Classification Accuracy of the Wrist-Worn Gravity Estimator of Normal Everyday Activity Accelerometer

Abstract

Purpose The purpose of this study was to determine whether the published left-wrist cut-points for the triaxial GENEA accelerometer, are accurate for predicting intensity categories during structured activity bouts. Methods A convenience sample of 130 adults wore a GENEA accelerometer on their left wrist while performing 14 different lifestyle activities. During each activity, oxygen consumption was continuously measured using the Oxycon mobile. Statistical analysis used Spearman's rank correlations to determine the relationship between measured and estimated intensity classifications. Cross tabulation tables were constructed to show under- or over-estimation of misclassified intensities. One-way chi-square tests were used to determine whether the intensity classification accuracy for each activity differed from 80%. Results For all activities the GENEA accelerometer-based physical activity monitor explained 41.1% of the variance in energy expenditure. The intensity classification accuracy was 69.8% for sedentary activities, 44.9% for light activities, 46.2% for moderate activities, and 77.7% for vigorous activities. The GENEA correctly classified intensity for 52.9% of observations when all activities were examined; this increased to 61.5% with stationary cycling removed. Conclusion A wrist-worn triaxial accelerometer has modest intensity classification accuracy across a broad range of activities, when using the cut-points of Esliger et al. Although the sensitivity and specificity are less than those reported by Esliger et al., they are generally in the same range as those reported for waist-worn, uniaxial accelerometer cut-points.

Performance of Activity Classification Algorithms in Free-Living Older Adults

“…Our algorithms presented overall activity recognition rates lower than 80%, which is the acceptable accuracy level suggested in previous studies (15, 17, 19). Thus, it is necessary to further improve the accuracy of the algorithms, which may be possible by implementing a modified direct observation system that allows for recoding of data.…”

“…Our results demonstrated that lab-based algorithms performed poorly in free-living conditions while algorithms developed with free-living accelerometer data improved activity type recognition rates. However, none of the algorithms achieved our preset acceptable accuracy level of 80%, which has been reported in previous studies that have developed activity classification algorithms from laboratory data (15, 17, 19). …”

“…locomotion), the equation was as follows: % correct for ‘locomotion’ = (minutes in locomotion that are correctly identified by the algorithm ÷ total minutes in locomotion) × 100. Similar to previous studies, 80% of correct classification rate was considered an acceptable accuracy level for our algorithms (15, 17, 19). In addition to percent correct classification, the Kappa Statistic was used to verify agreement between actual and predicted activity classification taking into account agreement that occurs by chance alone (16).…”

The potential benefits of Zumba Gold® in people with mild-to-moderate Parkinson’s: Feasibility and effects of dance styles and number of sessions

“…Despite the accelerometers being worn on the wrist in our study, it has been demonstrated that this method is valid to characterise activity levels during a variety of physical tasks involving both upper and lower limbs. 59 Our results showed a significantly lower HR mean in the backwards step salsa condition compared to side-step condition. It could be assumed that participants' lower HR was due to their lower capacity to perform the backwards steps at a high enough intensity due to their fear of falling.…”

Wearable motion sensors to continuously measure real-world physical activities

“…At best, a wrist-worn accelerometer may distinguish sedentary, household, walking and running as distinct activities and correctly classify intensity of activity 50% of the time. 9 In their present configuration, these are not suitable for research on patients with neurologic impairments.…”