Standardized Methods for Evaluating Physical and Eating Behaviors: The WEALTH Cross-Sectional Study Protocol
Bibliographic record
Abstract
Background: The accurate measurement of physical behaviors (PBs) and eating behaviors (EBs) 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 standardized methods to identify daily PBs and EBs from wearable research- and consumer-grade sensors and evaluate the interaction and contexts of these behaviors. 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 5 European research centers in the Czech Republic, France, Germany, and Ireland. In each center, participants attended a research lab, completed an online questionnaire, and provided measures of anthropometry and handgrip strength. The participants were then fitted with 2 research-grade and 2 consumer-grade devices and participated in a standardized semistructured lab-based activity protocol. The latter was specifically designed to collect labeled data that simulated common PBs and EBs 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 (EMAs). The EMA surveys were complemented by three 24-hour dietary recalls, using validated web-based programs. Upon the completion of the survey protocol, participants completed a questionnaire that assessed the feasibility of the procedures. Results: The final sample includes 627 participants, of whom 44% (n=275) were male. The mean age was 32.7 (SD 13.3) years, and the mean body mass index was 24.5 (SD 4.0) kg/m². The WEALTH study data will be used to develop machine learning (ML) models for classifying daily activities from wrist and hip-worn accelerometer data, evaluate EMA methods for studying interactions between PB and EB, and evaluate the feasibility and compliance of the methods. Data processing and ML model development are currently underway, with primary results expected to be published in 2026. Conclusions: The output of the WEALTH project will be provided via a repository and a comprised toolbox of publicly available labeled data, ML models for behavior classification from accelerometer data, and a methodology to simultaneously capture EB and PB, thereby producing an integrated data collection system to support future research.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.027 | 0.017 |
| Meta-epidemiology (narrow) | 0.003 | 0.003 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.027 | 0.011 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".