Evaluating an Artificial Intelligence software for opportunistic low bone mineral density and osteoporosis screening: a validation study
Bibliographic record
Abstract
Abstract Despite the profound prevalence and fracture risk of osteoporosis, access to the gold standard DXA scans remains limited, especially in rural communities. Rho is an artificial intelligence software that can identify individuals at risk of low BMD and osteoporosis using radiographs. This study will independently validate Rho software by evaluating its performance against DXA in a retrospective cohort of patients. We conducted a retrospective study of 4878 patients (mean age 70 ± 10, 80% female), with DXA acquired within 1 yr of a radiograph. The area under the curve (AUC) was calculated to evaluate the performance of Rho in identifying patients at risk for low BMD (T-Score < −1) and osteoporosis (T-Score ≤ −2.5). Further subgroup analyses were performed based on radiograph location, sex, and rural vs urban populations. The overall AUC for predicting low BMD was 0.840 (95% CI: 0.831-0.848), with an optimal Rho score threshold of 6. For osteoporosis prediction, the AUC was 0.815 (95% CI: 0.806-0.824), with an optimal Rho score threshold of 7. Rural and urban populations have strong AUCs for low BMD (AUC = 0.873; 0.873) and osteoporosis (AUC = 0.865; 0.812). Likewise, Rho demonstrated strong, comparable (p > .25) performance in both men and women for prediction of low BMD. Although, optimal cutoffs differed between females and males for both low BMD and osteoporosis. Rho demonstrated high effectiveness in identifying patients at risk for low BMD and osteoporosis. The findings support Rho as an opportunistic screening tool and may fill a clinical gap in communities lacking access to DXA.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".