Search

Tools for objective monitoring of home-based training and physical behavior (PB) in (pre)sarcopenic older adults are needed. The present study explored two approaches with machine learning models, including accelerometer data either with or without additional gyroscope data (in an inertial measurement unit). Twenty-five community-dwelling (pre)sarcopenic adults mean 80.7 [5.5] years) performed the Otago exercise protocol (OEP) and PB modules (e.g., sitting or walking) while wearing an inertial measurement unit on the lower back (Dynaport MoveMonitor; McRoberts, The Hague, The Netherlands). Machine learning (ML) models for classification were developed by two approaches (top-down and bottom-up approaches) and with two levels of classification: general (no wear, OEP, and PB) and detailed (all subclassifications). Classification output was compared with video recordings. For the bottom-up approach, one ML model was developed. For the top-down approach, data were first classified as no wear, OEP, or PB. Thereafter, OEP and PB were subclassified by one ML model each into subclassification. Only classification of the general classification no wear and the subclassification sitting/lying reached the acceptable performance threshold of 80%. This result was independent of the approach used. Moreover, a gyroscope did not improve performance. Despite the progress in ML techniques and monitors, objective compliance registrations remain challenging. [ABSTRACT FROM AUTHOR]

Background: The aim was to determine the reliability and validity of IPAQ measured sedentary behaviour (SB) and moderate–vigorous physical activity (MVPA) in older persons whilst examining any sex differences in reliability and validity results. Method: 89 participants (73.7 ± 6.3 years, 54% female) completed the IPAQ. Participants were fitted with a thigh mounted triaxial accelerometer (GeneActiv Original) for seven consecutive days and subsequently completed a second IPAQ. Results: IPAQ showed weak reliability qualities for Total SB (h·week-1) and 10 minute MVPA (accumulated in bouts ≥ 10 continuous minutes, h·week-1). IPAQ had poor concurrent validity qualities for Total SB, 10 minute MVPA, but not Sporadic MVPA (accumulated in bouts < 10 continuous minutes, h·week-1). IPAQ only categorised participant physical behaviour classification correctly 2% of the time. Sex differences were only present for the correlation slope of IPAQ 10 minute MVPA reliability measures. Conclusion: Our data suggests that the IPAQ is not suitable for assessing older adults habitual physical behaviour. [ABSTRACT FROM AUTHOR]

Accurate monitoring of sedentary behaviour and physical activity is key to investigate their exact role in healthy ageing. To date, accelerometers using cut-off point models are most preferred for this, however, machine learning seems a highly promising future alternative. Hence, the current study compared between cut-off point and machine learning algorithms, for optimal quantification of sedentary behaviour and physical activity intensities in the elderly. Thus, in a heterogeneous sample of forty participants (aged ≥60 years, 50% female) energy expenditure during laboratory-based activities (ranging from sedentary behaviour through to moderate-to-vigorous physical activity) was estimated by indirect calorimetry, whilst wearing triaxial thigh-mounted accelerometers. Three cut-off point algorithms and a Random Forest machine learning model were developed and cross-validated using the collected data. Detailed analyses were performed to check algorithm robustness, and examine and benchmark both overall and participant-specific balanced accuracies. This revealed that the four models can at least be used to confidently monitor sedentary behaviour and moderate-to-vigorous physical activity. Nevertheless, the machine learning algorithm outperformed the cut-off point models by being robust for all individual’s physiological and non-physiological characteristics and showing more performance of an acceptable level over the whole range of physical activity intensities. Therefore, we propose that Random Forest machine learning may be optimal for objective assessment of sedentary behaviour and physical activity in older adults using thigh-mounted triaxial accelerometry. [ABSTRACT FROM AUTHOR]