Predicting Falls Using the Stroke Assessment of Fall Risk Tool
Bibliographic record
Abstract
BACKGROUND: Falls in the inpatient stroke population are common, resulting in increased morbidity and slow rehabilitation progress. Falls may result from stroke-specific neurologic deficits; however, assessment of these deficits is lacking in many fall screening tools. OBJECTIVE: To compare the ability to predict falls of the Stroke Assessment of Fall Risk (SAFR) tool, which includes items related to stroke-specific neurologic deficits, and the commonly used Morse Fall Scale, which does not include these items. DESIGN: Prospective cohort study. SETTING: Inpatient tertiary stroke rehabilitation unit. PARTICIPANTS: Patients (N = 220) with acute stroke. MAIN OUTCOME MEASURES: Falls were captured by the medical records from January 2017 to September 2018. Logistic regression analysis evaluated both screening tools for predicting falls by calculating sensitivity, specificity, area under the receiver operating characteristic (AUC-ROC) curve, and odds ratio (OR). We compared SAFR and Morse mean scores between fallers and non-fallers using t-tests. RESULTS: Forty-eight (21.8%) patients experienced ≥1 fall. SAFR, but not Morse, scores showed a statistically significant difference between fallers and non-fallers (P = .001 vs P = .24, respectively). Higher SAFR score was associated with higher odds of falls (OR 1.36, 95% CI [1.12, 1.64]), whereas Morse was not (OR 1.04, 95% CI [0.97, 1.12]). SAFR showed a statistically significant difference in hemi-neglect between fallers and non-fallers (P = .03). Sensitivity and specificity of SAFR were 47.9% and 76.7%, vs 45.8% and 68.0% for Morse, respectively. SAFR positive predictive value and negative predictive value were 36.5% and 84.1%, respectively, similar to Morse (28.6% and 81.8%). The AUC-ROC was 0.65 for SAFR and 0.56 for Morse. CONCLUSIONS: SAFR was significantly associated with fall risk and had better discrimination between fallers and non-fallers than Morse. The neurologic-specific hemi-neglect component of SAFR, a component not present on the Morse, was a fall risk factor. Further research evaluating the predictive value of fall scales that include neurologic deficits is needed.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".