Evaluation of the Predictive Accuracy of the interRAI Falls Clinical Assessment Protocol, Scott Fall Risk Screen, and a Supplementary Falls Risk Assessment Tool Used in Residential Long-Term Care: A Retrospective Cohort Study
Bibliographic record
Abstract
Falls in residential long-term care (LTC) facilities continue to be a leading cause of injury for residents and cost for the health care system. Interdisciplinary clinical teams are responsible for assessing risk levels for their residents and developing appropriate care plans and interventions in response. This study compares the predictive accuracy of three separate fall risk assessment tools: the interRAI Falls Clinical Assessment Protocol (CAP), derived from the LTC Facility (LTCF) or Minimum Data Set (MDS) 2.0 assessments; the Scott Fall Risk Screen; and a modified Fall Risk Tool that was implemented as part of a provincial Fall Reduction Strategy in Nova Scotia. To conduct this retrospective cohort study, secondary data were collected from 1,553 LTC residents with interRAI assessments completed between March 1, 2015 and September 29, 2016, across Nova Scotia and New Brunswick. For each resident, data were collected regarding the three fall risk assessments, along with fall incident data for use in sensitivity, specificity, and logistic regression analyses. This study found that although all three tools had limitations with sensitivity or specificity thresholds, the interRAI Falls CAP delivered the highest accuracy with a c-statistic of 0.673, compared with the Scott Fall Risk Screen at 0.529 and the modified Fall Risk Tool at 0.609. When diseases that have been established to be a risk factor for falls were added to the model, the overall accuracy of the interRAI Falls CAP combined with those covariates increased to 0.749. These results suggest that the best practice guidelines for fall risk assessment be revisited, and that the interRAI Falls CAP could potentially be updated to include certain diseases and controls for optimal predictive ability.
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 | 0.018 | 0.058 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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 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".