Calibration of hip accelerometers for measuring physical activity and sedentary behaviours in adults with Down syndrome

BackgroundThe knowledge base on physical activity and sedentary behaviour in adults with Down syndrome (DS) may advance by accelerometer calibration studies. This study aimed to develop cut-points for sedentary behaviour and moderate-to-vigorous physical activity (MVPA) for adults with DS based on output from accelerometers worn on the dominant and non-dominant hips. MethodsSixteen adults with DS (10 men; age 31 +/- 15 years) performed 12 tasks including sedentary behaviours and physical activities. We obtained metabolic equivalents (METs) with indirect calorimetry and vector magnitude (VM) output from triaxial accelerometers (wGT3X-BT, ActiGraph) worn on the dominant and non-dominant hips. Receiver operating characteristic curves were used to identify optimal VM cut-points that maximised sensitivity and specificity. ResultsOverall classification accuracy was very high (area under the ROC curve: 0.95 and 0.92 for sedentary and MVPA models, respectively). For the non-dominant hip, the optimal VM cut-points were (1) sedentary behaviour <= 236 counts center dot min(-1) and (2) MVPA >= 2167 counts center dot min(-1). For the dominant hip, optimal cut-points were (1) sedentary behaviour <= 243 counts center dot min(-1) and (2) MVPA >= 2092 counts center dot min(-1). ConclusionsThe presented VM cut-points for sedentary behaviour and MVPA for adults with DS had high classification accuracy. There were small differences in accelerometer cut-points between the dominant and non-dominant hip.