Dataset Information

Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning.

ABSTRACT: Accelerometer-based fitness trackers and smartwatches are proliferating with incessant attention towards health tracking. Despite their growing popularity, accurately measuring hallmark measures of physical activities has yet to be accomplished in adults of all ages. In this work, we evaluated the performance of four machine learning models: decision tree, random forest, extreme gradient boosting (XGBoost) and least absolute shrinkage and selection operator (LASSO), to estimate the hallmark measures of physical activities in young (20-50 years), middle-aged (50-70 years], and older adults (70-89 years]. Our models were built to recognize physical activity types, recognize physical activity intensities, estimate energy expenditure (EE) and recognize individual physical activities using wrist-worn tri-axial accelerometer data (33 activities per participant) from a large sample of participants (n = 253, 62% women, aged 20-89 years old). Results showed that the machine learning models were quite accurate at recognizing physical activity type and intensity and estimating energy expenditure. However, models performed less optimally when recognizing individual physical activities. F1-Scores derived from XGBoost's models were high for sedentary (0.955-0.973), locomotion (0.942-0.964) and lifestyle (0.913-0.949) activity types with no apparent difference across age groups. Low (0.919-0.947), light (0.813-0.828) and moderate (0.846-0.875) physical activity intensities were also recognized accurately. The root mean square error range for EE was approximately 1 equivalent of resting EE [0.835-1.009 METs]. Generally, random forest and XGBoost models outperformed other models. In conclusion, machine learning models to label physical activity types, activity intensity and energy expenditure are accurate and there are minimal differences in their performance across young, middle-aged and older adults.

SUBMITTER: Mardini MT

PROVIDER: S-EPMC8150764 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Sufficient physical activity (PA) reduces the risk of a myriad of diseases and preserves physical capabilities in later life. While there have been significant achievements in mapping accelerations to real-life movements using machine learning (ML), errors continue to be common, particularly for wrist-worn devices. It remains unknown whether ML models are robust for estimating age-related loss of physical function. In this study, we evaluated the performance of ML models (XGBoost and LASSO) to estimate the hallmark measures of PA in low physical performance (LPP) and high physical performance (HPP) groups. Our models were built to recognize PA types and intensities, identify each individual activity, and estimate energy expenditure (EE) using wrist-worn accelerometer data (33 activities per participant) from a large sample of participants (n = 247, 57% females, aged 60+ years). Results indicated that the ML models were accurate in recognizing PA by type and intensity while also estimating EE accurately. However, the models built to recognize individual activities were less robust. Across all tasks, XGBoost outperformed LASSO. XGBoost obtained F1-Scores for sedentary (0.932 ± 0.005), locomotion (0.946 ± 0.003), lifestyle (0.927 ± 0.006), and strength flexibility exercise (0.915 ± 0.017) activity type recognition tasks. The F1-Scores for recognizing low, light, and moderate activity intensity were (0.932&nbsp;±&nbsp;0.005), (0.840 ± 0.004), and (0.869 ± 0.005), respectively. The root mean square error for EE estimation was 0.836 ± 0.059 METs. There was no evidence showing that splitting the participants into the LPP and HPP groups improved the models' performance on estimating the hallmark measures of physical activities. In conclusion, using features derived from wrist-worn accelerometer data, machine learning models can accurately recognize PA types and intensities and estimate EE for older adults with high and low physical function.

Project description:Accelerometers are widely used to measure physical activity behaviour, including in children. The traditional method for processing acceleration data uses cut points to define physical activity intensity, relying on calibration studies that relate the magnitude of acceleration to energy expenditure. However, these relationships do not generalise across diverse populations and hence they must be parametrised for each subpopulation (e.g., age groups) which is costly and makes studies across diverse populations and over time difficult. A data-driven approach that allows physical activity intensity states to emerge from the data, without relying on parameters derived from external populations, offers a new perspective on this problem and potentially improved results. We applied an unsupervised machine learning approach, namely a hidden semi-Markov model, to segment and cluster the raw accelerometer data recorded (using a waist-worn ActiGraph GT3X+) from 279 children (9-38 months old) with a diverse range of developmental abilities (measured using the Paediatric Evaluation of Disability Inventory-Computer Adaptive Testing measure). We benchmarked this analysis with the cut points approach, calculated using thresholds from the literature which had been validated using the same device and for a population which most closely matched ours. Time spent active as measured by this unsupervised approach correlated more strongly with PEDI-CAT measures of the child's mobility (R2: 0.51 vs 0.39), social-cognitive capacity (R2: 0.32 vs 0.20), responsibility (R2: 0.21 vs 0.13), daily activity (R2: 0.35 vs 0.24), and age (R2: 0.15 vs 0.1) than that measured using the cut points approach. Unsupervised machine learning offers the potential to provide a more sensitive, appropriate, and cost-effective approach to quantifying physical activity behaviour in diverse populations, compared to the current cut points approach. This, in turn, supports research that is more inclusive of diverse or rapidly changing populations.

