Detecting accelerometer non-wear periods using change in acceleration combined with rate-of-change in temperature

Abstract

Background Accelerometery is commonly used to estimate physical activity, sleep, and sedentary behavior. In free-living conditions, periods of device removal (non-wear) can lead to misclassification of behavior with consequences for research outcomes and clinical decision making. Common methods for non-wear detection are limited by data transformations (e.g., activity counts) or algorithm parameters such as minimum durations or absolute temperature thresholds that risk over- or under-estimating non-wear time. This study aimed to advance non-wear detection methods by integrating a ‘rate-of-change’ criterion for temperature into a combined temperature-acceleration algorithm. Methods Data were from 39 participants with neurodegenerative disease (36% female; age: 45–83 years) who wore a tri-axial accelerometer (GENEActiv) on their wrist 24-h per day for 7-days as part of a multi-sensor protocol. The reference dataset was derived from visual inspection conducted by two expert analysts. Linear regression was used to establish temperature rate-of-change as a criterion for non-wear detection. A classification and regression tree (CART) decision tree classifier determined optimal parameters separately for non-wear start and end detection. Classifiers were trained using data from 15 participants (38.5%). Outputs from the CART analysis were supplemented based on edge cases and published parameters. Results The dataset included 186 non-wear periods (85.5% < 60 min). Temperature rate-of-change over the first five minutes of non-wear was − 0.40 ± 0.17 °C/minute and 0.36 ± 0.21 °C/minute for the first five minutes following device donning. Performance of the DETACH (DEvice Temperature and Accelerometer CHange) algorithm was improved compared to existing algorithms with recall of 0.942 (95% CI 0.883 to 1.0), precision of 0.942 (95% CI 0.844 to 1.0), F1-Score of 0.942 (95% CI 0.880 to 1.0) and accuracy of 0.996 (0.994–1.000). Conclusion The DETACH algorithm accurately detected non-wear intervals as short as five minutes; improving non-wear classification relative to current interval-based methods. Using temperature rate-of-change combined with acceleration results in a robust algorithm appropriate for use across different temperature ranges and settings. The ability to detect short non-wear periods is particularly relevant to free-living scenarios where brief but frequent removals occur, and for clinical application where misclassification of behavior may have important implications for healthcare decision-making.

Does Wrist-Worn Accelerometer Wear Compliance Wane over a Free-Living Assessment Period? An NHANES Analysis

“…Some improvement has been made to these count-based, single behavior methods by using raw acceleration data in shorter windows and in two stages to account for more than one behavior (49)(50)(51). Nevertheless, the misidentification of sleep or sedentary time as nonwear and contrariwise remains a noted issue, particularly if the only information available for classification is movement data from a single attachment site (24,(51)(52)(53). ISM is believed to engage more frequently and for longer periods during low-movement periods, including overnight during plausible sleep, which may increase the likelihood of misclassifying wear time during sleep as nonwear (24).…”

“…Alternatively, the degree to which electronic reminders and newer cloud-based systems with near real-time monitoring can improve compliance and mitigate wear fatigue should be evaluated. Advances in sensor technology and incorporation of sensors with modalities other than movement, including heart rate (57,58) and/or skin temperature (52,59), may improve differentiation of nonwear, sleep, and SB, allowing a more complete characterization of wear behavior in the future.…”

SciKit digital health package for accelerometry-measured physical activity: comparisons to existing solutions and investigations of age effects in healthy adults

“…The next pre-processing step for the activity metric pipeline was to compute wear time. Using a previously published algorithm ( 23 ) called DETACH, acceleration, temperature, and rate of change in temperature were used to determine if a device was being worn. The DETACH algorithm computes wear status with resolutions down to single-digit seconds.…”

“…The following parameters were used: acceleration standard deviation of 0.008 g, low-temperature threshold of 26.0°C, high-temperature threshold of 30.0°C, temperature rate of decrease threshold of −0.2°C/min, and temperature rate of increase threshold of 0.1°C/min. A window size of s was used, based on the previous work ( 23 ). For use cases lacking temperature data, SKDH provides alternative methods of calculating wear time using only the accelerometer data ( 24 – 28 ).…”