Cargando…

LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management

To avoid serious diabetic complications, people with type 1 diabetes must keep their blood glucose levels (BGLs) as close to normal as possible. Insulin dosages and carbohydrate consumption are important considerations in managing BGLs. Since the 1960s, models have been developed to forecast blood g...

Descripción completa

Detalles Bibliográficos
Autores principales: Beauchamp, Jeremy, Bunescu, Razvan, Marling, Cindy, Li, Zhongen, Liu, Chang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8126192/
https://www.ncbi.nlm.nih.gov/pubmed/34068808
http://dx.doi.org/10.3390/s21093303
_version_ 1783693723651014656
author Beauchamp, Jeremy
Bunescu, Razvan
Marling, Cindy
Li, Zhongen
Liu, Chang
author_facet Beauchamp, Jeremy
Bunescu, Razvan
Marling, Cindy
Li, Zhongen
Liu, Chang
author_sort Beauchamp, Jeremy
collection PubMed
description To avoid serious diabetic complications, people with type 1 diabetes must keep their blood glucose levels (BGLs) as close to normal as possible. Insulin dosages and carbohydrate consumption are important considerations in managing BGLs. Since the 1960s, models have been developed to forecast blood glucose levels based on the history of BGLs, insulin dosages, carbohydrate intake, and other physiological and lifestyle factors. Such predictions can be used to alert people of impending unsafe BGLs or to control insulin flow in an artificial pancreas. In past work, we have introduced an LSTM-based approach to blood glucose level prediction aimed at “what-if” scenarios, in which people could enter foods they might eat or insulin amounts they might take and then see the effect on future BGLs. In this work, we invert the “what-if” scenario and introduce a similar architecture based on chaining two LSTMs that can be trained to make either insulin or carbohydrate recommendations aimed at reaching a desired BG level in the future. Leveraging a recent state-of-the-art model for time series forecasting, we then derive a novel architecture for the same recommendation task, in which the two LSTM chain is used as a repeating block inside a deep residual architecture. Experimental evaluations using real patient data from the OhioT1DM dataset show that the new integrated architecture compares favorably with the previous LSTM-based approach, substantially outperforming the baselines. The promising results suggest that this novel approach could potentially be of practical use to people with type 1 diabetes for self-management of BGLs.
format Online
Article
Text
id pubmed-8126192
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-81261922021-05-17 LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management Beauchamp, Jeremy Bunescu, Razvan Marling, Cindy Li, Zhongen Liu, Chang Sensors (Basel) Article To avoid serious diabetic complications, people with type 1 diabetes must keep their blood glucose levels (BGLs) as close to normal as possible. Insulin dosages and carbohydrate consumption are important considerations in managing BGLs. Since the 1960s, models have been developed to forecast blood glucose levels based on the history of BGLs, insulin dosages, carbohydrate intake, and other physiological and lifestyle factors. Such predictions can be used to alert people of impending unsafe BGLs or to control insulin flow in an artificial pancreas. In past work, we have introduced an LSTM-based approach to blood glucose level prediction aimed at “what-if” scenarios, in which people could enter foods they might eat or insulin amounts they might take and then see the effect on future BGLs. In this work, we invert the “what-if” scenario and introduce a similar architecture based on chaining two LSTMs that can be trained to make either insulin or carbohydrate recommendations aimed at reaching a desired BG level in the future. Leveraging a recent state-of-the-art model for time series forecasting, we then derive a novel architecture for the same recommendation task, in which the two LSTM chain is used as a repeating block inside a deep residual architecture. Experimental evaluations using real patient data from the OhioT1DM dataset show that the new integrated architecture compares favorably with the previous LSTM-based approach, substantially outperforming the baselines. The promising results suggest that this novel approach could potentially be of practical use to people with type 1 diabetes for self-management of BGLs. MDPI 2021-05-10 /pmc/articles/PMC8126192/ /pubmed/34068808 http://dx.doi.org/10.3390/s21093303 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
Beauchamp, Jeremy
Bunescu, Razvan
Marling, Cindy
Li, Zhongen
Liu, Chang
LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management
title LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management
title_full LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management
title_fullStr LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management
title_full_unstemmed LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management
title_short LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management
title_sort lstms and deep residual networks for carbohydrate and bolus recommendations in type 1 diabetes management
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8126192/
https://www.ncbi.nlm.nih.gov/pubmed/34068808
http://dx.doi.org/10.3390/s21093303
work_keys_str_mv AT beauchampjeremy lstmsanddeepresidualnetworksforcarbohydrateandbolusrecommendationsintype1diabetesmanagement
AT bunescurazvan lstmsanddeepresidualnetworksforcarbohydrateandbolusrecommendationsintype1diabetesmanagement
AT marlingcindy lstmsanddeepresidualnetworksforcarbohydrateandbolusrecommendationsintype1diabetesmanagement
AT lizhongen lstmsanddeepresidualnetworksforcarbohydrateandbolusrecommendationsintype1diabetesmanagement
AT liuchang lstmsanddeepresidualnetworksforcarbohydrateandbolusrecommendationsintype1diabetesmanagement