Extracting aerobic system dynamics during unsupervised activities of daily living using wearable sensor machine learning models

被引:27
作者
Beltrame, Thomas [1 ,2 ]
Amelard, Robert [3 ,4 ]
Wong, Alexander [3 ,4 ]
Hughson, Richard L. [1 ,4 ]
机构
[1] Univ Waterloo, Fac Appl Hlth Sci, Waterloo, ON, Canada
[2] Conselho Nacl Desenvolvimento Cient & Tecnol, Brasilia, DF, Brazil
[3] Univ Waterloo, Dept Syst Design Engn, Waterloo, ON, Canada
[4] Schlegel Univ Waterloo, Res Inst Aging, 250 Laurelwood Dr, Waterloo, ON N2J 0E2, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
aerobic fitness; kinetics; machine learning; oxygen uptake; smart devices; OXYGEN-UPTAKE KINETICS; VO2; KINETICS; GAS-EXCHANGE; EXERCISE; RESPONSES; LIMITATION; TRANSPORT; HUMANS; ONSET;
D O I
10.1152/japplphysiol.00299.2017
中图分类号
Q4 [生理学];
学科分类号
071003 ;
摘要
Physical activity levels are related through algorithms to the energetic demand, with no information regarding the integrity of the multiple physiological systems involved in the energetic supply. Longitudinal analysis of the oxygen uptake ((V) over dotO(2)) by wearable sensors in realistic settings might permit development of a practical tool for the study of the longitudinal aerobic system dynamics (i.e., (V) over dotO(2) kinetics). This study evaluated aerobic system dynamics based on predicted (V) over dotO(2) data obtained from wearable sensors during unsupervised activities of daily living (mu ADL). Thirteen healthy men performed a laboratory-controlled moderate exercise protocol and were monitored for approximate to 6 h/day for 4 days (mu ADL data). Variables derived from hip accelerometer (ACC(HIP)), heart rate monitor, and respiratory bands during mu ADL were extracted and processed by a validated random forest regression model to predict (V) over dotO(2). The aerobic system analysis was based on the frequency-domain analysis of ACC(HIP) and predicted (V) over dotO(2) data obtained during mu ADL. Optimal samples for frequency domain analysis (constrained to <= 0.01 Hz) were selected when ACC(HIP) was higher than 0.05 g at a given frequency (i.e., participants were active). The temporal characteristics of predicted (V) over dotO(2) data during mu ADL correlated with the temporal characteristics of measured (V) over dotO(2) data during laboratory-controlled protocol (r = 0.82, P < 0.001, n = 13). In conclusion, aerobic system dynamics can be investigated during unsupervised activities of daily living by wearable sensors. Although speculative, these algorithms have the potential to be incorporated into wearable systems for early detection of changes in health status in realistic environments by detecting changes in aerobic response dynamics. NEW & NOTEWORTHY The early detection of subclinical aerobic system impairments might be indicative of impaired physiological reserves that impact the capacity for physical activity. This study is the first to use wearable sensors in unsupervised activities of daily living in combination with novel machine learning algorithms to investigate the aerobic system dynamics with the potential to contribute to models of functional health status and guide future individualized health care in the normal population.
引用
收藏
页码:473 / 481
页数:9
相关论文
共 38 条
  • [1] Alexander NB, 2003, J GERONTOL A-BIOL, V58, P734
  • [2] Personalization of Energy Expenditure Estimation in Free Living Using Topic Models
    Altini, Marco
    Casale, Pierluigi
    Penders, Julien F.
    Amft, Oliver
    [J]. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2015, 19 (05) : 1577 - 1586
  • [3] MUSCLE ENERGETICS AND PULMONARY OXYGEN-UPTAKE KINETICS DURING MODERATE EXERCISE
    BARSTOW, TJ
    BUCHTHAL, S
    ZANCONATO, S
    COOPER, DM
    [J]. JOURNAL OF APPLIED PHYSIOLOGY, 1994, 77 (04) : 1742 - 1749
  • [4] Linear and non-linear contributions to oxygen transport and utilization during moderate random exercise in humans
    Beltrame, T.
    Hughson, R. L.
    [J]. EXPERIMENTAL PHYSIOLOGY, 2017, 102 (05) : 563 - 577
  • [5] Prediction of oxygen uptake dynamics by machine learning analysis of wearable sensors during activities of daily living
    Beltrame, T.
    Amelard, R.
    Wong, A.
    Hughson, R. L.
    [J]. SCIENTIFIC REPORTS, 2017, 7
  • [6] Aerobic system analysis based on oxygen uptake and hip acceleration during random over-ground walking activities
    Beltrame, Thomas
    Hughson, Richard L.
    [J]. AMERICAN JOURNAL OF PHYSIOLOGY-REGULATORY INTEGRATIVE AND COMPARATIVE PHYSIOLOGY, 2017, 312 (01) : R93 - R100
  • [7] Estimating oxygen uptake and energy expenditure during treadmill walking by neural network analysis of easy-to-obtain inputs
    Beltrame, Thomas
    Amelard, Robert
    Villar, Rodrigo
    Shafiee, Mohammad J.
    Wong, Alexander
    Hughson, Richard L.
    [J]. JOURNAL OF APPLIED PHYSIOLOGY, 2016, 121 (05) : 1226 - 1233
  • [8] Relationship between oxygen consumption kinetics and BODE Index in COPD patients
    Borghi-Silva, Audrey
    Beltrame, Thomas
    Reis, Michel Silva
    Malosa Sampaio, Luciana Maria
    Catai, Aparecida Maria
    Arena, Ross
    Costa, Dirceu
    [J]. INTERNATIONAL JOURNAL OF CHRONIC OBSTRUCTIVE PULMONARY DISEASE, 2012, 7 : 711 - 718
  • [9] Random forests
    Breiman, L
    [J]. MACHINE LEARNING, 2001, 45 (01) : 5 - 32
  • [10] Validity of the Actical for estimating free-living physical activity
    Crouter, Scott E.
    DellaValle, Diane M.
    Horton, Magdalene
    Haas, Jere D.
    Frongillo, Edward A.
    Bassett, David R., Jr.
    [J]. EUROPEAN JOURNAL OF APPLIED PHYSIOLOGY, 2011, 111 (07) : 1381 - 1389