Generalizability and performance of methods to detect non-wear with free-living accelerometer recordings.

Wearable physical activity sensors are widely used in research and practice as they provide objective measures of human behavior at a low cost. An important challenge for accurate assessment of physical activity behavior in free-living is the detection non-wear. Traditionally, heuristic algorithms that rely on specific interval lengths have been employed to detect non-wear time; however, machine learned models are emerging. We explore the potential of detecting non-wear using decision trees that combine raw acceleration and skin temperature, and we investigate the generalizability of our models, traditional heuristic algorithms, and recently developed machine learned models by external validation. The Decision tree models were trained using one week of data from thigh- and hip-worn accelerometers from 64 children. External validation was performed using data from wrist-worn accelerometers of 42 adolescents. For non-wear episodes longer than 60 min, the heuristic algorithms performed the best with F1-scores above 0.96. However, regarding episodes shorter than 60 min, the best performing method was the decision tree model including the six most important predictors with F1 scores above 0.74 for all sensor locations. We conclude that for classifying non-wear time, researchers should carefully select an appropriate method and we encourage the use of external validation when reporting on machine learned non-wear models.

Manual Annotation of Time in Bed Using Free-Living Recordings of Accelerometry Data.

With the emergence of machine learning for the classification of sleep and other human behaviors from accelerometer data, the need for correctly annotated data is higher than ever. We present and evaluate a novel method for the manual annotation of in-bed periods in accelerometer data using the open-source software Audacity®, and we compare the method to the EEG-based sleep monitoring device Zmachine® Insight+ and self-reported sleep diaries. For evaluating the manual annotation method, we calculated the inter- and intra-rater agreement and agreement with Zmachine and sleep diaries using interclass correlation coefficients and Bland-Altman analysis. Our results showed excellent inter- and intra-rater agreement and excellent agreement with Zmachine and sleep diaries. The Bland-Altman limits of agreement were generally around ±30 min for the comparison between the manual annotation and the Zmachine timestamps for the in-bed period. Moreover, the mean bias was minuscule. We conclude that the manual annotation method presented is a viable option for annotating in-bed periods in accelerometer data, which will further qualify datasets without labeling or sleep records.

Unprompted vigorous physical activity is associated with higher levels of subsequent sedentary behaviour in participants with low cardiorespiratory fitness: a cross-sectional study.

Performing physical activity is considered health promoting but may induce a need for subsequent rest periods. This study aimed to determine the within-day interactions between vigorous physical activity (VPA) and sedentary behaviour (SB) in participants with low cardiorespiratory fitness. We tested the hypothesis that VPA is associated with a temporary subsequent increase in SB. One week of accelerometer data containing a minimum of one 10-min bout of VPA from 62 participants with low cardiorespiratory fitness (31-50 years old) were obtained from the MILE study. A comparison of SB was made between days with a bout of VPA and days without (control). Due to a positive association between VPA and number and duration of sedentary bouts, the time accumulated in both uninterrupted and total sedentary bouts were 27 (95% CI, 10-45) min and 29 (95% CI, 9-50) min higher on VPA days compared to control days (P < 0.05). Our results indicate that in participants with low cardiovascular fitness, unprompted VPA is positively associated with an increase in subsequent sedentary time. We propose that such VPA-associated sedentary time may be viewed as part of a healthy activity pattern.