Proposed PEPHA framework links wearable movement data to cognition and mood in older adults
The proposed PEPHA framework uses wearable and assessment data from 67 older adults to find individual time windows where movement and sedentary patterns are associated with processing speed and depressive symptoms. It is exploratory, not a validated tool. [1]
Automatic summary · not editorially reviewed
The key findings
PEPHA is proposed as an interpretable AI framework to identify which 24-hour movement behavior dimensions and when they are associated with cognitive functioning and depressive symptoms in older adults. [1]
The longitudinal Providemus alz cohort included 67 people with up to 6 waves and 528 days of wearable data per person. [1]
About 40% of individuals showed moderate or large temporal order effects, and for one exemplar participant two potential windows were localized about 60 and 30 days before his processing speed assessment. [1]
The source at a glance
- Study type / format
- Abstract of a proposed AI framework evaluated with longitudinal cohort data.
- Population / context
- Older adults in the Providemus alz cohort (n=67).
- Summary based on
- Study abstract
- Original publication
- October 6, 2026
Proposed framework for timing of movement and mood
The abstract introduces PEPHA (Personalized Phenotyping for Aging) as a proposed, interpretable artificial intelligence framework. It is meant to identify which dimensions of 24-hour movement behaviors and when within an observation window are strongly associated with cognitive functioning and depressive symptoms in older adults. The authors note that current observational and interventional approaches rarely capture the temporal dynamics linking everyday movement patterns to cognitive and mental health trajectories. PEPHA is a proposal being evaluated, not an established or approved product.
Supporting source [1]
Cohort of 67 with wearable and wave data
The abstract describes longitudinal data from the Providemus alz cohort: 67 people, up to 6 assessment waves and 528 days of wearable data per person. PEPHA combines passive, high-frequency wearable data on physical activity and sleep with periodic, active, validated cognitive and affective assessments. Two outcomes were examined: processing speed for cognitive functioning and depressive symptoms for mental health. The framework summarizes daily activity and sedentary patterns into slope-based features, tunes a support vector regression model, and applies individualized analyses including time order-swap testing and change point detection to locate potential temporal association windows.
Supporting source [1]
Individual windows and differing behavioral correlates
About 40% of individuals showed moderate or large temporal order effects of 24-hour movement behavior on the outcomes. For one exemplar participant, a man above the mean sample age, two potential temporal association windows were localized roughly 60 and 30 days before his processing speed assessment. Across participants, processing speed was best explained by locomotor activity and depressive symptoms by sedentary behavior. Five control variables were noninformative, while chronological age had predictive power for depressive symptoms. These are associations in exploratory analyses, not evidence that behavior changes cause better cognition or mood.
Supporting source [1]
How to interpret this
Abstract only; the full text was not reviewed. The authors call the work exploratory. The abstract reports no randomized comparison, no intervention and no validated or approved product; findings are associations, not causes.
Based on the study abstract; the full paper, tables and supplementary data were not reviewed.
Source & supporting passages
Matias I, Mack M, Kliegel M, Wac K. · europepmc.org · October 6, 2026