Certified into the record
The exact text we saved
This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.
TRUVACE RECORD VERSION record: TRV-2026-2981 version: 1 kind: certified reason: Certified into the record timestamp: 2026-11-17T06:01:52.229855Z status: published lens: g_space sector: health headline: Opportunistic Risk Assessment of Major Osteoporotic Fractures from Routine Chest Radiographs Using Deep Learning dek: Background Bone mineral density (BMD) and the Fracture Risk Assessment Tool (FRAX) incompletely capture fracture risk in the osteopenic range, where much of the fracture burden occurs. Routine chest radiographs are acquired across a broad range of patients and may contain information relevant to fracture risk, offering a potential opportunistic complement without additional imaging burden. Methods We developed a convolutional neural network survival model in 53,109 adults at a tertiary hospital and externally va… gain_title: In an external validation of 85,284 patients, a deep-learning model reading routine chest radiographs predicted major osteoporotic fracture with a C-index of 0.843, versus 0.779 for FRAX with bone mineral density. problem_title: (none) trace_subject: (none) gain_reading: In an external validation of 85,284 patients, a deep-learning model reading routine chest radiographs predicted major osteoporotic fracture with a C-index of 0.843, versus 0.779 for FRAX with bone mineral density. gain_evidence: the deep-learning (DL) model achieved a C-index of 0.843 problem_reading: (none) problem_evidence: (none) quick_read: A convolutional neural network survival model that reads routine chest radiographs identified people at high risk of major osteoporotic fracture better than FRAX combined with bone mineral density. In external validation it reached a C-index of 0.843 and a 10-year AUROC of 0.855, against 0.779 and 0.785 for FRAX with BMD. Bone density and FRAX incompletely capture fracture risk in the osteopenic range, where much of the fracture burden occurs. Chest radiographs are already taken in a broad range of patients, so the approach could add risk information without extra imaging. The authors report the greatest benefit in patients with osteopenia. Everyone in the study had been referred for densitometry, so the results may not carry over to an unselected population. The authors say absolute-risk and case-finding estimates need prospective evaluation in routine radiography patients. limitation: All participants had been referred for densitometry, so absolute-risk and case-finding estimates require prospective evaluation in an unselected routine-radiography population. tag: Evidence-backed gain key_points: The model was developed in 53,109 adults at a tertiary hospital. | It was externally validated in 85,284 patients from two independent institutions. | External cohorts had a mean age of 58.6 years, were 68.9% female and had 77 months of follow-up. | The model's C-index was 0.843 (95% CI 0.837 to 0.850), versus 0.779 for FRAX with BMD. | Its censoring-adjusted 10-year AUROC was 0.855, versus 0.785 for FRAX with BMD. | The advantage was greatest in patients with osteopenia. rundown: Researchers built a convolutional neural network survival model in 53,109 adults at one tertiary hospital. Eligibility required a chest radiograph within 1 year of a dual-energy X-ray absorptiometry scan. The primary outcome was incident major osteoporotic fracture. The model was externally validated in 85,284 patients from two independent institutions. Discrimination was assessed with the C-index and AUROC at 2, 3, 5 and 10 years, compared with FRAX with BMD and with the lowest BMD T-score. In the validation cohorts, the model scored a C-index of 0.843 and a 10-year AUROC of 0.855, higher than FRAX with BMD. The authors conclude the benefit was greatest in patients with osteopenia, a group where standard tools miss much of the fracture risk. sources: - peer_reviewed | NEJM AI | https://doi.org/10.1056/aioa2600590 | 2026-11-16 prev: 0000000000000000000000000000000000000000000000000000000000000000
- SHA-256 hash
- c483e157568d6b813b36e3c4e3f22d6d1584f0bb5a932072aff8d79c91f6f789
- Previous version’s hash
- 0000000000000000000000000000000000000000000000000000000000000000
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2981 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace