Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management

Simple item page
dc.contributor.authorLangarica, Saul
dc.contributor.authorDe La Vega, Diego
dc.contributor.authorCariman, Nawel
dc.contributor.authorMiranda, Martin
dc.contributor.authorAndrade, David C.
dc.contributor.authorNunez, Felipe
dc.contributor.authorRodriguez-Fernandez, Maria
dc.date.accessioned2025-01-20T16:15:19Z
dc.date.available2025-01-20T16:15:19Z
dc.date.issued2024
dc.description.abstractAccurate 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.
dc.description.funderAgencia Nacional de Investigacin y Desarrollo
dc.fuente.origenWOS
dc.identifier.doi10.1109/OJEMB.2024.3365290
dc.identifier.eissn2644-1276
dc.identifier.urihttps://doi.org/10.1109/OJEMB.2024.3365290
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/90488
dc.identifier.wosidWOS:001246168200007
dc.language.isoen
dc.pagina.final475
dc.pagina.inicio467
dc.revistaIeee open journal of engineering in medicine and biology
dc.rightsacceso restringido
dc.subjectGlucose
dc.subjectInsulin
dc.subjectPredictive models
dc.subjectDiabetes
dc.subjectBlood
dc.subjectBiomedical monitoring
dc.subjectData models
dc.subjectGlucose prediction
dc.subjectdeep learning
dc.subjecttransfer learning
dc.subject.ods03 Good Health and Well-being
dc.subject.odspa03 Salud y bienestar
dc.titleDeep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management
dc.typeartículo
dc.volumen5
sipa.indexWOS
sipa.trazabilidadWOS;2025-01-12
Files
Collections
Artículos de revistas