Feasibility of Calibrating Smartphone to Access Physical Activity
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The purpose of the study was to develop algorithms to predict energy expenditure (EE) and to evaluate their utility compared to existing accelerometer technology. Forty-four participants wore an Actigraph GT3X (AG3X) and the Samsung Galaxy S2 Smartphone (SP) over a 69 min period. Oxygen consumption (VO2) was simultaneously measured by a portable indirect calorimetry system. EE prediction equations for the SP were developed from the walking and running activities using standard regression methods. The equation was then cross-validated on a separate holdout sample (n=22) using equivalence testing to evaluate accuracy. The overall mean absolute percentage errors were large for both the SP algorithm (42.4%) and the Freedson’s AG3X algorithm (38.2%). However, the estimated METs from the SP was statistically equivalent to the measured METs for the two activities used in calibration: walking (90% CI: 2.85, 3.50 kcal·min-1) and running (90% CI: 7.64, 8.25 kcal·min-1). Other activities were not accurately assessed with the SP but none of the estimates from the AG3X met the statistical criteria for equivalency. The study demonstrates that data from SP can be easily calibrated to estimate EE and that accuracy is comparable to the common research-grade monitors.
Abstract
The purpose of the study was to develop algorithms to predict energy expenditure (EE) and to evaluate their utility compared to existing accelerometer technology. Forty-four participants wore an Actigraph GT3X (AG3X) and the Samsung Galaxy S2 Smartphone (SP) over a 69 min period. Oxygen consumption (VO2) was simultaneously measured by a portable indirect calorimetry system. EE prediction equations for the SP were developed from the walking and running activities using standard regression methods. The equation was then cross-validated on a separate holdout sample (n=22) using equivalence testing to evaluate accuracy. The overall mean absolute percentage errors were large for both the SP algorithm (42.4%) and the Freedson’s AG3X algorithm (38.2%). However, the estimated METs from the SP was statistically equivalent to the measured METs for the two activities used in calibration: walking (90% CI: 2.85, 3.50 kcal·min-1) and running (90% CI: 7.64, 8.25 kcal·min-1). Other activities were not accurately assessed with the SP but none of the estimates from the AG3X met the statistical criteria for equivalency. The study demonstrates that data from SP can be easily calibrated to estimate EE and that accuracy is comparable to the common research-grade monitors.
참고문헌 (31)
- Alhassan, S., "Estimating physical activity from incomplete accelerometer data in field studies", J Phys Act Health, 5(Suppl 1), pp.S112~S125 (2008)
- Allen, JK, "Randomized Controlled Pilot Study Testing Use of Smartphone Technology for Obesity Treatment", Journal of Obesity, 7, pp.2013~2017 (2013)
- Ang, W. J. J., "Validating the Use of Smartphone-Based Accelerometers for Performance Assessment in a Simulated Neurosurgical Task", Neurosurgery, 10(1), pp.57~64 (2014)
- "Actually, The US Sma rtphone Revolution Has Entered The Late Inning s" (2012)[URL]
- Brouillette, RM, "Feasibility, reliability, and validity of a smartphone based application for the assessment of cognitive function in the elderly", PLoS One, 8(6), pp.e65925~ (2013)
- Brown, DW, "Associations between recommended levels of physical activity and health-related quality of life. Findings from the 2001 Behavioral Risk Factor Surveillance System (BRFSS) survey", Preventive Medicine, 37(5), pp.520~528 (2003)
- Calabro, M. A., "Validation of a computerized 24-hour physical activity recall (24PAR) instrument with pattern-recognition activity monitors", J Phys Act Health, 6(2), pp.211~220 (2009)
- Cho, J.-H., "Smart Phone-based Human Activity Classification and Energy Expenditure Generation in Building Environments", Paper presented at the Proceedings of the 7th International Symposium on Sustainable Healthy Buildings (2012)
