Dataset Information

Training-induced changes in daily energy expenditure: Methodological evaluation using wrist-worn accelerometer, heart rate monitor, and doubly labeled water technique.

ABSTRACT:

Introduction

Wrist-mounted motion sensors can quantify the volume and intensity of physical activities, but little is known about their long-term validity. Our aim was to validate a wrist motion sensor in estimating daily energy expenditure, including any change induced by long-term participation in endurance and strength training. Supplemental heart rate monitoring during weekly exercise was also investigated.

Methods

A 13-day doubly labeled water (DLW) measurement of total energy expenditure (TEE) was performed twice in healthy male subjects: during two last weeks of a 12-week Control period (n = 15) and during two last weeks of a 12-week combined strength and aerobic Training period (n = 13). Resting energy expenditure was estimated using two equations: one with body weight and age, and another one with fat-free mass. TEE and activity induced energy expenditure (AEE) were determined from motion sensor alone, and from motions sensor combined with heart rate monitor, the latter being worn during exercise only.

Results

When body weight and age were used in the calculation of resting energy expenditure, the motion sensor data alone explained 78% and 62% of the variation in TEE assessed by DLW at the end of Control and Training periods, respectively, with a bias of +1.75 (p <.001) and +1.19 MJ/day (p = .002). When exercise heart rate data was added to the model, the combined wearable device approach explained 85% and 70% of the variation in TEE assessed by DLW with a bias of +1.89 and +1.75 MJ/day (p <.001 for both). While significant increases in TEE and AEE were detected by all methods as a result of participation in regular training, motion sensor approach underestimated the change measured by DLW: +1.13±0.66 by DLW, +0.59±0.69 (p = .004) by motion sensor, and +0.98±0.70 MJ/day by combination of motion sensor and heart rate. Use of fat-free mass in the estimation of resting energy expenditure removed the biases between the wearable device estimations and the golden standard reference method of TEE and demonstrated a training-induced increase in resting energy expenditure by +0.18±0.13 MJ/day (p <.001).

Conclusions

Wrist motion sensor combined with a heart rate monitor during exercise sessions, showed high agreement with the golden standard measurement of daily TEE and its change induced by participation in a long-term training protocol. The positive findings concerning the validity, especially the ability to follow-up the change associated with a lifestyle modification, can be considered significant because they partially determine the feasibility of wearable devices as quantifiers of health-related behavior.

SUBMITTER: Kinnunen H

PROVIDER: S-EPMC6619827 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background: Huntington's disease (HD) leads to altered gait patterns and reduced daily-living physical activity. Accurate measurement of daily-living walking that takes into account involuntary movements (e.g. chorea) is needed. Objective: To evaluate daily-living gait quantity and quality in HD, taking into account irregular movements. Methods: Forty-two individuals with HD and fourteen age-matched non-HD peers completed clinic-based assessments and a standardized laboratory-based circuit of functional activities, wearing inertial measurement units on the wrists, legs, and trunk. These activities were used to train and test an algorithm for the automated detection of walking. Subsequently, 29 HD participants and 22 age-matched non-HD peers wore a tri-axial accelerometer on their non-dominant wrist for 7 days. Measures included gait quantity (e.g., steps per day), gait quality (e.g., regularity) metrics, and percentage of walking bouts with irregular movements. Results: Measures of daily-living gait quantity including step counts, walking time and bouts per day were similar in HD participants and non-HD peers (p > 0.05). HD participants with higher clinician-rated upper body chorea had a greater percentage of walking bouts with irregular movements compared to those with lower chorea (p = 0.060) and non-HD peers (p < 0.001). Even after accounting for irregular movements, within-bout walking consistency was lower in HD participants compared to non-HD peers (p < 0.001), while across-bout variability of these measures was higher (p < 0.001). Many of the daily-living measures were associated with disease-specific measures of motor function. Conclusions: Results suggest that a wrist-worn accelerometer can be used to evaluate the quantity and quality of daily-living gait in people with HD, while accounting for the influence of irregular (choreic-like) movements, and that gait features related to within- and across-bout consistency markedly differ in individuals with HD and non-HD peers.

