Cargando…

Ensemble Models of Cutting-Edge Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes

This article proposes two ensemble neural network-based models for blood glucose prediction at three different prediction horizons—30, 60, and 120 min—and compares their performance with ten recently proposed neural networks. The twelve models’ performances are evaluated under the same OhioT1DM Data...

Descripción completa

Detalles Bibliográficos
Autores principales: Tena, Félix, Garnica, Oscar, Lanchares, Juan, Hidalgo, Jose Ignacio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8588394/
https://www.ncbi.nlm.nih.gov/pubmed/34770397
http://dx.doi.org/10.3390/s21217090
_version_ 1784598446331658240
author Tena, Félix
Garnica, Oscar
Lanchares, Juan
Hidalgo, Jose Ignacio
author_facet Tena, Félix
Garnica, Oscar
Lanchares, Juan
Hidalgo, Jose Ignacio
author_sort Tena, Félix
collection PubMed
description This article proposes two ensemble neural network-based models for blood glucose prediction at three different prediction horizons—30, 60, and 120 min—and compares their performance with ten recently proposed neural networks. The twelve models’ performances are evaluated under the same OhioT1DM Dataset, preprocessing workflow, and tools at the three prediction horizons using the most common metrics in blood glucose prediction, and we rank the best-performing ones using three methods devised for the statistical comparison of the performance of multiple algorithms: scmamp, model confidence set, and superior predictive ability. Our analysis provides a comparison of the state-of-the-art neural networks for blood glucose prediction, estimating the model’s error, highlighting those with the highest probability of being the best predictors, and providing a guide for their use in clinical practice.
format Online
Article
Text
id pubmed-8588394
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-85883942021-11-13 Ensemble Models of Cutting-Edge Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes Tena, Félix Garnica, Oscar Lanchares, Juan Hidalgo, Jose Ignacio Sensors (Basel) Article This article proposes two ensemble neural network-based models for blood glucose prediction at three different prediction horizons—30, 60, and 120 min—and compares their performance with ten recently proposed neural networks. The twelve models’ performances are evaluated under the same OhioT1DM Dataset, preprocessing workflow, and tools at the three prediction horizons using the most common metrics in blood glucose prediction, and we rank the best-performing ones using three methods devised for the statistical comparison of the performance of multiple algorithms: scmamp, model confidence set, and superior predictive ability. Our analysis provides a comparison of the state-of-the-art neural networks for blood glucose prediction, estimating the model’s error, highlighting those with the highest probability of being the best predictors, and providing a guide for their use in clinical practice. MDPI 2021-10-26 /pmc/articles/PMC8588394/ /pubmed/34770397 http://dx.doi.org/10.3390/s21217090 Text en © 2021 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
Tena, Félix
Garnica, Oscar
Lanchares, Juan
Hidalgo, Jose Ignacio
Ensemble Models of Cutting-Edge Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes
title Ensemble Models of Cutting-Edge Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes
title_full Ensemble Models of Cutting-Edge Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes
title_fullStr Ensemble Models of Cutting-Edge Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes
title_full_unstemmed Ensemble Models of Cutting-Edge Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes
title_short Ensemble Models of Cutting-Edge Deep Neural Networks for Blood Glucose Prediction in Patients with Diabetes
title_sort ensemble models of cutting-edge deep neural networks for blood glucose prediction in patients with diabetes
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8588394/
https://www.ncbi.nlm.nih.gov/pubmed/34770397
http://dx.doi.org/10.3390/s21217090
work_keys_str_mv AT tenafelix ensemblemodelsofcuttingedgedeepneuralnetworksforbloodglucosepredictioninpatientswithdiabetes
AT garnicaoscar ensemblemodelsofcuttingedgedeepneuralnetworksforbloodglucosepredictioninpatientswithdiabetes
AT lancharesjuan ensemblemodelsofcuttingedgedeepneuralnetworksforbloodglucosepredictioninpatientswithdiabetes
AT hidalgojoseignacio ensemblemodelsofcuttingedgedeepneuralnetworksforbloodglucosepredictioninpatientswithdiabetes