MétaCan
Menu
Back to cohort
Record W7116955966 · doi:10.1002/alz70863_110570

From sensors to solutions: Integrating wearable sensor data into health research

2025· article· en· W7116955966 on OpenAlexaff
Kit B. Beyer, William E. McIlroy

Bibliographic record

VenueAlzheimer s & Dementia · 2025
Typearticle
Languageen
FieldComputer Science
TopicContext-Aware Activity Recognition Systems
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsWearable computerWearable technologyData qualityData collectionActivity recognitionExternal Data RepresentationQuality (philosophy)Activity tracker

Abstract

fetched live from OpenAlex

Integrating wearable sensor technology into research and clinical applications affords the opportunity to support aging individuals, including those living with Alzheimer's disease-related dementias (ADRD), by advancing our understanding of disease onset and progression and enhancing personalized healthcare. Wearable sensors enable continuous remote capture of behaviour and physiology for prolonged durations as individuals participate in their daily lives. Objective, quantitative analysis of these real-world data can yield important health-related outcomes across multiple domains, including mobility, cognition, cardiovascular function, sleep, and physical activity. These outcomes can reduce reliance on subjective self-reporting, improve the possibility of capturing infrequent events, detect subtle change over time, and provide a more comprehensive representation of an individual's health status. However, the volume and complexity of wearable data also present several challenges and considerations that must be addressed to fully realize this opportunity. Data quality is critical to the validity and utility of wearable-derived outcomes but is susceptible to many factors, including sensor calibration, device performance, participant adherence to wear protocols, and signal quality issues related to sensor malfunction, artifact, or noise. Complex, multi-domain analysis that requires integrating data from multiple sensor types across different wearable devices is complicated by the many different data types and formats (e.g., standard vs. proprietary) used by various device manufacturers and the lack of built-in capabilities to synchronize data across devices. Finally, advanced analytic techniques are often required to extract relevant features or events from large, complex wearable datasets. This presentation will describe various approaches to address these challenges in processing and analyzing wearable data and demonstrate the opportunities that arise. Specific emphasis will be placed on 1) study design and implementation considerations that can mitigate challenges, 2) preprocessing, signal processing, and data analytics techniques that directly address these challenges, and 3) examples of the types of outcomes that can be derived from wearable data when these challenges are adequately addressed.

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 imitation

Not 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.

metaresearch head score (Codex)0.030
metaresearch head score (Gemma)0.062
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.030
Threshold uncertainty score0.158

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0300.062
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0080.008
Science and technology studies0.0020.006
Scholarly communication0.0170.030
Open science0.0050.015
Research integrity0.0080.011
Insufficient payload (model declined to judge)0.0090.007

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.

Opus teacher head0.227
GPT teacher head0.410
Teacher spread0.183 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueAlzheimer s & DementiaSame topicContext-Aware Activity Recognition SystemsFrench-language works237,207