Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the two models on two physical movement datasets collected from several volunteers who carried tri-axial accelerometer sensors. The first dataset is from the UCI machine learning repository, which contains 14 different activities-of-daily-life (ADL) and is collected from 16 volunteers who carried a single wrist-worn tri-axial accelerometer. The second dataset includes ten other ADLs and is gathered from eight volunteers who placed the sensors on their hips. Our experiment results show that the RNN model provides accurate performance compared to the state-of-the-art methods in classifying the fundamental movement patterns with an overall accuracy of 84.89% and an overall F1-score of 82.56%. The results indicate that our method provides the medical doctors and trainers a promising way to track and understand a patient’s physical activities precisely for better treatment.

There is solid evidence for an association between physical activity and metabolic health outcomes in children and youth, but for methodological reasons most studies describe the intensity spectrum using only a few summary measures. We aimed to determine the multivariate physical activity intensity signature associated with metabolic health in a large and diverse sample of children and youth, by investigating the association pattern for the entire physical intensity spectrum. We used pooled data from 11 studies and 11,853 participants aged 5.8-18.4 years included in the International Children's Accelerometry Database. We derived 14 accelerometry-derived (ActiGraph) physical activity variables covering the intensity spectrum (from 0-99 to ≥8000 counts per minute). To handle the multicollinearity among these variables, we used multivariate pattern analysis to establish the associations with indices of metabolic health (abdominal fatness, insulin sensitivity, lipid metabolism, blood pressure). A composite metabolic health score was used as the main outcome variable. Associations with the composite metabolic health score were weak for sedentary time and light physical activity, but gradually strengthened with increasing time spent in moderate and vigorous intensities (up to 4000-5000 counts per minute). Association patterns were fairly consistent across sex and age groups, but varied across different metabolic health outcomes. This novel analytic approach suggests that vigorous intensity, rather than less intense activities or sedentary behavior, are related to metabolic health in children and youth.

Introduction: The United Kingdom and World Health Organization recently changed their youth physical activity (PA) guidelines from 60 min of moderate- to vigorous-intensity PA (MVPA) every day, to an average of 60 min of MVPA per day, over a week. The changes are based on expert opinion due to insufficient evidence comparing health outcomes associated with different guideline definitions. This study used the International Children’s Accelerometry Database to compare approaches to calculating youth PA compliance and associations with health indicators. Methods: Cross-sectional accelerometer data (n = 21,612, 5–18 yr) were used to examine compliance with four guideline definitions: daily method (DM; ≥60 min MVPA every day), average method (AM; average of ≥60 min MVPA per day), AM5 (AM compliance and ≥5 min of vigorous PA [VPA] on ≥3 d), and AM15 (AM compliance and ≥15 min VPA on ≥3 d). Associations between compliance and health indicators were examined for all definitions. Results: Compliance varied from 5.3% (DM) to 29.9% (AM). Associations between compliance and health indicators were similar for AM, AM5, and AM15. For example, compliance with AM, AM5, and AM15 was associated with a lower BMI z-score (statistics are coefficient [95% CI]): AM (−0.28 [−0.33 to −0.23]), AM5 (−0.28 [−0.33 to −0.23], and AM15 (−0.30 [−0.35 to −0.25]). Associations between compliance and health indicators for DM were similar/weaker, possibly reflecting fewer DM-compliant participants with health data and lower variability in exposure/outcome data. Conclusions: Youth completing 60 min of MVPA every day do not experience superior health benefits to youth completing an average of 60 min of MVPA per day. Guidelines should encourage youth to achieve an average of 60 min of MVPA per day. Different guideline definitions affect inactivity prevalence estimates; this must be considered when analyzing data and comparing studies.

Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify the physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the proposed models on two physical movement datasets collected from several volunteers who carried tri-axial accelerometer sensors. The first dataset is from the UCI machine learning repository, which contains 14 different activities-of-daily-life (ADL) and is collected from 16 volunteers who carried a single wrist-worn tri-axial accelerometer. The second dataset includes ten other ADLs and is gathered from 8 volunteers who placed the sensors on their hips. Our experiment results show that the RNN model provides the accuracy performance compared to the state-of-the-art methods in classifying the fundamental movement patterns with an overall accuracy of 84.89% and an overall F1-score of 82.56%. Our results indicate that the proposed method will provide the medical doctors and trainers a promising way to precisely track and understand a patient’s physical activities for better treatment.