Mobility-Based Smartphone Digital Phenotypes for Unobtrusively Capturing Everyday Cognition, Mood, and Community Life-Space in Older Adults: Feasibility, Acceptability, and Preliminary Validity Study
Bibliographic record
Abstract
BACKGROUND: Current methods of monitoring cognition in older adults are insufficient to address the growing burden of Alzheimer disease and related dementias (AD/ADRD). New approaches that are sensitive, scalable, objective, and reflective of meaningful functional outcomes are direly needed. Mobility trajectories and geospatial life space patterns reflect many aspects of cognitive and functional integrity and may be useful proxies of age-related cognitive decline. OBJECTIVE: We investigated the feasibility, acceptability, and preliminary validity of a 1-month smartphone digital phenotyping protocol to infer everyday cognition, function, and mood in older adults from passively obtained GPS data. We also sought to clarify intrinsic and extrinsic factors associated with mobility phenotypes for consideration in future studies. METHODS: Overall, 37 adults aged between 63 and 85 years with healthy cognition (n=31, 84%), mild cognitive impairment (n=5, 13%), and mild dementia (n=1, 3%) used an open-source smartphone app (mindLAMP) to unobtrusively capture GPS trajectories for 4 weeks. GPS data were processed into interpretable features across categories of activity, inactivity, routine, and location diversity. Monthly average and day-to-day intraindividual variability (IIV) metrics were calculated for each feature to test a priori hypotheses from a neuropsychological framework. Validation measures collected at baseline were compared against monthly GPS features to examine construct validity. Feasibility and acceptability outcomes included retention, comprehension of study procedures, technical difficulties, and satisfaction ratings at debriefing. RESULTS: All (37/37, 100%) participants completed the 4-week monitoring period without major technical adverse events, 100% (37/37) reported satisfaction with the explanation of study procedures, and 97% (36/37) reported no feelings of discomfort. Participants' scores on the comprehension of consent quiz were 97% on average and associated with education and race. Technical issues requiring troubleshooting were infrequent, though 41% (15/37) reported battery drain. Moderate to strong correlations (r≥0.3) were identified between GPS features and validators. Specifically, individuals with greater activity and more location diversity demonstrated better cognition, less functional impairment, less depression, more community participation, and more geospatial life space on objective and subjective validation measures. Contrary to predictions, greater IIV and less routine in mobility habits were also associated with positive outcomes. Many demographic and technology-related factors were not associated with GPS features; however, income, being a native English speaker, season of study participation, and occupational status were related to GPS features. CONCLUSIONS: Theoretically informed digital phenotypes of mobility are feasibly captured from older adults' personal smartphones and relate to clinically meaningful measures including cognitive test performance, reported functional decline, mood, and community activity. Future studies should consider the impact of intrinsic and extrinsic factors when interpreting mobility phenotypes. Overall, smartphone digital phenotyping is a promising method to unobtrusively capture relevant risk and resilience factors in the context of aging and AD/ADRD and should continue to be investigated in large, diverse samples.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".