Technology for home-based frailty assessment and prediction: A systematic review
Bibliographic record
Abstract
The current clinical frailty assessments are time-consuming and subjective which can lead to inaccurate results and delayed medical attention. Sensor technology and artificial intelligence enable home-based frailty assessment; however, there are no systematic reviews of existing technological methods for home-based frailty assessment and prediction. Objective: To analyze and synthesize the frailty criteria, sensor technology, and the statistical or artificial intelligence methods used in home-based frailty assessment and prediction. Methods: An exhaustive database search was performed. Three reviewers screened all studies by following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The sensors and AI used for assessing frailty were synthesized with a particular focus on home-based technology. The Sackett's Level of Evidence Scale was also used to evaluate clinical evidence for the included studies. Results: Body-worn sensors were the most commonly used (72%) technology in homebased frailty assessment. All of the body-worn sensors were accelerometer-based. 88% of the included studies measured physical activity for assessing frailty commonly defined by Fried's Frailty Index (75%). Heterogenous machine learning algorithms have been applied for classifying frailty. However, none of the AI methods were tested for the predictability of frailty. Only one longitudinal study followed up older participants for 10 years and revealed a high odds ratio for the development of frailty using physical activity.
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 | 0.008 | 0.035 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.008 | 0.008 |
| Bibliometrics | 0.010 | 0.009 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 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".