Machine Learning to Quantify Physical Activity in Children with Cerebral Palsy: Comparison of Group, Group-Personalized, and Fully-Personalized Activity Classification Models

Pattern recognition methodologies, such as those utilizing machine learning (ML) approaches, have the potential to improve the accuracy and versatility of accelerometer-based assessments of physical activity (PA). Children with cerebral palsy (CP) exhibit significant heterogeneity in relation to impairment and activity limitations; however, studies conducted to date have implemented “one-size fits all” group (G) models. Group-personalized (GP) models specific to the Gross Motor Function Classification (GMFCS) level and fully-personalized (FP) models trained on individual data may provide more accurate assessments of PA; however, these approaches have not been investigated in children with CP. In this study, 38 children classified at GMFCS I to III completed laboratory trials and a simulated free-living protocol while wearing an ActiGraph GT3X+ on the wrist, hip, and ankle. Activities were classified as sedentary, standing utilitarian movements, or walking. In the cross-validation, FP random forest classifiers (99.0–99.3%) exhibited a significantly higher accuracy than G (80.9–94.7%) and GP classifiers (78.7–94.1%), with the largest differential observed in children at GMFCS III. When evaluated under free-living conditions, all model types exhibited significant declines in accuracy, with FP models outperforming G and GP models in GMFCS levels I and II, but not III. Future studies should evaluate the comparative accuracy of personalized models trained on free-living accelerometer data.

Download Full-text

Machine Learning Models for Classifying Physical Activity in Free-Living Preschool Children

Sensors ◽

10.3390/s20164364 ◽

2020 ◽

Vol 20 (16) ◽

pp. 4364 ◽

Cited By ~ 1

Author(s):

Matthew N. Ahmadi ◽

Toby G. Pavey ◽

Stewart G. Trost

Keyword(s):

Machine Learning ◽

Free Play ◽

Living Conditions ◽

Accelerometer Data ◽

Classification Models ◽

Activity Classification ◽

Free Living ◽

Percentage Points ◽

Temporal Features ◽

Free Living Conditions

Machine learning (ML) activity classification models trained on laboratory-based activity trials exhibit low accuracy under free-living conditions. Training new models on free-living accelerometer data, reducing the number of prediction windows comprised of multiple activity types by using shorter windows, including temporal features such as standard deviation in lag and lead windows, and using multiple sensors may improve the classification accuracy under free-living conditions. The objective of this study was to evaluate the accuracy of Random Forest (RF) activity classification models for preschool-aged children trained on free-living accelerometer data. Thirty-one children (mean age = 4.0 ± 0.9 years) completed a 20 min free-play session while wearing an accelerometer on their right hip and non-dominant wrist. Video-based direct observation was used to categorize the children’s movement behaviors into five activity classes. The models were trained using prediction windows of 1, 5, 10, and 15 s, with and without temporal features. The models were evaluated using leave-one-subject-out-cross-validation. The F-scores improved as the window size increased from 1 to 15 s (62.6%–86.4%), with only minimal improvements beyond the 10 s windows. The inclusion of temporal features increased the accuracy, mainly for the wrist classification models, by an average of 6.2 percentage points. The hip and combined hip and wrist classification models provided comparable accuracy; however, both the models outperformed the models trained on wrist data by 7.9 to 8.2 percentage points. RF activity classification models trained with free-living accelerometer data provide accurate recognition of young children’s movement behaviors under real-world conditions.

Download Full-text

Reallocation of time between device-measured movement behaviours and risk of incident cardiovascular disease

British Journal of Sports Medicine ◽

10.1136/bjsports-2021-104050 ◽

2021 ◽

pp. bjsports-2021-104050

Author(s):

Rosemary Walmsley ◽

Shing Chan ◽

Karl Smith-Byrne ◽

Rema Ramakrishnan ◽

Mark Woodward ◽

...

Keyword(s):

Physical Activity ◽

Machine Learning ◽

Sedentary Behaviour ◽

Lower Risk ◽

Accelerometer Data ◽

Uk Biobank ◽

Free Living ◽

Machine Learning Methods ◽

Machine Learning Model ◽

Incident Cardiovascular Disease

ObjectiveTo improve classification of movement behaviours in free-living accelerometer data using machine-learning methods, and to investigate the association between machine-learned movement behaviours and risk of incident cardiovascular disease (CVD) in adults.MethodsUsing free-living data from 152 participants, we developed a machine-learning model to classify movement behaviours (moderate-to-vigorous physical activity behaviours (MVPA), light physical activity behaviours, sedentary behaviour, sleep) in wrist-worn accelerometer data. Participants in UK Biobank, a prospective cohort, were asked to wear an accelerometer for 7 days, and we applied our machine-learning model to classify their movement behaviours. Using compositional data analysis Cox regression, we investigated how reallocating time between movement behaviours was associated with CVD incidence.ResultsIn leave-one-participant-out analysis, our machine-learning method classified free-living movement behaviours with mean accuracy 88% (95% CI 87% to 89%) and Cohen’s kappa 0.80 (95% CI 0.79 to 0.82). Among 87 498 UK Biobank participants, there were 4105 incident CVD events. Reallocating time from any behaviour to MVPA, or reallocating time from sedentary behaviour to any behaviour, was associated with lower CVD risk. For an average individual, reallocating 20 min/day to MVPA from all other behaviours proportionally was associated with 9% (95% CI 7% to 10%) lower risk, while reallocating 1 hour/day to sedentary behaviour from all other behaviours proportionally was associated with 5% (95% CI 3% to 7%) higher risk.ConclusionMachine-learning methods classified movement behaviours accurately in free-living accelerometer data. Reallocating time from other behaviours to MVPA, and from sedentary behaviour to other behaviours, was associated with lower risk of incident CVD, and should be promoted by interventions and guidelines.

Download Full-text

Ability of RT3 Accelerometer Cut Points to Detect Physical Activity Intensity in Ambulatory Children With Cerebral Palsy

Adapted Physical Activity Quarterly ◽

10.1123/apaq.2013-0088 ◽

2014 ◽

Vol 31 (4) ◽

pp. 310-324 ◽

Cited By ~ 7

Author(s):

Jennifer Ryan ◽

Michael Walsh ◽

John Gormley

Keyword(s):

Physical Activity ◽

Cerebral Palsy ◽

Vigorous Physical Activity ◽

Accelerometer Data ◽

Physical Activity Intensity ◽

Cut Points ◽

Cut Point ◽

Activity Intensity ◽

Metabolic Equivalents ◽

Children With Cerebral Palsy

This study investigated the ability of published cut points for the RT3 accelerometer to differentiate between levels of physical activity intensity in children with cerebral palsy (CP). Oxygen consumption (metabolic equivalents; METs) and RT3 data (counts/min) were measured during rest and 5 walking trials. METs and corresponding counts/min were classified as sedentary, light physical activity (LPA), and moderate to vigorous physical activity (MVPA) according to MET thresholds. Counts were also classified according to published cut points. A published cut point exhibited an excellent ability to classify sedentary activity (sensitivity = 89.5%, specificity = 100.0%). Classification accuracy decreased when published cut points were used to classify LPA (sensitivity = 88.9%, specificity = 79.6%) and MVPA (sensitivity = 70%, specificity = 95–97%). Derivation of a new cut point improved classification of both LPA and MVPA. Applying published cut points to RT3 accelerometer data collected in children with CP may result in misclassification of LPA and MVPA.

Download Full-text