Cargando…

Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods

PURPOSE: This study aimed to improve estimates of sitting time from hip-worn accelerometers used in large cohort studies by using machine learning methods developed on free-living activPAL data. METHODS: Thirty breast cancer survivors concurrently wore a hip-worn accelerometer and a thigh-worn activ...

Descripción completa

Detalles Bibliográficos
Autores principales: KERR, JACQUELINE, CARLSON, JORDAN, GODBOLE, SUNEETA, CADMUS-BERTRAM, LISA, BELLETTIERE, JOHN, HARTMAN, SHERI
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Lippincott Williams & Wilkins 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6023581/
https://www.ncbi.nlm.nih.gov/pubmed/29443824
http://dx.doi.org/10.1249/MSS.0000000000001578
_version_ 1783335896254251008
author KERR, JACQUELINE
CARLSON, JORDAN
GODBOLE, SUNEETA
CADMUS-BERTRAM, LISA
BELLETTIERE, JOHN
HARTMAN, SHERI
author_facet KERR, JACQUELINE
CARLSON, JORDAN
GODBOLE, SUNEETA
CADMUS-BERTRAM, LISA
BELLETTIERE, JOHN
HARTMAN, SHERI
author_sort KERR, JACQUELINE
collection PubMed
description PURPOSE: This study aimed to improve estimates of sitting time from hip-worn accelerometers used in large cohort studies by using machine learning methods developed on free-living activPAL data. METHODS: Thirty breast cancer survivors concurrently wore a hip-worn accelerometer and a thigh-worn activPAL for 7 d. A random forest classifier, trained on the activPAL data, was used to detect sitting, standing, and sit–stand transitions in 5-s windows in the hip-worn accelerometer. The classifier estimates were compared with the standard accelerometer cut point, and significant differences across different bout lengths were investigated using mixed-effect models. RESULTS: Overall, the algorithm predicted the postures with moderate accuracy (stepping, 77%; standing, 63%; sitting, 67%; sit-to-stand, 52%; and stand-to-sit, 51%). Daily level analyses indicated that errors in transition estimates were only occurring during sitting bouts of 2 min or less. The standard cut point was significantly different from the activPAL across all bout lengths, overestimating short bouts and underestimating long bouts. CONCLUSIONS: This is among the first algorithms for sitting and standing for hip-worn accelerometer data to be trained from entirely free-living activPAL data. The new algorithm detected prolonged sitting, which has been shown to be the most detrimental to health. Further validation and training in larger cohorts is warranted.
format Online
Article
Text
id pubmed-6023581
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Lippincott Williams & Wilkins
record_format MEDLINE/PubMed
spelling pubmed-60235812018-07-11 Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods KERR, JACQUELINE CARLSON, JORDAN GODBOLE, SUNEETA CADMUS-BERTRAM, LISA BELLETTIERE, JOHN HARTMAN, SHERI Med Sci Sports Exerc SPECIAL COMMUNICATIONS: Methodological Advances PURPOSE: This study aimed to improve estimates of sitting time from hip-worn accelerometers used in large cohort studies by using machine learning methods developed on free-living activPAL data. METHODS: Thirty breast cancer survivors concurrently wore a hip-worn accelerometer and a thigh-worn activPAL for 7 d. A random forest classifier, trained on the activPAL data, was used to detect sitting, standing, and sit–stand transitions in 5-s windows in the hip-worn accelerometer. The classifier estimates were compared with the standard accelerometer cut point, and significant differences across different bout lengths were investigated using mixed-effect models. RESULTS: Overall, the algorithm predicted the postures with moderate accuracy (stepping, 77%; standing, 63%; sitting, 67%; sit-to-stand, 52%; and stand-to-sit, 51%). Daily level analyses indicated that errors in transition estimates were only occurring during sitting bouts of 2 min or less. The standard cut point was significantly different from the activPAL across all bout lengths, overestimating short bouts and underestimating long bouts. CONCLUSIONS: This is among the first algorithms for sitting and standing for hip-worn accelerometer data to be trained from entirely free-living activPAL data. The new algorithm detected prolonged sitting, which has been shown to be the most detrimental to health. Further validation and training in larger cohorts is warranted. Lippincott Williams & Wilkins 2018-07 2018-01-26 /pmc/articles/PMC6023581/ /pubmed/29443824 http://dx.doi.org/10.1249/MSS.0000000000001578 Text en Copyright © 2018 The Author(s). Published by Wolters Kluwer Health, Inc. on behalf of the American College of Sports Medicine. This is an open access article distributed under the Creative Commons Attribution License 4.0 (CCBY) (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle SPECIAL COMMUNICATIONS: Methodological Advances
KERR, JACQUELINE
CARLSON, JORDAN
GODBOLE, SUNEETA
CADMUS-BERTRAM, LISA
BELLETTIERE, JOHN
HARTMAN, SHERI
Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods
title Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods
title_full Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods
title_fullStr Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods
title_full_unstemmed Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods
title_short Improving Hip-Worn Accelerometer Estimates of Sitting Using Machine Learning Methods
title_sort improving hip-worn accelerometer estimates of sitting using machine learning methods
topic SPECIAL COMMUNICATIONS: Methodological Advances
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6023581/
https://www.ncbi.nlm.nih.gov/pubmed/29443824
http://dx.doi.org/10.1249/MSS.0000000000001578
work_keys_str_mv AT kerrjacqueline improvinghipwornaccelerometerestimatesofsittingusingmachinelearningmethods
AT carlsonjordan improvinghipwornaccelerometerestimatesofsittingusingmachinelearningmethods
AT godbolesuneeta improvinghipwornaccelerometerestimatesofsittingusingmachinelearningmethods
AT cadmusbertramlisa improvinghipwornaccelerometerestimatesofsittingusingmachinelearningmethods
AT bellettierejohn improvinghipwornaccelerometerestimatesofsittingusingmachinelearningmethods
AT hartmansheri improvinghipwornaccelerometerestimatesofsittingusingmachinelearningmethods