STRENGTHS AND LIMITATIONS OF USING DIFFERENT SENSOR TECHNOLOGIES TO ASSESS CLINICAL OUTCOMES IN DYADIC CARE
Bibliographic record
Abstract
Abstract Home sensor and smart home technologies offer the potential to provide important objective information on daily activities, functional abilities, and caregiving tasks for individuals with cognitive impairment and care partners. Combining information from multiple sensors, such as a bedmat, wearable, and motion sensors, can deliver more informative data on dyadic interactions during nighttime activity (e.g., room location and which partners are out of bed in addition to sleep measures). Preliminary work from a study developing a digital signature of caregiver burden using data from multiple sensors in a home technology platform is presented. Using data from two different sensors provided additional information on nighttime behaviors related to care partner burden level in a sample of 47 dyads (care partner and individual with dementia or mild cognitive impairment). Estimated sleep duration calculated from an under the mattress bedmat and activity monitoring wristwatch showed a low concordance (r=0.36). However, an additional 9156 nights were collected from the union of the two sensors as compared to the wristwatch (29318 nights) or bedmat (15704 nights) alone. Benefits to using multiple sensors include the ability to expand the amount of information collected on a dyad and the locations where information can be collected (e.g., sleep occurring outside of the bedroom). Challenges include determining the more accurate estimate when there is discordance between different sensor types and evaluating the accuracy of new or updated sensors. Additional work is needed to determine which sensor or combination of sensors is optimal at approximating a clinical outcome of interest.
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 | 0.166 | 0.261 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.004 |
| Bibliometrics | 0.006 | 0.009 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.006 | 0.004 |
| Open science | 0.006 | 0.006 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".