Cargando…

Assessment of Seasonal Stochastic Local Models for Glucose Prediction without Meal Size Information under Free-Living Conditions

Accurate blood glucose (BG) forecasting is key in diabetes management, as it allows preventive actions to mitigate harmful hypoglycemic/hyperglycemic episodes. Considering the encouraging results obtained by seasonal stochastic models in proof-of-concept studies, this work assesses the methodology i...

Descripción completa

Detalles Bibliográficos
Autores principales: Prendin, Francesco, Díez, José-Luis, Del Favero, Simone, Sparacino, Giovanni, Facchinetti, Andrea, Bondia, Jorge
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9694694/
https://www.ncbi.nlm.nih.gov/pubmed/36433278
http://dx.doi.org/10.3390/s22228682
_version_ 1784837867154964480
author Prendin, Francesco
Díez, José-Luis
Del Favero, Simone
Sparacino, Giovanni
Facchinetti, Andrea
Bondia, Jorge
author_facet Prendin, Francesco
Díez, José-Luis
Del Favero, Simone
Sparacino, Giovanni
Facchinetti, Andrea
Bondia, Jorge
author_sort Prendin, Francesco
collection PubMed
description Accurate blood glucose (BG) forecasting is key in diabetes management, as it allows preventive actions to mitigate harmful hypoglycemic/hyperglycemic episodes. Considering the encouraging results obtained by seasonal stochastic models in proof-of-concept studies, this work assesses the methodology in two datasets (open-loop and closed-loop) recorded in free-living conditions. First, similar postprandial glycemic profiles are grouped together with fuzzy C-means clustering. Then, a seasonal stochastic model is identified for each cluster. Finally, real-time BG forecasting is performed by weighting each model’s prediction. The proposed methodology (named C-SARIMA) is compared to other linear and nonlinear black-box methods: autoregressive integrated moving average (ARIMA), its variant with input (ARIMAX), a feed-forward neural network (NN), and its modified version (NN-X) fed by BG, insulin, and carbohydrates (timing and dosing) information for several prediction horizons (PHs). In the open-loop dataset, C-SARIMA grants a median root-mean-squared error (RMSE) of 20.13 mg/dL (PH = 30) and 27.23 mg/dL (PH = 45), not significantly different from ARIMA and NN. Over a longer PH, C-SARIMA achieves an RMSE = 31.96 mg/dL (PH = 60) and RMSE = 33.91 mg/dL (PH = 75), significantly outperforming the ARIMA and NN, without significant differences from the ARIMAX for PH ≥ 45 and the NN-X for PH ≥ 60. Similar results hold on the closed-loop dataset: for PH = 30 and 45 min, the C-SARIMA achieves an RMSE = 21.63 mg/dL and RMSE = 29.67 mg/dL, not significantly different from the ARIMA and NN. On longer PH, the C-SARIMA outperforms the ARIMA for PH > 45 and the NN for PH > 60 without significant differences from the ARIMAX for PH ≥ 45. Although using less input information, the C-SARIMA achieves similar performance to other prediction methods such as the ARIMAX and NN-X and outperforming the CGM-only approaches on PH > 45min.
format Online
Article
Text
id pubmed-9694694
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96946942022-11-26 Assessment of Seasonal Stochastic Local Models for Glucose Prediction without Meal Size Information under Free-Living Conditions Prendin, Francesco Díez, José-Luis Del Favero, Simone Sparacino, Giovanni Facchinetti, Andrea Bondia, Jorge Sensors (Basel) Article Accurate blood glucose (BG) forecasting is key in diabetes management, as it allows preventive actions to mitigate harmful hypoglycemic/hyperglycemic episodes. Considering the encouraging results obtained by seasonal stochastic models in proof-of-concept studies, this work assesses the methodology in two datasets (open-loop and closed-loop) recorded in free-living conditions. First, similar postprandial glycemic profiles are grouped together with fuzzy C-means clustering. Then, a seasonal stochastic model is identified for each cluster. Finally, real-time BG forecasting is performed by weighting each model’s prediction. The proposed methodology (named C-SARIMA) is compared to other linear and nonlinear black-box methods: autoregressive integrated moving average (ARIMA), its variant with input (ARIMAX), a feed-forward neural network (NN), and its modified version (NN-X) fed by BG, insulin, and carbohydrates (timing and dosing) information for several prediction horizons (PHs). In the open-loop dataset, C-SARIMA grants a median root-mean-squared error (RMSE) of 20.13 mg/dL (PH = 30) and 27.23 mg/dL (PH = 45), not significantly different from ARIMA and NN. Over a longer PH, C-SARIMA achieves an RMSE = 31.96 mg/dL (PH = 60) and RMSE = 33.91 mg/dL (PH = 75), significantly outperforming the ARIMA and NN, without significant differences from the ARIMAX for PH ≥ 45 and the NN-X for PH ≥ 60. Similar results hold on the closed-loop dataset: for PH = 30 and 45 min, the C-SARIMA achieves an RMSE = 21.63 mg/dL and RMSE = 29.67 mg/dL, not significantly different from the ARIMA and NN. On longer PH, the C-SARIMA outperforms the ARIMA for PH > 45 and the NN for PH > 60 without significant differences from the ARIMAX for PH ≥ 45. Although using less input information, the C-SARIMA achieves similar performance to other prediction methods such as the ARIMAX and NN-X and outperforming the CGM-only approaches on PH > 45min. MDPI 2022-11-10 /pmc/articles/PMC9694694/ /pubmed/36433278 http://dx.doi.org/10.3390/s22228682 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Prendin, Francesco
Díez, José-Luis
Del Favero, Simone
Sparacino, Giovanni
Facchinetti, Andrea
Bondia, Jorge
Assessment of Seasonal Stochastic Local Models for Glucose Prediction without Meal Size Information under Free-Living Conditions
title Assessment of Seasonal Stochastic Local Models for Glucose Prediction without Meal Size Information under Free-Living Conditions
title_full Assessment of Seasonal Stochastic Local Models for Glucose Prediction without Meal Size Information under Free-Living Conditions
title_fullStr Assessment of Seasonal Stochastic Local Models for Glucose Prediction without Meal Size Information under Free-Living Conditions
title_full_unstemmed Assessment of Seasonal Stochastic Local Models for Glucose Prediction without Meal Size Information under Free-Living Conditions
title_short Assessment of Seasonal Stochastic Local Models for Glucose Prediction without Meal Size Information under Free-Living Conditions
title_sort assessment of seasonal stochastic local models for glucose prediction without meal size information under free-living conditions
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9694694/
https://www.ncbi.nlm.nih.gov/pubmed/36433278
http://dx.doi.org/10.3390/s22228682
work_keys_str_mv AT prendinfrancesco assessmentofseasonalstochasticlocalmodelsforglucosepredictionwithoutmealsizeinformationunderfreelivingconditions
AT diezjoseluis assessmentofseasonalstochasticlocalmodelsforglucosepredictionwithoutmealsizeinformationunderfreelivingconditions
AT delfaverosimone assessmentofseasonalstochasticlocalmodelsforglucosepredictionwithoutmealsizeinformationunderfreelivingconditions
AT sparacinogiovanni assessmentofseasonalstochasticlocalmodelsforglucosepredictionwithoutmealsizeinformationunderfreelivingconditions
AT facchinettiandrea assessmentofseasonalstochasticlocalmodelsforglucosepredictionwithoutmealsizeinformationunderfreelivingconditions
AT bondiajorge assessmentofseasonalstochasticlocalmodelsforglucosepredictionwithoutmealsizeinformationunderfreelivingconditions