Publication:
Deep physiological model for blood glucose prediction in T1DM patients

Simple item page
dc.affiliation.dptoUC3M. Departamento de Ingeniería Telemáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Aplicaciones y Servicios Telemáticos (GAST)es
dc.affiliation.institutoUC3M. Instituto UC3M - Santander de Big Dataes
dc.contributor.authorMuñoz Organero, Mario
dc.contributor.funderMinisterio de Economía y Competitividad (España)es
dc.date.accessioned2021-02-25T10:35:06Z
dc.date.available2021-02-25T10:35:06Z
dc.date.issued2020-07-13
dc.description.abstractAccurate estimations for the near future levels of blood glucose are crucial for Type 1 Diabetes Mellitus (T1DM) patients in order to be able to react on time and avoid hypo and hyper-glycemic episodes. Accurate predictions for blood glucose are the base for control algorithms in glucose regulating systems such as the artificial pancreas. Numerous research studies have already been conducted in order to provide predictions for blood glucose levels with particularities in the input signals and underlying models used. These models can be categorized into two major families: those based on tuning glucose physiological-metabolic models and those based on learning glucose evolution patterns based on machine learning techniques. This paper reviews the state of the art in blood glucose predictions for T1DM patients and proposes, implements, validates and compares a new hybrid model that decomposes a deep machine learning model in order to mimic the metabolic behavior of physiological blood glucose methods. The differential equations for carbohydrate and insulin absorption in physiological models are modeled using a Recurrent Neural Network (RNN) implemented using Long Short-Term Memory (LSTM) cells. The results show Root Mean Square Error (RMSE) values under 5 mg/dL for simulated patients and under 10 mg/dL for real patients.en
dc.description.sponsorshipThis work was supported by the "ANALYTICS USING SENSOR DATA FOR FLATCITY"; Project (MINECO/ERDF, EU) funded in part by the Spanish Agencia Estatal de InvestigaciĂłn (AEI) under Grant TIN2016-77158-C4-1-R and in part by the European Regional Development Fund (ERDF).en
dc.format.extent17es
dc.identifier.bibliographicCitationSensors, 20(14), 3896, July 2020, 17 pp.en
dc.identifier.doihttps://doi.org/10.3390/s20143896
dc.identifier.issn1424-8220
dc.identifier.publicationfirstpage1es
dc.identifier.publicationissue14, 3896es
dc.identifier.publicationlastpage17es
dc.identifier.publicationtitleSENSORSen
dc.identifier.publicationvolume20es
dc.identifier.urihttps://hdl.handle.net/10016/32022
dc.identifier.uxxiAR/0000026214
dc.language.isoengen
dc.publisherMDPIen
dc.relation.datasethttps://doi.org/10.21950/MMVBUJ
dc.relation.projectIDGobierno de España. TIN2016-77158-C4-1-Res
dc.rights© 2020 by the author. Licensee MDPI, Basel, Switzerland.en
dc.rightsThis article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) licenseen
dc.rightsAtribución 3.0 Españaes
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/es/*
dc.subject.ecienciaBiologĂ­a y Biomedicinaes
dc.subject.ecienciaInformáticaes
dc.subject.otherBlood glucose predictionen
dc.subject.otherType 1 Diabetes mellitusen
dc.subject.otherDeep machine learningen
dc.subject.otherPhysiological modelsen
dc.titleDeep physiological model for blood glucose prediction in T1DM patientsen
dc.typeresearch article*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
deep_SENSORS_2020.pdf
Size:
662.24 KB
Format:
Adobe Portable Document Format
Download
Collections
DIT - GAST - ArtĂ­culos de Revistas
USBDI - ArtĂ­culos de Revistas