Project description:BACKGROUND:Physical activity (PA) level is associated with multiple health benefits during early childhood. However, inconsistency in the methods for quantification of PA levels among preschoolers remains a problem. OBJECTIVE:This study aimed to develop PA intensity cut points for wrist-worn accelerometers by using machine learning (ML) approaches to assess PA in preschoolers. METHODS:Wrist- and hip-derived acceleration data were collected simultaneously from 34 preschoolers on 3 consecutive preschool days. Two supervised ML models, receiver operating characteristic curve (ROC) and ordinal logistic regression (OLR), and one unsupervised ML model, k-means cluster analysis, were applied to establish wrist-worn accelerometer vector magnitude (VM) cut points to classify accelerometer counts into sedentary behavior, light PA (LPA), moderate PA (MPA), and vigorous PA (VPA). Physical activity intensity levels identified by hip-worn accelerometer VM cut points were used as reference to train the supervised ML models. Vector magnitude counts were classified by intensity based on three newly established wrist methods and the hip reference to examine classification accuracy. Daily estimates of PA were compared to the hip-reference criterion. RESULTS:In total, 3600 epochs with matched hip- and wrist-worn accelerometer VM counts were analyzed. All ML approaches performed differently on developing PA intensity cut points for wrist-worn accelerometers. Among the three ML models, k-means cluster analysis derived the following cut points: ?2556 counts per minute (cpm) for sedentary behavior, 2557-7064 cpm for LPA, 7065-14532 cpm for MPA, and ?14533 cpm for VPA; in addition, k-means cluster analysis had the highest classification accuracy, with more than 70% of the total epochs being classified into the correct PA categories, as examined by the hip reference. Additionally, k-means cut points exhibited the most accurate estimates on sedentary behavior, LPA, and VPA as the hip reference. None of the three wrist methods were able to accurately assess MPA. CONCLUSIONS:This study demonstrates the potential of ML approaches in establishing cut points for wrist-worn accelerometers to assess PA in preschoolers. However, the findings from this study warrant additional validation studies.

Project description:BackgroundThe rapid advancements in science and technology of wrist-wearable activity devices offer considerable potential for clinical applications. Self-monitoring of physical activity (PA) with activity devices is helpful to improve the PA levels of adolescents. However, knowing the accuracy of activity devices in adolescents is necessary to identify current levels of PA and assess the effectiveness of intervention programs designed to increase PA.ObjectiveThe study aimed to determine the validity of the 11 commercially available wrist-wearable activity devices for monitoring total steps and total 24-hour total energy expenditure (TEE) in healthy adolescents under simulated free-living conditions.MethodsNineteen (10 male and 9 female) participants aged 14 to 18 years performed a 24-hour activity cycle in a metabolic chamber. Each participant simultaneously wore 11 commercial wrist-wearable activity devices (Mi Band 2 [XiaoMi], B2 [Huawei], Bong 2s [Meizu], Amazfit [Huamei], Flex [Fitbit], UP3 [Jawbone], Shine 2 [Misfit], GOLiFE Care-X [GoYourLife], Pulse O2 [Withings], Vivofit [Garmin], and Loop [Polar Electro]) and one research-based triaxial accelerometer (GT3X+ [ActiGraph]). Criterion measures were total EE from the metabolic chamber (mcTEE) and total steps from the GT3X+ (AGsteps).ResultsPearson correlation coefficients r for 24-hour TEE ranged from .78 (Shine 2, Amazfit) to .96 (Loop) and for steps ranged from 0.20 (GOLiFE) to 0.57 (Vivofit). Mean absolute percent error (MAPE) for TEE ranged from 5.7% (Mi Band 2) to 26.4% (Amazfit) and for steps ranged from 14.2% (Bong 2s) to 27.6% (Loop). TEE estimates from the Mi Band 2, UP3, Vivofit, and Bong 2s were equivalent to mcTEE. Total steps from the Bong 2s were equivalent to AGsteps.ConclusionsOverall, the Bong 2s had the best accuracy for estimating TEE and total steps under simulated free-living conditions. Further research is needed to examine the validity of these devices in different types of physical activities under real-world conditions.

Dataset Information

Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets