Extracting aerobic system dynamics during unsupervised activities of daily living using wearable sensor machine learning models.
J Appl Physiol (1985)
; 124(2): 473-481, 2018 02 01.
Article
em En
| MEDLINE
| ID: mdl-28596271
ABSTRACT
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 (VÌo2) by wearable sensors in realistic settings might permit development of a practical tool for the study of the longitudinal aerobic system dynamics (i.e., VÌo2 kinetics). This study evaluated aerobic system dynamics based on predicted VÌo2 data obtained from wearable sensors during unsupervised activities of daily living (µADL). Thirteen healthy men performed a laboratory-controlled moderate exercise protocol and were monitored for ≈6 h/day for 4 days (µADL data). Variables derived from hip accelerometer (ACCHIP), heart rate monitor, and respiratory bands during µADL were extracted and processed by a validated random forest regression model to predict VÌo2. The aerobic system analysis was based on the frequency-domain analysis of ACCHIP and predicted VÌo2 data obtained during µADL. Optimal samples for frequency domain analysis (constrained to ≤0.01 Hz) were selected when ACCHIP was higher than 0.05 g at a given frequency (i.e., participants were active). The temporal characteristics of predicted VÌo2 data during µADL correlated with the temporal characteristics of measured VÌo2 data during laboratory-controlled protocol ([Formula see text] = 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.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Consumo de Oxigênio
/
Atividades Cotidianas
/
Aprendizado de Máquina
/
Dispositivos Eletrônicos Vestíveis
Tipo de estudo:
Guideline
/
Prognostic_studies
/
Screening_studies
Limite:
Adult
/
Humans
/
Male
Idioma:
En
Revista:
J Appl Physiol (1985)
Assunto da revista:
FISIOLOGIA
Ano de publicação:
2018
Tipo de documento:
Article
País de afiliação:
Canadá