Cargando…
Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals
Non-coordinated physical activity may lead to hypoglycemia, which is a dangerous condition for diabetic people. Decision support systems related to type 1 diabetes mellitus (T1DM) still lack the capability of automated therapy modification by recognizing and categorizing the physical activity. Furth...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9658555/ https://www.ncbi.nlm.nih.gov/pubmed/36366265 http://dx.doi.org/10.3390/s22218568 |
_version_ | 1784829980194111488 |
---|---|
author | Dénes-Fazakas, Lehel Siket, Máté Szilágyi, László Kovács, Levente Eigner, György |
author_facet | Dénes-Fazakas, Lehel Siket, Máté Szilágyi, László Kovács, Levente Eigner, György |
author_sort | Dénes-Fazakas, Lehel |
collection | PubMed |
description | Non-coordinated physical activity may lead to hypoglycemia, which is a dangerous condition for diabetic people. Decision support systems related to type 1 diabetes mellitus (T1DM) still lack the capability of automated therapy modification by recognizing and categorizing the physical activity. Further, this desired adaptive therapy should be achieved without increasing the administrative load, which is already high for the diabetic community. These requirements can be satisfied by using artificial intelligence-based solutions, signals collected by wearable devices, and relying on the already available data sources, such as continuous glucose monitoring systems. In this work, we focus on the detection of physical activity by using a continuous glucose monitoring system and a wearable sensor providing the heart rate—the latter is accessible even in the cheapest wearables. Our results show that the detection of physical activity is possible based on these data sources, even if only low-complexity artificial intelligence models are deployed. In general, our models achieved approximately 90% accuracy in the detection of physical activity. |
format | Online Article Text |
id | pubmed-9658555 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96585552022-11-15 Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals Dénes-Fazakas, Lehel Siket, Máté Szilágyi, László Kovács, Levente Eigner, György Sensors (Basel) Article Non-coordinated physical activity may lead to hypoglycemia, which is a dangerous condition for diabetic people. Decision support systems related to type 1 diabetes mellitus (T1DM) still lack the capability of automated therapy modification by recognizing and categorizing the physical activity. Further, this desired adaptive therapy should be achieved without increasing the administrative load, which is already high for the diabetic community. These requirements can be satisfied by using artificial intelligence-based solutions, signals collected by wearable devices, and relying on the already available data sources, such as continuous glucose monitoring systems. In this work, we focus on the detection of physical activity by using a continuous glucose monitoring system and a wearable sensor providing the heart rate—the latter is accessible even in the cheapest wearables. Our results show that the detection of physical activity is possible based on these data sources, even if only low-complexity artificial intelligence models are deployed. In general, our models achieved approximately 90% accuracy in the detection of physical activity. MDPI 2022-11-07 /pmc/articles/PMC9658555/ /pubmed/36366265 http://dx.doi.org/10.3390/s22218568 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 Dénes-Fazakas, Lehel Siket, Máté Szilágyi, László Kovács, Levente Eigner, György Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals |
title | Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals |
title_full | Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals |
title_fullStr | Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals |
title_full_unstemmed | Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals |
title_short | Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals |
title_sort | detection of physical activity using machine learning methods based on continuous blood glucose monitoring and heart rate signals |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9658555/ https://www.ncbi.nlm.nih.gov/pubmed/36366265 http://dx.doi.org/10.3390/s22218568 |
work_keys_str_mv | AT denesfazakaslehel detectionofphysicalactivityusingmachinelearningmethodsbasedoncontinuousbloodglucosemonitoringandheartratesignals AT siketmate detectionofphysicalactivityusingmachinelearningmethodsbasedoncontinuousbloodglucosemonitoringandheartratesignals AT szilagyilaszlo detectionofphysicalactivityusingmachinelearningmethodsbasedoncontinuousbloodglucosemonitoringandheartratesignals AT kovacslevente detectionofphysicalactivityusingmachinelearningmethodsbasedoncontinuousbloodglucosemonitoringandheartratesignals AT eignergyorgy detectionofphysicalactivityusingmachinelearningmethodsbasedoncontinuousbloodglucosemonitoringandheartratesignals |