Assessment of wear/nonwear time classification algorithms for triaxial accelerometer - PubMed (original) (raw)
Assessment of wear/nonwear time classification algorithms for triaxial accelerometer
Leena Choi et al. Med Sci Sports Exerc. 2012 Oct.
Abstract
Purpose: The objective of this study is to assess the performance of existing wear/nonwear time classification algorithms for accelerometry data collected in the free-living environment using a wrist-worn triaxial accelerometer and a waist-worn uniaxial accelerometer in older adults.
Methods: Twenty-nine adults age 76 to 96 yr wore wrist accelerometers for approximately 24 h per day and waist accelerometers during waking for approximately 7 d of free living. Wear and nonwear times were classified by existing algorithms (Alg([ActiLife]), Alg([Troiano]), and Alg([Choi])) and compared with wear and nonwear times identified by data plots and diary records. With the use of bias and probability of correct classification, the performance of the algorithms, two time windows (60 and 90 min), and vector magnitude (VM) versus vertical axis (V) counts from a triaxial accelerometer were compared.
Results: Automated algorithms (Alg([Choi]) and Alg([Troiano])) classified wear/nonwear time intervals more accurately from VM than V counts. The use of the 90-min time window improved wear/nonwear classification accuracy when compared with the 60-min window. The Alg([Choi]) and Alg([Troiano]) performed better than the manufacturer-provided algorithm (Alg([ActiLife])), and the Alg([Choi]) performed better than the Alg([Troiano]) for wear/nonwear time classification using the data collected by both accelerometers.
Conclusions: Triaxial wrist-worn accelerometer can be used for an accurate wear/nonwear time classification in free-living older adults. The use of the 90-min window and the VM counts improves the performance of commonly used algorithms for wear/nonwear classification for both uniaxial and triaxial accelerometers.
Conflict of interest statement
Conflict of Interest: none.
Figures
Figure 1
(A) and (B) The first two days of representative data for two subjects who wore wrist monitor for 24-h and waist monitor during waking period: wrist VM (top), wrist V (middle), and waist V (bottom). Wear and nonwear identification during period classified as sleep are represented by dashed arrows. Intervals identified as nonwear during waking are represented by solid arrows in (B).
Figure 1
(A) and (B) The first two days of representative data for two subjects who wore wrist monitor for 24-h and waist monitor during waking period: wrist VM (top), wrist V (middle), and waist V (bottom). Wear and nonwear identification during period classified as sleep are represented by dashed arrows. Intervals identified as nonwear during waking are represented by solid arrows in (B).
Figure 2
Box plots of individual bias in the daily average wear time (identified - classified) (min) classified by algorithms with two window time settings (60- and 90-min) using wrist (VM and V) and waist (V) counts data during 24-h and both monitors-worn waking periods: (A) Alg[Troiano]; (B) Alg[Choi]. The solid circles represent individual data points (N=29).
Figure 2
Box plots of individual bias in the daily average wear time (identified - classified) (min) classified by algorithms with two window time settings (60- and 90-min) using wrist (VM and V) and waist (V) counts data during 24-h and both monitors-worn waking periods: (A) Alg[Troiano]; (B) Alg[Choi]. The solid circles represent individual data points (N=29).
Figure 3
Box plots of individual probability of correct classification by algorithms with two window time settings (60- and 90-min) using wrist (VM and V) and waist (V) counts data during 24-h and both monitors-worn waking periods: (A) Alg[Troiano]; (B) Alg[Choi]. The solid circles represent individual data points (N=29).
Figure 3
Box plots of individual probability of correct classification by algorithms with two window time settings (60- and 90-min) using wrist (VM and V) and waist (V) counts data during 24-h and both monitors-worn waking periods: (A) Alg[Troiano]; (B) Alg[Choi]. The solid circles represent individual data points (N=29).
Similar articles
- Validation of automatic wear-time detection algorithms in a free-living setting of wrist-worn and hip-worn ActiGraph GT3X.
Knaier R, Höchsmann C, Infanger D, Hinrichs T, Schmidt-Trucksäss A. Knaier R, et al. BMC Public Health. 2019 Feb 28;19(1):244. doi: 10.1186/s12889-019-6568-9. BMC Public Health. 2019. PMID: 30819148 Free PMC article. - Validation of accelerometer wear and nonwear time classification algorithm.
Choi L, Liu Z, Matthews CE, Buchowski MS. Choi L, et al. Med Sci Sports Exerc. 2011 Feb;43(2):357-64. doi: 10.1249/MSS.0b013e3181ed61a3. Med Sci Sports Exerc. 2011. PMID: 20581716 Free PMC article. - Impact of accelerometer data processing decisions on the sample size, wear time and physical activity level of a large cohort study.
Keadle SK, Shiroma EJ, Freedson PS, Lee IM. Keadle SK, et al. BMC Public Health. 2014 Nov 24;14:1210. doi: 10.1186/1471-2458-14-1210. BMC Public Health. 2014. PMID: 25421941 Free PMC article. Clinical Trial. - Prediction of activity-related energy expenditure using accelerometer-derived physical activity under free-living conditions: a systematic review.
Jeran S, Steinbrecher A, Pischon T. Jeran S, et al. Int J Obes (Lond). 2016 Aug;40(8):1187-97. doi: 10.1038/ijo.2016.14. Epub 2016 Feb 2. Int J Obes (Lond). 2016. PMID: 27163747 Review. - The impact of selected methodological factors on data collection outcomes in observational studies of device-measured physical behaviour in adults: A systematic review.
Pulsford RM, Brocklebank L, Fenton SAM, Bakker E, Mielke GI, Tsai LT, Atkin AJ, Harvey DL, Blodgett JM, Ahmadi M, Wei L, Rowlands A, Doherty A, Rangul V, Koster A, Sherar LB, Holtermann A, Hamer M, Stamatakis E. Pulsford RM, et al. Int J Behav Nutr Phys Act. 2023 Mar 8;20(1):26. doi: 10.1186/s12966-022-01388-9. Int J Behav Nutr Phys Act. 2023. PMID: 36890553 Free PMC article. Review.
Cited by
- Plasma markers of neurodegeneration, latent cognitive abilities and physical activity in healthy aging.
Nilsson J, Jiang Y, Johannesson M, Moberg M, Wang R, Fabre S, Lövdén M, Ekblom Ö, Ekblom M. Nilsson J, et al. Sci Rep. 2024 Sep 17;14(1):21702. doi: 10.1038/s41598-024-72806-0. Sci Rep. 2024. PMID: 39289522 Free PMC article. - Cook and Move for Your Life, an eHealth intervention for women with breast cancer.
Greenlee H, Rillamas-Sun E, Yung RL, Cobos S, Donzella SM, Huang Y, Schattenkerk L, Ueland K, VanDoren M, Myers SA, Garcia G, King T, Santiago-Torres M, Di C, Dey N, Guthrie KA, Davidson NE. Greenlee H, et al. NPJ Breast Cancer. 2024 Jul 25;10(1):62. doi: 10.1038/s41523-024-00662-2. NPJ Breast Cancer. 2024. PMID: 39054321 Free PMC article. - Feasibility and preliminary effects of the Fit2ThriveMB pilot physical activity promotion intervention on physical activity and patient reported outcomes in individuals with metastatic breast cancer.
Phillips SM, Starikovsky J, Solk P, Desai R, Reading JM, Hasanaj K, Wang SD, Cullather E, Lee J, Song J, Spring B, Gradishar W. Phillips SM, et al. Breast Cancer Res Treat. 2024 Jul 16. doi: 10.1007/s10549-024-07432-5. Online ahead of print. Breast Cancer Res Treat. 2024. PMID: 39014267 - Accelerometry-assessed physical activity and sedentary behavior patterns using single- and multi-component latent class analysis among postmenopausal women.
Evenson KR, Wen F, Di C, Kebede M, LaMonte MJ, Lee IM, Tinker LF, LaCroix AZ, Howard AG. Evenson KR, et al. Womens Health (Lond). 2024 Jan-Dec;20:17455057241257361. doi: 10.1177/17455057241257361. Womens Health (Lond). 2024. PMID: 38805324 Free PMC article. - Time- vs Step-Based Physical Activity Metrics for Health.
Hamaya R, Shiroma EJ Jr, Moore CC, Buring JE, Evenson KR, Lee IM. Hamaya R, et al. JAMA Intern Med. 2024 Jul 1;184(7):718-725. doi: 10.1001/jamainternmed.2024.0892. JAMA Intern Med. 2024. PMID: 38767892 Clinical Trial.
References
- Buchowski MS, Acra S, Majchrzak KM, Sun M, Chen KY. Patterns of physical activity in free-living adults in the southern united states. Eur J Clin Nutr. 2007;58(5):828–37. - PubMed
- Choi L, Liu Z, Matthews CE, Buchowski MS. Physicalactivity: Process physical activity accelerometer data. 2010:1–14.
Publication types
MeSH terms
Grants and funding
- P60 DK020593/DK/NIDDK NIH HHS/United States
- R01 DK69465/DK/NIDDK NIH HHS/United States
- TL1 RR024978/RR/NCRR NIH HHS/United States
- KL2 RR024977/RR/NCRR NIH HHS/United States
- 1UL1 RR024975/RR/NCRR NIH HHS/United States
- P30 DK020593/DK/NIDDK NIH HHS/United States
- R01 DK069465/DK/NIDDK NIH HHS/United States
- UL1 RR024975/RR/NCRR NIH HHS/United States
LinkOut - more resources
Full Text Sources
Other Literature Sources