Evaluating physiological signal salience for estimating metabolic energy cost from wearable sensors.

Publisher: American Physiological Society Country of Publication: United States NLM ID: 8502536 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1522-1601 (Electronic) Linking ISSN: 01617567 NLM ISO Abbreviation: J Appl Physiol (1985) Subsets: MEDLINE

Original Publication: Bethesda, MD : American Physiological Society, c1985-

Energy Metabolism/*physiology; Adult ; Algorithms ; Calorimetry, Indirect/methods ; Electromyography/methods ; Extremities/physiology ; Female ; Heart Rate/physiology ; Humans ; Male ; Masks ; Walking/physiology ; Wearable Electronic Devices

Body-in-the-loop optimization algorithms have the capability to automatically tune the parameters of robotic prostheses and exoskeletons to minimize the metabolic energy expenditure of the user. However, current body-in-the-loop algorithms rely on indirect calorimetry to obtain measurements of energy cost, which are noisy, sparsely sampled, time-delayed, and require wearing a respiratory mask. To improve these algorithms, the goal of this work is to predict a user's steady-state energy cost quickly and accurately using physiological signals obtained from portable, wearable sensors. In this paper, we quantified physiological signal salience to discover which signals, or groups of signals, have the best predictive capability when estimating metabolic energy cost. We collected data from 10 healthy individuals performing 6 activities (walking, incline walking, backward walking, running, cycling, and stair climbing) at various speeds or intensities. Subjects wore a suite of physiological sensors that measured breath frequency and volume, limb accelerations, lower limb EMG, heart rate, electrodermal activity, skin temperature, and oxygen saturation; indirect calorimetry was used to establish the 'ground truth' energy cost for each activity. Evaluating Pearson's correlation coefficients and single and multiple linear regression models with cross validation (leave-one- subject-out and leave-one- task-out), we found that 1) filtering the accelerations and EMG signals improved their predictive power, 2) global signals (e.g., heart rate, electrodermal activity) were more sensitive to unknown subjects than tasks, while local signals (e.g., accelerations) were more sensitive to unknown tasks than subjects, and 3) good predictive performance was obtained combining a small number of signals (4-5) from multiple sensor modalities. NEW & NOTEWORTHY In this paper, we systematically compare a large set of physiological signals collected from portable sensors and determine which sensor signals contain the most salient information for predicting steady-state metabolic energy cost, robust to unknown subjects or tasks. This information, together with the comprehensive data set that is published in conjunction with this paper, will enable researchers and clinicians across many fields to develop novel algorithms to predict energy cost from wearable sensors.

Am J Clin Nutr. 1993 Nov;58(5):602-7. (PMID: 8237863)
J Neuroeng Rehabil. 2014 May 09;11:80. (PMID: 24885527)
Int J Biometeorol. 1971 Dec;15(2):189-94. (PMID: 5146806)
J Appl Physiol (1985). 1998 Jan;84(1):362-71. (PMID: 9451658)
Eur J Appl Physiol. 2006 Dec;98(6):601-12. (PMID: 17058102)
IEEE Int Conf Rehabil Robot. 2017 Jul;2017:340-345. (PMID: 28813842)
J Sports Sci Med. 2012 Mar 01;11(1):182-3. (PMID: 24137070)
Sports Med. 2010 Feb 1;40(2):95-111. (PMID: 20092364)
Science. 2017 Jun 23;356(6344):1280-1284. (PMID: 28642437)
Physiol Meas. 2014 Nov;35(11):2191-203. (PMID: 25340969)
Eur J Clin Nutr. 2005 Apr;59(4):561-70. (PMID: 15714212)
J Neuroeng Rehabil. 2016 Jan 28;13:4. (PMID: 26817449)
J Appl Physiol (1985). 2006 Apr;100(4):1324-31. (PMID: 16322367)
IEEE J Biomed Health Inform. 2015 Jan;19(1):219-26. (PMID: 24691168)
Hum Nutr Clin Nutr. 1987 Nov;41(6):463-71. (PMID: 3429265)
Appl Physiol Nutr Metab. 2015 Oct;40(10):1019-24. (PMID: 26360814)
JPEN J Parenter Enteral Nutr. 2003 Jan-Feb;27(1):16-20. (PMID: 12549593)
J Appl Physiol (1985). 2009 Oct;107(4):1300-7. (PMID: 19644028)
J Biomech. 2012 Jun 26;45(10):1842-9. (PMID: 22578744)
J Neuroeng Rehabil. 2007 Dec 21;4:48. (PMID: 18154649)
Sci Rep. 2017 Apr 05;7:45738. (PMID: 28378815)
J Appl Physiol (1985). 2007 Oct;103(4):1419-27. (PMID: 17641221)
IEEE Trans Neural Syst Rehabil Eng. 2009 Feb;17(1):31-7. (PMID: 19211321)
Sci Robot. 2018 Feb 28;3(15):. (PMID: 33141683)
J Appl Physiol (1985). 2014 Dec 1;117(11):1406-15. (PMID: 25257873)
J Gerontol A Biol Sci Med Sci. 2011 May;66(5):541-7. (PMID: 21345892)
J Strength Cond Res. 2009 Aug;23(5):1489-95. (PMID: 19593221)
Med Sci Sports Exerc. 2001 Jun;33(6):939-45. (PMID: 11404659)
J Sports Sci. 2005 Mar;23(3):289-97. (PMID: 15966347)
Med Sci Sports Exerc. 2000 Sep;32(9 Suppl):S450-6. (PMID: 10993414)
Eur J Appl Physiol. 2010 May;109(2):159-71. (PMID: 20043228)
IEEE J Biomed Health Inform. 2015 Sep;19(5):1577-86. (PMID: 25838531)
J Rehabil Res Dev. 1995 May;32(2):111-9. (PMID: 7562650)
J Appl Physiol (1985). 2003 Jul;95(1):364-72. (PMID: 12651862)
Springerplus. 2013 May 19;2(1):229. (PMID: 23741656)
Res Q Exerc Sport. 2006 Mar;77(1):64-80. (PMID: 16646354)
Philos Trans R Soc Lond B Biol Sci. 2011 May 27;366(1570):1554-64. (PMID: 21502126)
J Exp Biol. 2008 May;211(Pt 9):1402-13. (PMID: 18424674)
IEEE Trans Neural Syst Rehabil Eng. 2011 Dec;19(6):652-9. (PMID: 21968791)
Med Sci Sports Exerc. 2014 Sep;46(9):1831-9. (PMID: 24504428)
Arch Phys Med Rehabil. 2016 Apr;97(4):619-632.e1. (PMID: 26686877)
J Appl Physiol (1985). 2004 Jan;96(1):343-51. (PMID: 12972441)
J Appl Physiol (1985). 2016 Nov 1;121(5):1226-1233. (PMID: 27687561)
PLoS One. 2015 Aug 19;10(8):e0135342. (PMID: 26288361)
PLoS One. 2017 Sep 19;12(9):e0184054. (PMID: 28926613)

R03 HD092639 United States HD NICHD NIH HHS

Keywords: biomechanics; energetics; exercise; locomotion; metabolics

figshare 10.6084/m9.figshare.7473191

Date Created: 20190111 Date Completed: 20200617 Latest Revision: 20210730

20231215

PMC6459384

10.1152/japplphysiol.00714.2018

30629472