Composite activity type and stride-specific energy expenditure estimation model for thigh-worn accelerometry.

Accurately measuring energy expenditure during physical activity outside of the laboratory is challenging, especially on a large scale. Thigh-worn accelerometers have gained popularity due to the possibility to accurately detect physical activity types. The use of machine learning techniques for activity classification and energy expenditure prediction may improve accuracy over current methods. Here, we developed a novel composite energy expenditure estimation model by combining an activity classification model with a stride specific energy expenditure model for walking, running, and cycling. We first trained a supervised deep learning activity classification model using pooled data from available adult accelerometer datasets. The composite energy expenditure model was then developed and validated using additional data based on a sample of 69 healthy adult participants (49% female; age = 25.2 ± 5.8 years) who completed a standardised activity protocol with indirect calorimetry as the reference measure. The activity classification model showed an overall accuracy of 99.7% across all five activity types during validation. The composite model for estimating energy expenditure achieved a mean absolute percentage error of 10.9%. For running, walking, and cycling, the composite model achieved a mean absolute percentage error of 6.6%, 7.9% and 16.1%, respectively. The integration of thigh-worn accelerometers with machine learning models provides a highly accurate method for classifying physical activity types and estimating energy expenditure. Our novel composite model approach improves the accuracy of energy expenditure measurements and supports better monitoring and assessment methods in non-laboratory settings.

Lendt C ，Hansen N ，Froböse I ，Stewart T ... -  《International Journal of Behavioral Nutrition and Physical Activity》

Thigh-worn accelerometry: a comparative study of two no-code classification methods for identifying physical activity types.

The more accurate we can assess human physical behaviour in free-living conditions the better we can understand its relationship with health and wellbeing. Thigh-worn accelerometry can be used to identify basic activity types as well as different postures with high accuracy. User-friendly software without the need for specialized programming may support the adoption of this method. This study aims to evaluate the classification accuracy of two novel no-code classification methods, namely SENS motion and ActiPASS. A sample of 38 healthy adults (30.8 ± 9.6 years; 53% female) wore the SENS motion accelerometer (12.5 Hz; ±4 g) on their thigh during various physical activities. Participants completed standardized activities with varying intensities in the laboratory. Activities included walking, running, cycling, sitting, standing, and lying down. Subsequently, participants performed unrestricted free-living activities outside of the laboratory while being video-recorded with a chest-mounted camera. Videos were annotated using a predefined labelling scheme and annotations served as a reference for the free-living condition. Classification output from the SENS motion software and ActiPASS software was compared to reference labels. A total of 63.6 h of activity data were analysed. We observed a high level of agreement between the two classification algorithms and their respective references in both conditions. In the free-living condition, Cohen's kappa coefficients were 0.86 for SENS and 0.92 for ActiPASS. The mean balanced accuracy ranged from 0.81 (cycling) to 0.99 (running) for SENS and from 0.92 (walking) to 0.99 (sedentary) for ActiPASS across all activity types. The study shows that two available no-code classification methods can be used to accurately identify basic physical activity types and postures. Our results highlight the accuracy of both methods based on relatively low sampling frequency data. The classification methods showed differences in performance, with lower sensitivity observed in free-living cycling (SENS) and slow treadmill walking (ActiPASS). Both methods use different sets of activity classes with varying definitions, which may explain the observed differences. Our results support the use of the SENS motion system and both no-code classification methods.

Lendt C ，Braun T ，Biallas B ，Froböse I ，Johansson PJ ... -  《International Journal of Behavioral Nutrition and Physical Activity》

Wrist-Worn Activity Trackers in Laboratory and Free-Living Settings for Patients With Chronic Pain: Criterion Validity Study.

Physical activity is evidently a crucial part of the rehabilitation process for patients with chronic pain. Modern wrist-worn activity tracking devices seemingly have a great potential to provide objective feedback and assist in the adoption of healthy physical activity behavior by supplying data of energy expenditure expressed as metabolic equivalent of task units (MET). However, no studies of any wrist-worn activity tracking devices' have examined criterion validity in estimating energy expenditure, heart rate, or step count in patients with chronic pain. The aim was to determine the criterion validity of wrist-worn activity tracking devices for estimations of energy expenditure, heart rate, and step count in a controlled laboratory setting and free-living settings for patients with chronic pain. In this combined laboratory and field validation study, energy expenditure, heart rate, and step count were simultaneously estimated by a wrist-worn activity tracker (Fitbit Versa), indirect calorimetry (Jaeger Oxycon Pro), and a research-grade hip-worn accelerometer (ActiGraph GT3X) during treadmill walking at 3 speeds (3.0 km/h, 4.5 km/h, and 6.0 km/h) in the laboratory setting. Energy expenditure and step count were also estimated by the wrist-worn activity tracker in free-living settings for 72 hours. The criterion validity of each measure was determined using intraclass and Spearman correlation, Bland-Altman plots, and mean absolute percentage error. An analysis of variance was used to determine whether there were any significant systematic differences between estimations. A total of 42 patients (age: 25-66 years; male: 10/42, 24%; female: 32/42, 76%), living with chronic pain (duration, in years: mean 9, SD 6.72) were included. At baseline, their mean pain intensity was 3.5 (SD 1.1) out of 6 (Multidimensional Pain Inventory, Swedish version). Results showed that the wrist-worn activity tracking device (Fitbit Versa) systematically overestimated energy expenditure when compared to the criterion standard (Jaeger Oxycon Pro) and the relative criterion standard (ActiGraph GT3X). Poor agreement and poor correlation were shown between Fitbit Versa and both Jaeger Oxycon Pro and ActiGraph GT3X for estimated energy expenditure at all treadmill speeds. Estimations of heart rate demonstrated poor to fair agreement during laboratory-based treadmill walks. For step count, the wrist-worn devices showed fair agreement and fair correlation at most treadmill speeds. In free-living settings; however, the agreement for step count between the wrist-worn device and waist-worn accelerometer was good, and the correlation was excellent. The wrist-worn device systematically overestimated energy expenditure and showed poor agreement and correlation compared to the criterion standard (Jaeger Oxycon Pro) and the relative criterion standard (ActiGraph GT3X), which needs to be considered when used clinically. Step count measured with a wrist-worn device, however, seemed to be a valid estimation, suggesting that future guidelines could include such variables in this group with chronic pain.

Sjöberg V ，Westergren J ，Monnier A ，Lo Martire R ，Hagströmer M ，Äng BO ，Vixner L ... -  《JMIR mHealth and uHealth》

Energy expenditure prediction using a miniaturized ear-worn sensor.

Atallah L ，Leong JJ ，Lo B ，Yang GZ ... -  《-》

Cross-validation and out-of-sample testing of physical activity intensity predictions with a wrist-worn accelerometer.

Montoye AHK ，Westgate BS ，Fonley MR ，Pfeiffer KA ... -  《-》