Physical activity is associated with a broad range of health indicators and is probably already of importance during the preschool years [1]. An accurate method to measure physical activity and sedentary time is essential to study correlates of these behaviors and to evaluate interventions, both in research and in clinical settings. Accelerometers have revolutionized the research field by enabling objective measures of physical activity intensity, frequency and duration, which are possible to use in large cohorts [2]. Objective methods are of particular importance for preschool children who can neither recall nor estimate past physical activities, and whose intermittent activity patterns make proxy reports very difficult [3]. Accelerometers have been proven feasible, reliable and valid for assessing physical activity in children [4, 5]. Accelerometers can be worn on different body sites. The hip has been the traditional location, but during recent years the wrist has been increasingly used as it has been shown to yield superior compliance in children, compared with hip placement [6]. Accelerometer output, expressed as counts, is affected by the body part it is attached to. As an example, an accelerometer placed on the hip does not capture arm movements. However, the estimated time in different intensities is similar when site-specific cut-points are applied [7]. To determine the time spent at different intensity levels, accelerometer counts need to be calibrated against a reference method. In children, observational methods such as The Children’s Activity Rating Scale (CARS) [8] have been suggested as the best reference method and CARS has been used in many previous calibration studies [5, 9, 10]. Taken the large difference in children’s motor skills between the age of one and six year there is a need for age-specific cut-points. Calibration studies for wrist-placement have been performed in two-year-olds [5] and in 8–12 year olds [11] but cut-points for children aged 3–5 are lacking.

The aim was to calibrate the accelerometer Actigraph GT3X+ for non-dominant wrist and hip placement in four-year-old children by developing upper vertical axis (VA), and vector magnitude (VM), intensity thresholds for sedentary behavior and lower VA and VM intensity thresholds for moderate-to-vigorous intensity physical activity (MVPA). Further aims were to cross-validate the developed intensity thresholds and to test the sensitivity and specificity of two existing cut points for hip-worn accelerometers.

Table 1 shows descriptive characteristics of the included children. Of the 30 children, 14 were boys. One fifth was considered overweight, but no child was obese.

Average observed time was 29 (SD 6) minutes per child. Mean accelerometer counts were lowest when children were watching a cartoon and highest when dancing to music (Table 2).

Pursuant to the protocol, mean accelerometer counts increased by CARS score (Table 3).

Table 4 shows the developed intensity thresholds together with sensitivity, specificity and AUC.

Sensitivity was 100% and 70%, and specificity was 60% and 93–100% for the sedentary and MVPA intensity thresholds, respectively. AUC ranged from 0.91–0.99.

The absolute agreement was 82% (VA and VM) for the wrist-worn accelerometer and 68% (VA) and 75% (VM) for the accelerometer worn on the hip. For the wrist-worn accelerometer, the quadratic weighted Kappa was almost perfect; 0.92 (95% CI 0.91–0.93) and 0.95 (95% CI 0.94–0.96) for the VA and the VM, respectively. The Kappa values for the hip-worn accelerometer were lower compared to the wrist-worn device; 0.76 (98% CI 0.74–0.77) and 0.86 (95% CI 0.85–0.87) for the VA and VM, respectively.

When applying the Pate et al. intensity thresholds to our VA ROC curve for the hip, sensitivity and specificity for the MVPA intensity threshold were 97% and 67%, respectively. For the Sirard et al. threshold, sensitivity and specificity were 73% and 97%.

This is the first study to develop intensity thresholds for both the VA and the VM for a wrist-worn Actigraph accelerometer in preschool children. A previous study has been performed in two-year-olds, using an almost identical protocol as in this study [20], as well as in 8–12 years olds [11]. Compared to those, the intensity thresholds developed in this study were higher. This indicates that age-specific thresholds are needed. During the infant, toddler and preschool years, motor skills are developing rapidly. The gait becomes increasingly stable which enables the child to move around more effectively than at earlier ages. Arm movements decrease gradually as the child ages, explaining the higher count thresholds in comparison with the study on 8–12 year olds [11]. In comparison with these studies, we found higher measures of AUC, sensitivity and specificity for the developed intensity thresholds.