- Choi, L., "Assessment of wear", nonwear time classification algorithms for triaxial accelerometer, 2012, pp.44(10), 2009~2016
- Compher, C., "Best practice methods to apply to measurement of resting metabolic rate in adults: a systematic review", Journal of the American Dietetic Association, 106(6), pp.881~903 (2006)
- Dixon, PM, "A statistical test to show negligible trend", Ecology, 86(7), pp.1751~1756 (2005)
- Donaire-Gonzalez, D., "Comparison of Physical Activity Measures Using Mobile Phone-Based CalFit and Actigraph", Journal of Medical Internet Research, 15(6), pp.e111~ (2013)
- Freedson, P. S., "Calibration of the Computer Science and Applications, Inc. accelerometer", Med Sci Sports Exerc, 30(5), pp.777~781 (1998)
- Fujiki, Y., "iPhone as a physical activity measurement platform", Paper presented at the CHI'10 Extended Abstracts on Human Factors in Computing Systems (2010)
- Glynn, LG., "SMART MOVE-a smartphone-based intervention to promote physical activity in primary care: study protocol for a randomized controlled trial", Trials, 14(1), pp.157~ (2013)
- Haskell, WL, "Physical activity and public health: updated recommendation for adults from the American College of Sports Medicine and the American Heart Association", Medicine and Science in Sports and Exercise, 39(8), pp.1423~1434 (2007)
- Kim, Y., "Everything you wanted to know about selecting the "right" Actigraph accelerometer cut-points for youth, but...: a systematic review", J Sci Med Sport, 15(4), pp.311~321 (2012)
- Kirwan, M., "Design, development, and formative evaluation of a smartphone application for recording and monitoring physical activity levels: the 10,000 Steps "iStepLog"", Health Educ Behav, 40(2), pp.140~151 (2013)
- Lamonte, MJ, "Quantifying energy expenditure and physical activity in the context of dose response", Medicine and Science in Sports and Exercise, 33(6 Suppl), pp.S370~S378 (2001)
- Lira, MM, "Combining multiple artificial neural networks using random committee to decide upon electrical disturbance classification", Paper presented at the Neural Networks, 2007. IJCNN 2007. International Joint Conference on (2007)
- Michael, BD, "Development of ClickClinica: a novel smartphone application to generate real-time global disease surveillance and clinical practice data", BMC Medical Informatics and Decision Making, 13, pp.70~ (2013)
- Nolan, M., "Validity of the Apple iPhone(R)", iPod Touch(R) as an accelerometer-based physical activity monitor:a proof-of-concept study, 2014, pp.11(4), 759~769
- Rosdahl, H., "Evaluation of the Oxycon Mobile metabolic system against the Douglas bag method", European Journal of Applied Physiology, 109(2), pp.159~171 (2010)
- Sasaki, JE, "Validation and comparison of ActiGraph activity monitors", Journal of Science and Medicine in Sport, 14(5), pp.411~416 (2011)
- Sirard, JR, "Compliance with wearing physical activity accelerometers in high school students", J Phys Act Health, (Suppl 1), pp.S148~S155 (2009)
- Strath, SJ, "Accelerometer use with children, older adults, and adults with functional limitations", Medicine and Science in Sports and Exercise, 44(1 Suppl 1), pp.S77~ (2012)
- Varady, KA, "Validation of hand-held bioelectrical impedance analysis with magnetic resonance imaging for the assessment of body composition in overweight women", American Journal of Human Biology, 19(3), pp.429~433 (2007)
- Welk, GJ, "Principles of design and analyses for the calibration of accelerometry-based activity monitors", Medicine and Science in Sports and Exercise, 37(11 Suppl), pp.S501~S511 (2005)
- Wellek, S., "Testing statistical hypotheses of equivalence", pp.2003, Chapman & Hall
- Wu, W., "Classification accuracies of physical activities using smartphone motion sensors", Journal of Medical Internet Research, 14(5), pp.e130~ (2012)
- Yamada, M., "Objective assessment of abnormal gait in patients with rheumatoid arthritis using a smartphone", Rheumatology international, 32(12), pp.3869~3874 (2012)