Defining accelerometer thresholds for physical activity in girls using ROC analysis

Calibrating Wrist-Worn Accelerometers for Physical Activity Assessment in Preschoolers: Machine Learning Approaches

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.

Sleep duration, timing, variability and measures of adiposity among 8- to 12-year-old children with obesity

OBJECTIVES

Sleep disruption in laboratory studies increases adiposity and decreases glucose tolerance. However, few epidemiological studies have used objective measures of sleep. This study aims to assess associations between sleep duration, timing and regularity with measures of adiposity.

METHODS

This is a cross-sectional study of 188 children with obesity (age: 10.50 ± 1.39 years; body mass index: 29.24 ± 5.04 kg m-2). Nightly sleep duration, bedtime and wake time were measured by multiple-day actigraphy and parent reports. Per cent overweight (per cent over median body mass index for age and sex) was chosen as the primary measure of obesity status. Objective measures of height, weight, waist circumference, blood pressure, fasting blood lipids, glucose, insulin, glycated haemoglobin and C-reactive protein were obtained. Television screen time and total caloric intake were assessed via parent questionnaire.

RESULTS

Each hour later in weekday bedtime was associated with an additional 6.17 per cent overweight (95% confidence interval [CI]: 1.42-10.92). Each hour greater in day-to-day variability in weekday bedtime and weekday wake time was associated with an additional 10.20 (95% CI: 0.50-19.91) and 10.02 (95% CI: 1.55-18.50) per cent overweight, respectively. Associations were similar after controlling for other obesity-related behaviours (television screen time, total caloric intake and physical activity.).

CONCLUSIONS

Among children with obesity, later bedtime and greater variability in bedtime and wake time are associated with greater adiposity, independent of other obesity-related behaviours. Early bedtime and wake time and consistent day-to-day sleep timing may be strategies to reduce adiposity in high-risk children.

Do moderate- to vigorous-intensity accelerometer count thresholds correspond to relative moderate- to vigorous-intensity physical activity?

We aimed to predict % maximal oxygen consumption at absolute accelerometer thresholds and to estimate and compare durations of objective physical activity (PA) among body mass index (BMI) categories using thresholds that account for cardiorespiratory fitness. Eight hundred twenty-eight adults (53.5% male; age, 33.9 ± 0.3 years) from the National Health and Nutrition Examination Survey 2003-2004 were analyzed. Metabolic equivalent values at absolute thresholds were converted to percentage of maximal oxygen consumption, and accelerometer counts corresponding to 40% or 60% maximal oxygen consumption were determined using 4 energy expenditure prediction equations. Absolute thresholds underestimated PA intensity for all adults; however, because of lower fitness, individuals with overweight and obesity work at significantly higher percentage of maximal oxygen consumption at the absolute thresholds and require significantly lower accelerometer counts to reach relative moderate and vigorous PA intensities compared with those with normal weight (P < 0.05). However, moderate-to-vigorous physical activity (MVPA) durations were shorter when using relative thresholds compared with absolute thresholds (in all BMI groups, P < 0.05), and they were shorter among individuals with obesity compared with those with normal weight when using relative thresholds (P < 0.05). Regardless of the thresholds used, a greater proportion of individuals with normal weight met the PA guideline of 150 min·week^-1 of MVPA compared with individuals with obesity (absolute: 21.3% vs 6.7%; Yngve: 4.0% vs 0.2%; Swartz: 10.7% vs 3.9%; Hendelman: 4.7% vs 0.2%; Freedson: 6.4% vs 0.5%; P < 0.05). Current absolute thresholds of accelerometry-derived PA may overestimate MVPA for all BMI categories when compared with relative thresholds that account for cardiorespiratory fitness. Given the large variability in our results, more work is needed to better understand how to use accelerometers for evaluating PA at the population level.

Accelerometer thresholds: Accounting for body mass reduces discrepancies between measures of physical activity for individuals with overweight and obesity

The objective of this study was to explore whether accelerometer thresholds that are adjusted to account for differences in body mass influence discrepancies between self-report and accelerometer-measured physical activity (PA) volume for individuals with overweight and obesity. We analyzed 6164 adults from the National Health and Nutrition Examination Survey between 2003-2006. Established accelerometer thresholds were adjusted to account for differences in body mass to produce a similar energy expenditure (EE) rate as individuals with normal weight. Moderate-, vigorous-, and moderate- to vigorous-intensity PA (MVPA) durations were measured using established and adjusted accelerometer thresholds and compared with self-report. Durations of self-report were longer than accelerometer-measured MVPA using established thresholds (normal weight: 57.8 ± 2.4 vs 9.0 ± 0.5 min/day, overweight: 56.1 ± 2.7 vs 7.4 ± 0.5 min/day, and obesity: 46.5 ± 2.2 vs 3.7 ± 0.3 min/day). Durations of subjective and objective PA were negatively associated with body mass index (BMI) (P < 0.05). Using adjusted thresholds increased MVPA durations, and reduced discrepancies between accelerometer and self-report measures for overweight and obese groups by 6.0 ± 0.3 min/day and 17.7 ± 0.8 min/day, respectively (P < 0.05). Using accelerometer thresholds that represent equal EE rates across BMI categories reduced the discrepancies between durations of subjective and objective PA for overweight and obese groups. However, accelerometer-measured PA generally remained shorter than durations of self-report within all BMI categories. Further research may be necessary to improve analytical approaches when using objective measures of PA for individuals with overweight or obesity.

