Assessment of laboratory and daily energy expenditure estimates from consumer multi-sensor physical activity monitors-dataset

Wearable physical activity monitors are growing in popularity and provide the opportunity for large numbers of the public to self-monitor physical activity behaviours. The latest generation of these devices feature multiple sensors, ostensibly similar or even superior to advanced research instruments. However, little is known about the accuracy of their energy expenditure estimates. Here, we assessed their performance against criterion measurements in both controlled laboratory conditions (simulated activities of daily living and structured exercise) and over a 24 hour period in free-living conditions. Thirty men (n=15) and women (n=15) wore three multi-sensor consumer monitors (Microsoft Band, Apple Watch and Fitbit Charge HR), an accelerometry-only device as a comparison (Jawbone UP24) and validated research-grade multi-sensor devices (BodyMedia Core and individually calibrated Actiheart™). During discrete laboratory activities when compared against indirect calorimetry, the Apple Watch performed similarly to criterion measures. The Fitbit Charge HR was less consistent at measurement of discrete activities, but produced similar free-living estimates to the Apple Watch. Both these devices underestimated free-living energy expenditure (-394 kcal/d and -405 kcal/d, respectively; P<0.01). The multi-sensor Microsoft Band and accelerometry-only Jawbone UP24 devices underestimated most laboratory activities and substantially underestimated free-living expenditure (-1128 kcal/d and -998 kcal/d, respectively; P<0.01). None of the consumer devices were deemed equivalent to the reference method for daily energy expenditure. For all devices, there was a tendency for negative bias with greater daily energy expenditure. No consumer monitors performed as well as the research-grade devices although in some (but not all) cases, estimates were close to criterion measurements. Thus, whilst industry-led innovation has improved the accuracy of consumer monitors, these devices are not yet equivalent to the best research-grade devices or indeed equivalent to each other. We propose independent quality standards and/or accuracy ratings for consumer devices are required.

可穿戴式身体活动监测器正日益受到欢迎，并为大量公众自我监控身体活动行为提供了机会。这些设备的最新一代配备多个传感器，其性能在实质上与高级研究仪器相似甚至更优。然而，关于其能量消耗估计的准确性知之甚少。在本研究中，我们评估了这些设备在受控实验室条件（模拟日常生活活动和有组织的运动）以及24小时自由生活条件下的表现，与标准测量结果进行了比较。三十名男性（n=15）和女性（n=15）分别佩戴了三种多传感器消费级监测器（Microsoft Band、Apple Watch 和 Fitbit Charge HR），一种仅配备加速度计的设备作为对比（Jawbone UP24）以及经过验证的研究级多传感器设备（BodyMedia Core 和单独校准的Actiheart™）。在实验室特定活动中，与间接代谢率相比，Apple Watch 的表现与标准测量结果相似。Fitbit Charge HR 在测量特定活动时的一致性较低，但其自由生活估计结果与Apple Watch相似。这两种设备均低估了自由生活的能量消耗（分别为-394 kcal/d 和 -405 kcal/d；P<0.01）。多传感器Microsoft Band和仅配备加速度计的Jawbone UP24设备低估了大多数实验室活动，并且对自由生活的消耗估计大幅度低估（分别为-1128 kcal/d 和 -998 kcal/d；P<0.01）。没有任何消费级设备被认为与日常能量消耗的参考方法相当。对于所有设备，存在随着每日能量消耗增加而产生负偏差的趋势。尽管在某些情况下（但不完全如此）估计值接近标准测量结果，但没有任何消费级监测器的性能能够与研究级设备相媲美。因此，尽管以行业为主导的创新提升了消费级监测器的准确性，但这些设备尚未达到最佳研究级设备的水平，更不用说相互之间相当。我们建议为消费级设备设立独立的质量标准或准确性评级。