Two previous studies have developed intensity thresholds for the hip-worn uniaxial Actigraph accelerometer for four-year-old children [10, 19]. In the study by Pate et al. oxygen consumption was used as the criterion measure and children performed structured activities during the calibration session [19]. In the study by Sirard et al. CARS was used as the reference method, as in the present study. Using the same definition of MVPA (CARS score of at least 4), the developed count thresholds were similar to those derived in this study [10], confirming the validity of our hip MVPA intensity threshold. When applying the intensity thresholds by Pate et al. and Sirard et al. to the output from the ROC curves from this study, the sensitivity and specificity were almost the same in our study as for the MVPA threshold developed by Sirard et al. In order to avoid overestimation of the time spent in MVPA, we chose an intensity threshold with high specificity, at the expense of a lower sensitivity for that threshold. For the threshold developed by Pate et al., however, the sensitivity was high but the specificity relatively low, which will lead to an overestimation of time spent in MVPA. This indicates that the choice of criterion measure and definition of moderate intensity have great impact on the intensity thresholds derived.

The definition of moderate intensity is under debate and has been defined differently across studies [11, 21]. Like in previous studies [9, 10, 14] CARS scores 4 and 5 were categorized as a proxy for MVPA. This is based on a validation study, in which CARS was validated against oxygen consumption in 5-6-year-olds. In that study, CARS score 3 and 4 was found to correspond to 2.69 and 3.45 metabolic equivalents, respectively [8]. CARS has also been found to accurately classify the level of energy expenditure and to correlate with Caltrac motion sensors in children aged 2–6 [15]. Nevertheless, estimating what represents moderate intensity in preschoolers is problematic. It is known that the energy cost for physical activity per kilo body weight tends to decrease with advancing age [22]. Since the ability to absorb oxygen, muscle strength and motor skills develop as the child mature, it is likely that the metabolic equivalent for a certain activity differs between a four- and a six-year-old. This area of research needs further exploration.

Since a three axial accelerometer was used in the present study, intensity thresholds for the VM were also developed. These were found to have higher validity than those for the VA (Kappa value of 0.95 vs 0.92 for the wrist and 0.86 vs 0.76 for the hip). This is in accordance with a previous study, which found that activity counts derived from the VM yielded a more accurate estimation of energy expenditure than those derived from the VA, in youths, adults and older adults [23]. In the present study, the VM also had higher validity for the wrist intensity thresholds, as was found in a previous study on two-year-olds [5]. Thus, placing the Actigraph on the wrist and using the VM may be recommended for assessing time in different physical activity intensities in this population.

The accelerometer output differs according to the body site to which it is attached. A wrist-worn accelerometer captures movements performed by the arms, unlike a hip-mounted monitor. In accordance with results from previous studies, we found that accelerometer data collected from the wrist yielded higher accelerometer output compared with the hip-worn monitor, while measuring the same individual concurrently [6, 7]. Previous studies on adults have demonstrated that hip-mounted monitors have better accuracy in predicting physical activity energy expenditure than wrist-mounted monitors [24–26]. Wearing the accelerometer on the wrist can be problematic if the subject is walking with the hands constrained, for example when carrying a load. The accelerometer output will probably then be much different from walking with the hands swinging freely. However, when observing children during free play children tend to engage in activities like carrying heavy objects infrequently, making this likely to represent a minor problem among the preschool population. A wrist placement has been shown to accurately estimate energy expenditure [27] and, as in the present study, to estimate time spent in different intensities [5, 11] in children. Since a wrist placement can increase compliance [6], these results are promising.

The derived thresholds were found to be valid for categorizing physical activity intensity in four-year-old children. For both wrist and hip placement the VM had higher validity than the VA. In comparison with placing the accelerometer on the hip, the wrist-mounted monitor performed better in accurately assessing time spent being sedentary, in light activity and in MVPA. Based on the findings of this study, the VM based on wrist-worn accelerometers for measuring physical activity in 4-year-old children is recommended to use.