Physical activity practice among children and adolescents with visual impairment--influence of parental support and perceived barriers

PURPOSE

To analyze the practice of physical activity among children and adolescents with visual impairments (VI), regarding the possible influence of parental support and perceived barriers.

METHODS

Twenty-two young people with VIs (10 + 2.74 years old) and one of each of their parents were evaluated. They responded to the Physical Activity Questionnaire for Older Children (PAQ-C), Baecke Questionnaire, the Parental Support Scale and a questionnaire about perceived barriers to physical activity. The independent samples t-test, pearson correlation test and chi-square test were performed.

RESULTS

Blind young people showed lower physical activity levels. There were significant correlations both between parents' physical activity and the support offered to children and between the PAQ-C results and the importance given by young people to physical activity, but only for those aged between 8 and 10 years old. The main perceived barriers were lack of security, motivation, professional training and information about available physical activity programs.

CONCLUSION

The influence of parental support seems to be an important factor in the adoption of a physically active lifestyle for young people with VI. Parents and children should have more information about the benefits and opportunities of physical activity. Implications for Rehabilitation Young people with visual impairment should be encouraged by parents to practice physical activity. More information should be provided on the benefits of physical activity to both parents and children. Professional training should be available to help support this group become more active.

Physical activity practice, body image and visual impairment: a comparison between Brazilian and Italian children and adolescents

The aim of this study was to analyze the physical activity and body image of children and adolescents with visual impairment (VI) in Brazil and Italy. For this, 41 children and adolescents with VI (19 Brazilian and 22 Italian) aged 10.22 ± 2.19 years old (18 girls and 23 boys) answered the Physical Activity Questionnaire for Children (PAQ-C), the Offer Self-Image Questionnaire (OSIQ), and an instrument with information about the disability, body weight and height. We analyzed the relationship between data from PAQ-C and OSIQ, as well as the gender, level of disability (blindness or low vision) and country using independent Mann-Whitney test. Body mass index (BMI) values were higher for Brazilian youths, with more than half of them classified as overweight and obese. Italian youths exhibited values of body image that were more positive and only 27% presented overweight or obesity. Blind children and adolescents were less active than those with low vision, but no differences were found between countries or genders. In Brazil, we detected significant correlations (p>0.05) between physical activity, body image and BMI, which more active youths presenting lower values of BMI and a better perception of body image. Physical activity seems to have a positive influence on body image and BMI for children and adolescents with VI, thus it should be encouraged especially for those with higher disability degrees.

A calibration protocol for population-specific accelerometer cut-points in children

PURPOSE

To test a field-based protocol using intermittent activities representative of children's physical activity behaviours, to generate behaviourally valid, population-specific accelerometer cut-points for sedentary behaviour, moderate, and vigorous physical activity.

METHODS

Twenty-eight children (46% boys) aged 10-11 years wore a hip-mounted uniaxial GT1M ActiGraph and engaged in 6 activities representative of children's play. A validated direct observation protocol was used as the criterion measure of physical activity. Receiver Operating Characteristics (ROC) curve analyses were conducted with four semi-structured activities to determine the accelerometer cut-points. To examine classification differences, cut-points were cross-validated with free-play and DVD viewing activities.

RESULTS

Cut-points of ≤ 372, >2160 and >4806 counts • min(-1) representing sedentary, moderate and vigorous intensity thresholds, respectively, provided the optimal balance between the related needs for sensitivity (accurately detecting activity) and specificity (limiting misclassification of the activity). Cross-validation data demonstrated that these values yielded the best overall kappa scores (0.97; 0.71; 0.62), and a high classification agreement (98.6%; 89.0%; 87.2%), respectively. Specificity values of 96-97% showed that the developed cut-points accurately detected physical activity, and sensitivity values (89-99%) indicated that minutes of activity were seldom incorrectly classified as inactivity.

CONCLUSION

The development of an inexpensive and replicable field-based protocol to generate behaviourally valid and population-specific accelerometer cut-points may improve the classification of physical activity levels in children, which could enhance subsequent intervention and observational studies.