Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management
Accurate short- and mid-term blood glucose predictions are crucial for patients with diabetes struggling to maintain healthy glucose levels, as well as for individuals at risk of developing the disease. Consequently, numerous efforts from the scientific community have focused on developing predictiv...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Engineering in Medicine and Biology |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10433750/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582286244052992 |
|---|---|
| author | Saul Langarica Diego de la Vega Nawel Cariman Martin Miranda David C. Andrade Felipe Nunez Maria Rodriguez-Fernandez |
| author_facet | Saul Langarica Diego de la Vega Nawel Cariman Martin Miranda David C. Andrade Felipe Nunez Maria Rodriguez-Fernandez |
| author_sort | Saul Langarica |
| collection | DOAJ |
| description | Accurate short- and mid-term blood glucose predictions are crucial for patients with diabetes struggling to maintain healthy glucose levels, as well as for individuals at risk of developing the disease. Consequently, numerous efforts from the scientific community have focused on developing predictive models for glucose levels. This study harnesses physiological data collected from wearable sensors to construct a series of data-driven models based on deep learning approaches. We systematically compare these models to offer insights for practitioners and researchers venturing into glucose prediction using deep learning techniques. Key questions addressed in this work encompass the comparison of various deep learning architectures for this task, determining the optimal set of input variables for accurate glucose prediction, comparing population-wide, fine-tuned, and personalized models, and assessing the impact of an individual's data volume on model performance. Additionally, as part of our outcomes, we introduce a meticulously curated dataset inclusive of data from both healthy individuals and those with diabetes, recorded in free-living conditions. This dataset aims to foster research in this domain and facilitate equitable comparisons among researchers. |
| format | Article |
| id | doaj-art-1616b5cdea9d47c1a41a881a99bfaba8 |
| institution | Kabale University |
| issn | 2644-1276 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Engineering in Medicine and Biology |
| spelling | doaj-art-1616b5cdea9d47c1a41a881a99bfaba82025-01-30T00:03:50ZengIEEEIEEE Open Journal of Engineering in Medicine and Biology2644-12762024-01-01546747510.1109/OJEMB.2024.336529010433750Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes ManagementSaul Langarica0https://orcid.org/0000-0002-1763-0135Diego de la Vega1https://orcid.org/0009-0005-8509-3385Nawel Cariman2https://orcid.org/0009-0001-3611-5745Martin Miranda3https://orcid.org/0000-0001-8587-1531David C. Andrade4https://orcid.org/0000-0003-2006-1444Felipe Nunez5https://orcid.org/0000-0002-8741-717XMaria Rodriguez-Fernandez6https://orcid.org/0000-0003-1966-2920Department of Electrical Engineering, Pontificia Universidad Católica de Chile, Santiago, ChileInstitute for Biological and Medical Engineering, Schools of Engineering, Medicine and Biological Sciences, Pontificia Universidad Católica de Chile, Santiago, ChileDepartment of Electrical Engineering, Pontificia Universidad Católica de Chile, Santiago, ChileInstitute for Biological and Medical Engineering, Schools of Engineering, Medicine and Biological Sciences, Pontificia Universidad Católica de Chile, Santiago, ChileCentro de Investigación en Fisiología y Medicina de Altura, Facultad de Ciencias de la Salud, Universidad de Antofagasta, Antofagasta, ChileDepartment of Electrical Engineering, Pontificia Universidad Católica de Chile, Santiago, ChileInstitute for Biological and Medical Engineering, Schools of Engineering, Medicine and Biological Sciences, Pontificia Universidad Católica de Chile, Santiago, ChileAccurate short- and mid-term blood glucose predictions are crucial for patients with diabetes struggling to maintain healthy glucose levels, as well as for individuals at risk of developing the disease. Consequently, numerous efforts from the scientific community have focused on developing predictive models for glucose levels. This study harnesses physiological data collected from wearable sensors to construct a series of data-driven models based on deep learning approaches. We systematically compare these models to offer insights for practitioners and researchers venturing into glucose prediction using deep learning techniques. Key questions addressed in this work encompass the comparison of various deep learning architectures for this task, determining the optimal set of input variables for accurate glucose prediction, comparing population-wide, fine-tuned, and personalized models, and assessing the impact of an individual's data volume on model performance. Additionally, as part of our outcomes, we introduce a meticulously curated dataset inclusive of data from both healthy individuals and those with diabetes, recorded in free-living conditions. This dataset aims to foster research in this domain and facilitate equitable comparisons among researchers.https://ieeexplore.ieee.org/document/10433750/DiabetesGlucose predictiondeep learningtransfer learning |
| spellingShingle | Saul Langarica Diego de la Vega Nawel Cariman Martin Miranda David C. Andrade Felipe Nunez Maria Rodriguez-Fernandez Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management IEEE Open Journal of Engineering in Medicine and Biology Diabetes Glucose prediction deep learning transfer learning |
| title | Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management |
| title_full | Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management |
| title_fullStr | Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management |
| title_full_unstemmed | Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management |
| title_short | Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management |
| title_sort | deep learning based glucose prediction models a guide for practitioners and a curated dataset for improved diabetes management |
| topic | Diabetes Glucose prediction deep learning transfer learning |
| url | https://ieeexplore.ieee.org/document/10433750/ |
| work_keys_str_mv | AT saullangarica deeplearningbasedglucosepredictionmodelsaguideforpractitionersandacurateddatasetforimproveddiabetesmanagement AT diegodelavega deeplearningbasedglucosepredictionmodelsaguideforpractitionersandacurateddatasetforimproveddiabetesmanagement AT nawelcariman deeplearningbasedglucosepredictionmodelsaguideforpractitionersandacurateddatasetforimproveddiabetesmanagement AT martinmiranda deeplearningbasedglucosepredictionmodelsaguideforpractitionersandacurateddatasetforimproveddiabetesmanagement AT davidcandrade deeplearningbasedglucosepredictionmodelsaguideforpractitionersandacurateddatasetforimproveddiabetesmanagement AT felipenunez deeplearningbasedglucosepredictionmodelsaguideforpractitionersandacurateddatasetforimproveddiabetesmanagement AT mariarodriguezfernandez deeplearningbasedglucosepredictionmodelsaguideforpractitionersandacurateddatasetforimproveddiabetesmanagement |