Using Consumer-Grade Physical Activity Trackers to Measure Frailty Transitions in Older Critical Care Survivors: Exploratory Observational Study (Preprint)
Bibliographic record
Abstract
BACKGROUND Critical illness has been suggested as a sentinel event for frailty development in at-risk older adults. Frail critical illness survivors are affected by increased adverse health outcomes, but monitoring the recovery after intensive care unit (ICU) discharge is challenging. Clinicians and funders of health care systems envision an increased role of wearable devices in monitoring clinically relevant measures, as sensor technology is advancing rapidly. The use of wearable devices has also generated great interest among older patients, and they are the fastest growing group of consumer-grade wearable device users. Recent research studies indicate that consumer-grade wearable devices offer the possibility of measuring frailty. OBJECTIVE This study aims to examine the data collected from wearable devices for the progression of frailty among critical illness survivors. METHODS An observational study was conducted with 12 older survivors of critical illness from Kingston General Hospital in Canada. Frailty was measured using the Clinical Frailty Scale (CFS) at ICU admission, hospital discharge, and 4-week follow-up. A wearable device was worn between hospital discharge and 4-week follow-up. The wearable device collected data on step count, physical activity, sleep, and heart rate (HR). Patient assessments were reviewed, including the severity of illness, cognition level, delirium, activities of daily living, and comorbidity. RESULTS The CFS scores increased significantly following critical illness compared with the pre-ICU frailty level (P=.02; d=−0.53). Survivors who were frail over the 4-week follow-up period had significantly lower daily step counts than survivors who were not frail (P=.02; d=1.81). There was no difference in sleep and HR measures. Daily step count was strongly correlated with the CFS at 4-week follow-up (r=−0.72; P=.04). The average HR was strongly correlated with the CFS at hospital discharge (r=−0.72; P=.046). The HR SD was strongly correlated (r=0.78; P=.02) with the change in CFS from ICU admission to 4-week follow-up. No association was found between the CFS and sleep measures. The pattern of increasing step count over the 4-week follow-up period was correlated with worsening of frailty (r=.62; P=.03). CONCLUSIONS This study demonstrated an association between frailty and data generated from a consumer-grade wearable device. Daily step count and HR showed a strong association with the frailty progression of the survivors of critical illness over time. Understanding this association could unlock a new avenue for clinicians to monitor and identify a vulnerable subset of the older adult population that might benefit from an early intervention. CLINICALTRIAL
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".