Standardized Methods for Evaluating Physical and Eating Behaviours: The Wearable Sensor Assessment of Physical and Eating Behaviours “WEALTH” Project. (Preprint)
Year: 2024
Type: preprint
Abstract: BACKGROUND The accurate measurement of physical and eating behaviours is critical for designing, monitoring, and implementing public health guidelines and intervention strategies. The objective of the Wearable Sensor Assessment of Physical and Eating Behaviours (WEALTH) project was to develop standardised methods to identify daily physical and eating behaviours from wearable research- and consumer-grade sensors and to evaluate the interaction and contexts of these behaviours. OBJECTIVE The aim of this paper is to describe the study design and methods, and report on the descriptive characteristics of the participants. METHODS Within the framework of the WEALTH project, a cross-sectional study (spring 2023 to spring 2024) was completed in five European research centres in the Czech Republic, France, Germany, and Ireland. In each centre, participants attended the research lab, completed an online questionnaire and provided measures of anthropometry and handgrip strength. The participants were then fitted with two research-grade (ActiGraph wGT3X-BT, activPAL 3 micro) and two consumer-grade (Fitbit® Charge 5, LifeQ® enabled smartwatch) devices and participated in a standardised semi-structured lab-based activity protocol. The latter was specifically designed to collect labelled data that simulated common physical behaviours (PB) and eating behaviours (EB) typical for a daily routine. Participants were then followed during a 9-day free-living data collection period which combined the assessment of PB and EB via wearable devices and time-based, event-based and self-initiated ecological momentary assessments (EMA). The EMA surveys were complemented by three 24-hour dietary recalls, using validated web-based programs. Upon completion of the survey protocol, participants completed a questionnaire that assessed the feasibility of the procedures. RESULTS The WEALTH study data will be used to develop machine learning (ML) models for classifying daily activities from wrist and hip worn accelerometer data, to evaluate EMA methods for studying interactions between PB and EB and to evaluate feasibility and compliance of the methods. Further analyses will provide insights in the association of classified PB and related EB examining behavioural patterns and health outcomes.The final sample was 627 participants, of which 44% were male. The mean age was 32.7 years (± 13.3), and the mean body mass index was 24.5 kg/m² (± 4.0). CONCLUSIONS The output of the WEALTH project will be provided via a repository and a comprised toolbox of publicly available labelled data, ML models for behaviour classification from accelerometer data and a methodology to simultaneously capture EB and PB, thereby producing an integrated data collection system to support future research.
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4405738298