Estimation of physical activity using accelerometry in adult populations: Using the Sensewear Armband and the ACT24 as comparison tools for the estimation of energy expenditure and physical activity intensity by the Sojourn method

Wrist-worn fitness trackers and smartwatches are proliferating with an incessant attention towards health tracking. Given the growing popularity of wrist-worn devices across all age groups, a rigorous evaluation for recognizing hallmark measures of physical activities and estimating energy expenditure is needed to compare their accuracy across the lifespan. The goal of the study was to build machine learning models to recognize physical activity type (sedentary, locomotion, and lifestyle) and intensity (low, light, and moderate), identify individual physical activities, and estimate energy expenditure. The primary aim of this study was to build and compare models for different age groups: young [20-50 years], middle (50-70 years], and old (70-89 years]. Participants (n = 253, 62% women, aged 20-89 years old) performed a battery of 33 daily activities in a standardized laboratory setting while wearing a portable metabolic unit to measure energy expenditure that was used to gauge metabolic intensity. Tri-axial accelerometer collected data at 80-100 Hz from the right wrist that was processed for 49 features. Results from random forests algorithm were quite accurate in recognizing physical activity type, the F1-Score range across age groups was: sedentary [0.955 – 0.973], locomotion [0.942 – 0.964], and lifestyle [0.913 – 0.949]. Recognizing physical activity intensity resulted in lower performance, the F1-Score range across age groups was: sedentary [0.919 – 0.947], light [0.813 – 0.828], and moderate [0.846 – 0.875]. The root mean square error range was [0.835 – 1.009] for the estimation of energy expenditure. The F1-Score range for recognizing individual physical activities was [0.263 – 0.784]. Performances were relatively similar and the accelerometer data features were ranked similarly between age groups. In conclusion, data features derived from wrist worn accelerometers lead to high-moderate accuracy estimating physical activity type, intensity and energy expenditure and are robust to potential age-differences.

Download Full-text

Validity and Comparability of a Wrist-Worn Accelerometer in Children

Journal of Physical Activity and Health ◽

10.1123/jpah.9.3.389 ◽

2012 ◽

Vol 9 (3) ◽

pp. 389-393 ◽

Cited By ~ 43

Author(s):

Orjan Ekblom ◽

Gisela Nyberg ◽

Elin Ekblom Bak ◽

Ulf Ekelund ◽

Claude Marcus

Keyword(s):

Physical Activity ◽

Energy Expenditure ◽

Roc Analysis ◽

Living Condition ◽

Criterion Measure ◽

Physical Activity Intensity ◽

Free Living ◽

Activity Intensity ◽

Mechanical Shaker

Background:Wrist-worn accelerometers may provide an alternative to hip-worn monitors for assessing physical activity as they are easier to wear and may thus facilitate long-term recordings. The current study aimed at a) assessing the validity of the Actiwatch (wrist-worn) for estimating energy expenditure, b) determining cut-off values for light, moderate, and vigorous activities, c) studying the comparability between the Actiwatch and the Actigraph (hip-worn), and d) assessing reliability.Methods:For validity, indirect calorimetry was used as criterion measure. ROC-analyses were applied to identify cut-off values. Comparability was tested by simultaneously wearing of the 2 accelerometers during free-living condition. Reliability was tested in a mechanical shaker.Results:All-over correlation between accelerometer output and energy expenditure were found to be 0.80 (P < .001).Based on ROC-analysis, cut-off values for 1.5, 3, and 6 METs were found to be 80, 262, and 406 counts per 15 s, respectively. Energy expenditure estimates differed between the Actiwatch and the Actigraph (P < .05). The intra- and interinstrument coefficient of variation of the Actiwatch ranged between 0.72% and 8.4%.Conclusion:The wrist-worn Actiwatch appears to be valid and reliable for estimating energy expenditure and physical activity intensity in children aged 8 to 10 years.

Download Full-text

A proper reference metabolic equivalent value to assess physical activity intensity in Japanese female nurses

Women s Midlife Health ◽

10.1186/s40695-019-0048-3 ◽

2019 ◽

Vol 5 (1) ◽

Author(s):

Yuki Ideno ◽

Kunihiko Hayashi ◽

Jung Su Lee ◽

Yukiko Miyazaki ◽

Shosuke Suzuki

Keyword(s):

Physical Activity ◽

Energy Expenditure ◽

Vigorous Physical Activity ◽

Working Women ◽

Physical Activity Intensity ◽

Self Administration ◽

Activity Intensity ◽

Metabolic Equivalents ◽

Epidemiological Surveys ◽

Mcmc Simulation

Abstract Background Various questionnaires have been developed to assess physical activity, but only a few simple questionnaires are suitable for self-administration in large groups of midlife working women. This study examined the usefulness of the Japan Nurses’ Health Study (JNHS) questionnaire for self-administered physical activity surveys. Methods The JNHS physical activity questionnaire consisted of items covering seven degrees of intensity. The metabolic equivalents (METs) for the physical activity intensity of the questionnaire were estimated from energy expenditure as measured by a uniaxial accelerometer with the Markov Chain Monte Carlo (MCMC) simulation. The estimated METs were then assigned to the JNHS baseline survey data, and the total energy expenditure (TEE) and the time spent performing ≥3 METs hour of physical activity, called moderate to vigorous intensity physical activity (MVPA), were calculated. Results For working situations, application of the MCMC simulation resulted in estimated reference values of 1.2 METs for “sitting work”, 1.6 METs for “standing work”, 1.8 METs for “walking work”, and 4.5 METs for “heavy work”. For non-working situations, the estimated values were 1.1 METs for sedentary time, 2.4 METs for “moderate physical activity”, 4.4 METs for “vigorous physical activity”, and 9.4 METs for “very vigorous physical activity”. When these estimated METs were used, the mean TEE/day was 1808 kcal. This corresponded to − 3.0% of the TEE/day generated by the accelerometer. These estimated MET values showed similar results as a previous study measuring activity using the doubly-labeled water method. The number of hours per week of MVPA significantly decreased with age, which is also consistent with previous findings. Conclusions Estimated reference MET values in this study were similar to those in previous studies of Japanese women. The JNHS questionnaire is therefore useful for epidemiological surveys of midlife working women because it assigns estimated MET values as physical activity intensities.

Download Full-text