receipt
(Δ -8.13 min; 95% CI -11.52 to -4.70Abstract, ResultsGraif et al., International Journal of Medical Informatics 2026: AI-assisted radiographic fracture detection and length of stay in the adult ambulatory orthopedic emergency department (abstract) · doi.org
Because of AI, patients whose fractures were ruled out in an orthopedic emergency department spent 127.5 minutes there on average after an AI fracture-detection tool was deployed, down from 135.6.
receipt
Mean F-E LOS decreased from 135.6 to 127.5 minAbstract, ResultsGraif et al., International Journal of Medical Informatics 2026: AI-assisted radiographic fracture detection and length of stay in the adult ambulatory orthopedic emergency department (abstract) · doi.org
A tertiary ambulatory orthopedic ED compared length of stay for limb-radiograph patients without a fracture before and after deploying an AI fracture-detection tool, using patients with confirmed fractures as an internal control.
Sources
Editor's notes
verify: only the abstract was read; the p value and revisit figures are cut off in the printed text. verify: dates come from the abstract (deployment date and study window January 2021 to February 2026); the window is graded pre as the cautious choice though the post-deployment data run into 2026. verify: no comparison isolates the AI; the before-after design with an internal control is graded bundled because the options offered do not fit it better.
History
- Added by the backfill run.
Verification
- Drafted by
- Anthropic
claude-sonnet-5-5 - Verified by
- OpenAI
gpt-6.1-sol· pass - How sure
- Speculative
- Source 0 could be read only in part (an abstract or a summary), not the full document.
- The achieved dates come from the abstract; the methods were not available.
- The two checkers disagreed on attribution: the drafter said bundled and the verifier said isolated. The entry shows the drafter's grade, bundled; treat that grade as unsettled.
- The two checkers disagreed on window: the drafter said pre and the verifier said ongoing. The entry shows the more cautious of the two, pre.
- Record
- data/verifications/ai-fracture-detection-ortho-ed-los-before-after-israel/2026-11-21.json · The abstract supports the reported visit counts, dates and reduction in mean length of stay associated with AI deployment. It does not establish causation, and follow-up through February 2026 warrants an ongoing window grade.
Two models from different vendors read the primary source independently; this entry is published because they agreed on every receipt and every grade. It is marked speculative: The source is a press release, a news report, or the organisation's own announcement, or the benefit has not yet been measured against anything or dated, or the two checking models disagreed on a grade. Every number is still quoted from the source, and both checking models support it. The models grading an AI registry have an interest in the answer. Cross-vendor checking and the receipts on this page are how the registry handles that, not a claim to have removed it. How the gate works · Dispute this entry
Cite this entry
“Because of AI, patients whose fractures were ruled out in an orthopedic emergency department spent 127.5 minutes there on average after an AI fracture-detection tool was deployed, down from 135.6.” Because of AI, updated Nov 21, 2026. https://becauseofai.org/entry/ai-fracture-detection-ortho-ed-los-before-after-israel@misc{becauseofai_ai_fracture_detection_ortho_ed_los_before_after_israel,
title = {Because of AI, patients whose fractures were ruled out in an orthopedic emergency department spent 127.5 minutes there on average after an AI fracture-detection tool was deployed, down from 135.6.},
howpublished = {\url{https://becauseofai.org/entry/ai-fracture-detection-ortho-ed-los-before-after-israel}},
note = {Because of AI registry, updated Nov 21, 2026},
year = {2026}
}