Project description:Although accelerometry data are widely utilized to estimate physical activity and sedentary behavior among children age 3 years or older, for toddlers age 1 and 2 year(s), accelerometry data recorded during such behaviors have been far less examined. In particular, toddler's unique behaviors, such as riding in a stroller or being carried by an adult, have not yet been examined. The objective of this study was to describe accelerometry signal outputs recorded during participation in nine types of behaviors (i.e., running, walking, climbing up/down, crawling, riding a ride-on toy, standing, sitting, riding in a stroller/wagon, and being carried by an adult) among toddlers. Twenty-four toddlers aged 13 to 35 months (50% girls) performed various prescribed behaviors during free play in a commercial indoor playroom while wearing ActiGraph wGT3X-BT accelerometers on a hip and a wrist. Participants' performances were video-recorded. Based on the video data, accelerometer data were annotated with behavior labels to examine accelerometry signal outputs while performing the nine types of behaviors. Accelerometer data collected during 664 behavior assessments from the 21 participants were used for analysis. Hip vertical axis counts for walking were low (median = 49 counts/5 s). They were significantly lower than those recorded while a toddler was "carried" by an adult (median = 144 counts/5 s; p < 0.01). While standing, sitting, and riding in a stroller, very low hip vertical axis counts were registered (median ≤ 5 counts/5 s). Although wrist vertical axis and vector magnitude counts for "carried" were not higher than those for walking, they were higher than the cut-points for sedentary behaviors. Using various accelerometry signal features, machine learning techniques showed 89% accuracy to differentiate the "carried" behavior from ambulatory movements such as running, walking, crawling, and climbing. In conclusion, hip vertical axis counts alone may be unable to capture walking as physical activity and "carried" as sedentary behavior among toddlers. Machine learning techniques that utilize additional accelerometry signal features could help to recognize behavior types, especially to differentiate being "carried" from ambulatory movements.

Project description:Motor fluctuations in Parkinson's disease are characterized by unpredictability in the timing and duration of dopaminergic therapeutic benefits on symptoms, including bradykinesia and rigidity. These fluctuations significantly impair the quality of life of many Parkinson's patients. However, current clinical evaluation tools are not designed for the continuous, naturalistic (real-world) symptom monitoring needed to optimize clinical therapy to treat fluctuations. Although commercially available wearable motor monitoring, used over multiple days, can augment neurological decision making, the feasibility of rapid and dynamic detection of motor fluctuations is unclear. So far, applied wearable monitoring algorithms are trained on group data. In this study, we investigated the influence of individual model training on short timescale classification of naturalistic bradykinesia fluctuations in Parkinson's patients using a single-wrist accelerometer. As part of the Parkinson@Home study protocol, 20 Parkinson patients were recorded with bilateral wrist accelerometers for a one hour OFF medication session and a one hour ON medication session during unconstrained activities in their own homes. Kinematic metrics were extracted from the accelerometer data from the bodyside with the largest unilateral bradykinesia fluctuations across medication states. The kinematic accelerometer features were compared over the 1 h duration of recording, and medication-state classification analyses were performed on 1 min segments of data. Then, we analyzed the influence of individual versus group model training, data window length, and total number of training patients included in group model training, on classification. Statistically significant areas under the curves (AUCs) for medication induced bradykinesia fluctuation classification were seen in 85% of the Parkinson patients at the single minute timescale using the group models. Individually trained models performed at the same level as the group trained models (mean AUC both 0.70, standard deviation respectively 0.18 and 0.10) despite the small individual training dataset. AUCs of the group models improved as the length of the feature windows was increased to 300 s, and with additional training patient datasets. We were able to show that medication-induced fluctuations in bradykinesia can be classified using wrist-worn accelerometry at the time scale of a single minute. Rapid, naturalistic Parkinson motor monitoring has the clinical potential to evaluate dynamic symptomatic and therapeutic fluctuations and help tailor treatments on a fast timescale.

Project description:BACKGROUND:There has been an increasing interest in understanding the usefulness of wrist-based accelerometer data for physical activity (PA) assessment due to the ease of use and higher user compliance than other body placements. PA assessment studies have relied on machine learning methods which take accelerometer data in forms of variables, or feature vectors. METHODS:In this work, we introduce automated shape feature derivation methods to transform epochs of accelerometer data into feature vectors. As the first step, recurring patterns in the collected data are identified and placed in a codebook. Similarities between epochs of accelerometer data and codebook's patterns are the basis of feature calculations. In this paper, we demonstrate supervised and unsupervised approaches to learn codebooks. We evaluated these methods and compared them with the standard statistical measures for PA assessment. The experiments were performed on 146 participants who wore an ActiGraph GT3X+ accelerometer on the right wrist and performed 33 activities of daily living. RESULTS:Our evaluations show that the shape feature derivation methods were able to perform comparably with the standard wrist model (F1-score: 0.89) for identifying sedentary PAs (F1-scores of 0.86 and 0.85 for supervised and unsupervised methods, respectively). This was also observed for identifying locomotion activities (F1-scores: 0.87, 0.83, and 0.81 for the standard wrist, supervised, unsupervised models, respectively). All the wrist models were able to estimate energy expenditure required for PAs with low error (rMSE: 0.90, 0.93, and 0.90 for the standard wrist, supervised, and unsupervised models, respectively). CONCLUSION:The automated shape feature derivation methods offer insights into the performed activities by providing a summary of repeating patterns in the accelerometer data. Furthermore, they could be used as efficient alternatives (or additions) for manually engineered features, especially important for cases where the latter fail to provide sufficient information to machine learning methods for PA assessment.