Evaluating the Prognostic and Clinical Validity of the Fall Risk Score Derived From an AI-Based mHealth App for Fall Prevention: Retrospective Real-World Data Analysis
Bibliographic record
Abstract
Background: Falls pose a significant public health concern, with increasing occurrence due to the aging population, and they are associated with high mortality rates and risks such as multimorbidity and frailty. Falls not only lead to physical injuries but also have detrimental psychological and social consequences, negatively impacting quality of life. Identifying individuals at high risk for falls is crucial, particularly for those aged ≥60 years and living in residential care settings; current professional guidelines favor personalized, multifactorial fall risk assessment approaches for effective fall prevention. Objective: This study aimed to explore the prognostic validity of the Fall Risk Score (FRS), a multifactorial-based metric to assess fall risk (using longitudinal real-world data), and establish the clinical relevance of the FRS by identifying threshold values and the minimum clinically important differences. Methods: This retrospective cohort study involved 617 older adults (857 observations: 615 of women, 242 of men; mean age 83.3, SD 8.7 years; mean gait speed 0.49, SD 0.19 m/s; 622 using walking aids) residing in German residential care facilities and used the LINDERA mobile health app for fall risk assessment. The study focused on the association between FRS at the initial assessment (T1) and the normalized number of falls at follow-up (T2). A quadratic regression model and Spearman correlation analysis were utilized to analyze the data, supported by descriptive statistics and subgroup analyses. Results: The quadratic model exhibited the lowest root mean square error (0.015), and Spearman correlation analysis revealed that a higher FRS at T1 was linked to an increased number of falls at T2 (ρ=0.960, P<.001). Subgroups revealed significant strong correlations between FRS at T1 and falls at T2, particularly for older adults with slower gait speeds (ρ=0.954, P<.001) and those using walking aids (ρ=0.955, P<.001). Threshold values revealed that an FRS of 45%, 32%, and 24% corresponded to the expectation of a fall within 6, 12, and 24 months, respectively. Distribution-based minimum clinically important difference values were established, providing ranges for small, medium, and large effect sizes for FRS changes. Conclusions: The FRS exhibits good prognostic validity for predicting future falls, particularly in specific subgroups. The findings support a stratified fall risk assessment approach and emphasize the significance of early and personalized intervention. This study contributes to the knowledge base on fall risk, despite limitations such as demographic focus and potential assessment interval variability.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 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 teacher head, 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".