Poster (Knowledge Generation) ID 1985362
Bibliographic record
Abstract
Objective To develop a lower extremity (LE) fragility fracture risk score estimation method among adults with chronic spinal cord injury (SCI). Methods Adults (≥18) with chronic traumatic SCI (n=90, C2-T12, AIS:A-D) participated in a 2-year prospective cohort study. We used a literature search and practice expertise to identify LE fracture predictors. Reference categories (i.e., risk score = 0) were: no prior fracture, 0-9 years post-injury, AIS-CD, no parental history of osteoporosis, and no opioid use. Using logistic regression coefficients, we calculated how far each category is from the base category and computed β i (W ij -W iREF ) for each risk factor. In this model, B was the increase in risk associated with each year post injury. The point value for each fracture risk category was calculated by Point sij =β i (W ij -W iREF )/B. The total points range from 0-21, and the probability of LE fracture is calculated for each point to determine the probability of developing a LE fracture using the formula: Results Most participants had an AIS-A impairment (60.0%), the mean time post-injury=15.23 years (SD=9.58). For the points system (0-17), prior fracture, years post-injury, AIS, Benzodiazepine use, Opioid use, and parental osteoporosis were defined risk factors. An individual’s risk profile can estimate LE fracture risk. A score of 11 equates to 20% or high fracture risk over a 5-year time period. Conclusion We describe our preliminary model to estimate LE fracture risk among those with chronic SCI. We plan to apply statistical and machine learning algorithms using Canadian RHSCIR data and US VHA data to validate the model, and increase the model’s predictability.
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.005 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.003 | 0.002 |
| Insufficient payload (model declined to judge) | 0.931 | 0.789 |
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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".