Cargando…

Assessing Upper Limb Function in Breast Cancer Survivors Using Wearable Sensors and Machine Learning in a Free-Living Environment

(1) Background: Being able to objectively assess upper limb (UL) dysfunction in breast cancer survivors (BCS) is an emerging issue. This study aims to determine the accuracy of a pre-trained lab-based machine learning model (MLM) to distinguish functional from non-functional arm movements in a home...

Descripción completa

Detalles Bibliográficos
Autores principales: Vets, Nieke, De Groef, An, Verbeelen, Kaat, Devoogdt, Nele, Smeets, Ann, Van Assche, Dieter, De Baets, Liesbet, Emmerzaal, Jill
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10347074/
https://www.ncbi.nlm.nih.gov/pubmed/37447951
http://dx.doi.org/10.3390/s23136100
_version_ 1785073463685283840
author Vets, Nieke
De Groef, An
Verbeelen, Kaat
Devoogdt, Nele
Smeets, Ann
Van Assche, Dieter
De Baets, Liesbet
Emmerzaal, Jill
author_facet Vets, Nieke
De Groef, An
Verbeelen, Kaat
Devoogdt, Nele
Smeets, Ann
Van Assche, Dieter
De Baets, Liesbet
Emmerzaal, Jill
author_sort Vets, Nieke
collection PubMed
description (1) Background: Being able to objectively assess upper limb (UL) dysfunction in breast cancer survivors (BCS) is an emerging issue. This study aims to determine the accuracy of a pre-trained lab-based machine learning model (MLM) to distinguish functional from non-functional arm movements in a home situation in BCS. (2) Methods: Participants performed four daily life activities while wearing two wrist accelerometers and being video recorded. To define UL functioning, video data were annotated and accelerometer data were analyzed using a counts threshold method and an MLM. Prediction accuracy, recall, sensitivity, f1-score, ‘total minutes functional activity’ and ‘percentage functionally active’ were considered. (3) Results: Despite a good MLM accuracy (0.77–0.90), recall, and specificity, the f1-score was poor. An overestimation of the ‘total minutes functional activity’ and ‘percentage functionally active’ was found by the MLM. Between the video-annotated data and the functional activity determined by the MLM, the mean differences were 0.14% and 0.10% for the left and right side, respectively. For the video-annotated data versus the counts threshold method, the mean differences were 0.27% and 0.24%, respectively. (4) Conclusions: An MLM is a better alternative than the counts threshold method for distinguishing functional from non-functional arm movements. However, the abovementioned wrist accelerometer-based assessment methods overestimate UL functional activity.
format Online
Article
Text
id pubmed-10347074
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-103470742023-07-15 Assessing Upper Limb Function in Breast Cancer Survivors Using Wearable Sensors and Machine Learning in a Free-Living Environment Vets, Nieke De Groef, An Verbeelen, Kaat Devoogdt, Nele Smeets, Ann Van Assche, Dieter De Baets, Liesbet Emmerzaal, Jill Sensors (Basel) Article (1) Background: Being able to objectively assess upper limb (UL) dysfunction in breast cancer survivors (BCS) is an emerging issue. This study aims to determine the accuracy of a pre-trained lab-based machine learning model (MLM) to distinguish functional from non-functional arm movements in a home situation in BCS. (2) Methods: Participants performed four daily life activities while wearing two wrist accelerometers and being video recorded. To define UL functioning, video data were annotated and accelerometer data were analyzed using a counts threshold method and an MLM. Prediction accuracy, recall, sensitivity, f1-score, ‘total minutes functional activity’ and ‘percentage functionally active’ were considered. (3) Results: Despite a good MLM accuracy (0.77–0.90), recall, and specificity, the f1-score was poor. An overestimation of the ‘total minutes functional activity’ and ‘percentage functionally active’ was found by the MLM. Between the video-annotated data and the functional activity determined by the MLM, the mean differences were 0.14% and 0.10% for the left and right side, respectively. For the video-annotated data versus the counts threshold method, the mean differences were 0.27% and 0.24%, respectively. (4) Conclusions: An MLM is a better alternative than the counts threshold method for distinguishing functional from non-functional arm movements. However, the abovementioned wrist accelerometer-based assessment methods overestimate UL functional activity. MDPI 2023-07-02 /pmc/articles/PMC10347074/ /pubmed/37447951 http://dx.doi.org/10.3390/s23136100 Text en © 2023 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
Vets, Nieke
De Groef, An
Verbeelen, Kaat
Devoogdt, Nele
Smeets, Ann
Van Assche, Dieter
De Baets, Liesbet
Emmerzaal, Jill
Assessing Upper Limb Function in Breast Cancer Survivors Using Wearable Sensors and Machine Learning in a Free-Living Environment
title Assessing Upper Limb Function in Breast Cancer Survivors Using Wearable Sensors and Machine Learning in a Free-Living Environment
title_full Assessing Upper Limb Function in Breast Cancer Survivors Using Wearable Sensors and Machine Learning in a Free-Living Environment
title_fullStr Assessing Upper Limb Function in Breast Cancer Survivors Using Wearable Sensors and Machine Learning in a Free-Living Environment
title_full_unstemmed Assessing Upper Limb Function in Breast Cancer Survivors Using Wearable Sensors and Machine Learning in a Free-Living Environment
title_short Assessing Upper Limb Function in Breast Cancer Survivors Using Wearable Sensors and Machine Learning in a Free-Living Environment
title_sort assessing upper limb function in breast cancer survivors using wearable sensors and machine learning in a free-living environment
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10347074/
https://www.ncbi.nlm.nih.gov/pubmed/37447951
http://dx.doi.org/10.3390/s23136100
work_keys_str_mv AT vetsnieke assessingupperlimbfunctioninbreastcancersurvivorsusingwearablesensorsandmachinelearninginafreelivingenvironment
AT degroefan assessingupperlimbfunctioninbreastcancersurvivorsusingwearablesensorsandmachinelearninginafreelivingenvironment
AT verbeelenkaat assessingupperlimbfunctioninbreastcancersurvivorsusingwearablesensorsandmachinelearninginafreelivingenvironment
AT devoogdtnele assessingupperlimbfunctioninbreastcancersurvivorsusingwearablesensorsandmachinelearninginafreelivingenvironment
AT smeetsann assessingupperlimbfunctioninbreastcancersurvivorsusingwearablesensorsandmachinelearninginafreelivingenvironment
AT vanasschedieter assessingupperlimbfunctioninbreastcancersurvivorsusingwearablesensorsandmachinelearninginafreelivingenvironment
AT debaetsliesbet assessingupperlimbfunctioninbreastcancersurvivorsusingwearablesensorsandmachinelearninginafreelivingenvironment
AT emmerzaaljill assessingupperlimbfunctioninbreastcancersurvivorsusingwearablesensorsandmachinelearninginafreelivingenvironment