjectFull: Blood sugar analysis Type: general – SubjectFull: Type 1 diabetes Type: general – SubjectFull: University of Virginia Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Aging Type: general – SubjectFull: Insulin therapy Type: general Titles: – TitleFull: Generalizing CGM Sensor-Based Glucose Prediction across Age Cohorts Using LSTM Models: An In Silico Study with the UVA/Padova T1DMS Simulator. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Alzahrani, Saleh I. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 03 Text: 2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 26268493 Numbering: – Type: volume Value: 22 – Type: issue Value: 4 Titles: – TitleFull: International Journal of Online & Biomedical Engineering Type: main |
| ResultId | 1 |
