The Physical Activity Assessment using Wearable Sensors (PAAWS) Study
The PAAWS Study (Physical Activity Assessment using Wearable Sensors) Study is an NIH-funded effort being conducted by the mHealth Research Group at Northeastern University in Boston, MA, in collaboration with researchers at Brigham and Women's Hospital.
Goals
Accurate measurement of human behavior using devices could significantly advance current knowledge on the dose-response relationships between chronic diseases and behaviors such as physical activity, sedentary behavior, and sleep. The primary objective of this project is to develop valid approaches to measure 24-hour physical behavior, as well as to demonstrate a procedure via which those approaches can be compared to others. We aim to help the research community to converge on methods that use devices to accurately measure physical activity type and intensity, sedentary behavior and posture, and sleep in adults. Many promising methods have been proposed to measure behavior from activity monitors. Unfortunately, these methods are typically validated on small amounts of data. Thus, they may perform well on a subset of the same data, but fail when deployed in the real world. Moreover, the performance of different methods is rarely compared head-to-head, creating uncertainty for public health researchers about which are the best to use. Quantifying the relative performance of methods that produce similar outcome measures but use different devices or on-body device locations is even more unusual.
We are trying to make it easy for researchers interested in physical activity measurement to meaningfully compare performance between new methods and confidently apply those methods to both large-scale surveillance studies and longitudinal interventions. The project has three specific aims:
The overall goal is to enable human activity recognition scientists to conduct a rigorous comparison of performance among existing approaches, enable the development of updated methods, and increase the possibility of applying these methods to both large-scale surveillance studies and longitudinal interventions.
The open-source dataset generated through this effort will provide a foundation for establishing gold-standard methods to measure PA across diverse and emerging device configurations.
- Collect well-annotated 24-hour data of physical activity, sedentary behavior, and sleep,
- Use the data from Aim 1 to develop and validate approaches that yield 24-hour estimates of free-living physical activity (type, intensity), sedentary behavior (type, posture), and sleep (wake/sleep, stages),
- Develop and incrementally refine a suite of tools that researchers can use to easily deploy advanced approaches to measure physical activity, sedentary behavior, and sleep, even for large data.
The overall goal is to enable human activity recognition scientists to conduct a rigorous comparison of performance among existing approaches, enable the development of updated methods, and increase the possibility of applying these methods to both large-scale surveillance studies and longitudinal interventions.
The open-source dataset generated through this effort will provide a foundation for establishing gold-standard methods to measure PA across diverse and emerging device configurations.
