Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data

OBJECTIVE: To develop a noninvasive hypoglycemia detection approach using smartwatch data. RESEARCH DESIGN AND METHODS: We prospectively collected data from two wrist-worn wearables (Garmin vivoactive 4S, Empatica E4) and continuous glucose monitoring values in adults with diabetes on insulin treatm...

Descripción completa

Detalles Bibliográficos
Autores principales: Lehmann, Vera, Föll, Simon, Maritsch, Martin, van Weenen, Eva, Kraus, Mathias, Lagger, Sophie, Odermatt, Katja, Albrecht, Caroline, Fleisch, Elgar, Zueger, Thomas, Wortmann, Felix, Stettler, Christoph
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Diabetes Association 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10154647/
https://www.ncbi.nlm.nih.gov/pubmed/36805169
http://dx.doi.org/10.2337/dc22-2290
_version_ 1785036171918704640
author Lehmann, Vera
Föll, Simon
Maritsch, Martin
van Weenen, Eva
Kraus, Mathias
Lagger, Sophie
Odermatt, Katja
Albrecht, Caroline
Fleisch, Elgar
Zueger, Thomas
Wortmann, Felix
Stettler, Christoph
author_facet Lehmann, Vera
Föll, Simon
Maritsch, Martin
van Weenen, Eva
Kraus, Mathias
Lagger, Sophie
Odermatt, Katja
Albrecht, Caroline
Fleisch, Elgar
Zueger, Thomas
Wortmann, Felix
Stettler, Christoph
author_sort Lehmann, Vera
collection PubMed
description OBJECTIVE: To develop a noninvasive hypoglycemia detection approach using smartwatch data. RESEARCH DESIGN AND METHODS: We prospectively collected data from two wrist-worn wearables (Garmin vivoactive 4S, Empatica E4) and continuous glucose monitoring values in adults with diabetes on insulin treatment. Using these data, we developed a machine learning (ML) approach to detect hypoglycemia (<3.9 mmol/L) noninvasively in unseen individuals and solely based on wearable data. RESULTS: Twenty-two individuals were included in the final analysis (age 54.5 ± 15.2 years, HbA(1c) 6.9 ± 0.6%, 16 males). Hypoglycemia was detected with an area under the receiver operating characteristic curve of 0.76 ± 0.07 solely based on wearable data. Feature analysis revealed that the ML model associated increased heart rate, decreased heart rate variability, and increased tonic electrodermal activity with hypoglycemia. CONCLUSIONS: Our approach may allow for noninvasive hypoglycemia detection using wearables in people with diabetes and thus complement existing methods for hypoglycemia detection and warning.
format Online
Article
Text
id pubmed-10154647
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher American Diabetes Association
record_format MEDLINE/PubMed
spelling pubmed-101546472023-05-04 Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data Lehmann, Vera Föll, Simon Maritsch, Martin van Weenen, Eva Kraus, Mathias Lagger, Sophie Odermatt, Katja Albrecht, Caroline Fleisch, Elgar Zueger, Thomas Wortmann, Felix Stettler, Christoph Diabetes Care Brief Report OBJECTIVE: To develop a noninvasive hypoglycemia detection approach using smartwatch data. RESEARCH DESIGN AND METHODS: We prospectively collected data from two wrist-worn wearables (Garmin vivoactive 4S, Empatica E4) and continuous glucose monitoring values in adults with diabetes on insulin treatment. Using these data, we developed a machine learning (ML) approach to detect hypoglycemia (<3.9 mmol/L) noninvasively in unseen individuals and solely based on wearable data. RESULTS: Twenty-two individuals were included in the final analysis (age 54.5 ± 15.2 years, HbA(1c) 6.9 ± 0.6%, 16 males). Hypoglycemia was detected with an area under the receiver operating characteristic curve of 0.76 ± 0.07 solely based on wearable data. Feature analysis revealed that the ML model associated increased heart rate, decreased heart rate variability, and increased tonic electrodermal activity with hypoglycemia. CONCLUSIONS: Our approach may allow for noninvasive hypoglycemia detection using wearables in people with diabetes and thus complement existing methods for hypoglycemia detection and warning. American Diabetes Association 2023-05 2023-02-17 /pmc/articles/PMC10154647/ /pubmed/36805169 http://dx.doi.org/10.2337/dc22-2290 Text en © 2023 by the American Diabetes Association https://www.diabetesjournals.org/journals/pages/licenseReaders may use this article as long as the work is properly cited, the use is educational and not for profit, and the work is not altered. More information is available at https://www.diabetesjournals.org/journals/pages/license.
spellingShingle Brief Report
Lehmann, Vera
Föll, Simon
Maritsch, Martin
van Weenen, Eva
Kraus, Mathias
Lagger, Sophie
Odermatt, Katja
Albrecht, Caroline
Fleisch, Elgar
Zueger, Thomas
Wortmann, Felix
Stettler, Christoph
Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data
title Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data
title_full Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data
title_fullStr Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data
title_full_unstemmed Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data
title_short Noninvasive Hypoglycemia Detection in People With Diabetes Using Smartwatch Data
title_sort noninvasive hypoglycemia detection in people with diabetes using smartwatch data
topic Brief Report
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10154647/
https://www.ncbi.nlm.nih.gov/pubmed/36805169
http://dx.doi.org/10.2337/dc22-2290
work_keys_str_mv AT lehmannvera noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT follsimon noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT maritschmartin noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT vanweeneneva noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT krausmathias noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT laggersophie noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT odermattkatja noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT albrechtcaroline noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT fleischelgar noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT zuegerthomas noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT wortmannfelix noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata
AT stettlerchristoph noninvasivehypoglycemiadetectioninpeoplewithdiabetesusingsmartwatchdata