Deep learning-based identification of vertebral fracture and osteoporosis in lateral spine radiographs and DXA vertebral fracture assessment to predict incident fracture
Bibliographic record
Abstract
Deep learning (DL) identification of vertebral fractures and osteoporosis in lateral spine radiographs and DXA vertebral fracture assessment (VFA) images may improve fracture risk assessment in older adults. In 26 299 lateral spine radiographs from 9276 individuals attending a tertiary-level institution (60% train set; 20% validation set; 20% test set; VERTE-X cohort), DL models were developed to detect prevalent vertebral fracture (pVF) and osteoporosis. The pre-trained DL models from lateral spine radiographs were then fine-tuned in 30% of a DXA VFA dataset (KURE cohort), with performance evaluated in the remaining 70% test set. The area under the receiver operating characteristics curve (AUROC) for DL models to detect pVF and osteoporosis was 0.926 (95% CI 0.908-0.955) and 0.848 (95% CI 0.827-0.869) from VERTE-X spine radiographs, respectively, and 0.924 (95% CI 0.905-0.942) and 0.867 (95% CI 0.853-0.881) from KURE DXA VFA images, respectively. A total of 13.3% and 13.6% of individuals sustained an incident fracture during a median follow-up of 5.4 years and 6.4 years in the VERTE-X test set (n = 1852) and KURE test set (n = 2456), respectively. Incident fracture risk was significantly greater among individuals with DL-detected vertebral fracture (hazard ratios [HRs] 3.23 [95% CI 2.51-5.17] and 2.11 [95% CI 1.62-2.74] for the VERTE-X and KURE test sets) or DL-detected osteoporosis (HR 2.62 [95% CI 1.90-3.63] and 2.14 [95% CI 1.72-2.66]), which remained significant after adjustment for clinical risk factors and femoral neck bone mineral density. DL scores improved incident fracture discrimination and net benefit when combined with clinical risk factors. In summary, DL-detected pVF and osteoporosis in lateral spine radiographs and DXA VFA images enhanced fracture risk prediction in older adults.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".