AI tools spot spinal fractures missed in routine scan reports

NICE found that AI tools detect moderate to severe vertebral fragility fractures missed in original radiology reports, generally with specificity above 90%. It allowed five in the NHS in 2025.

  • 2 an organization

    The tools detected additional moderate to severe vertebral fractures that original radiology reports had missed, generally with specificity above 90%.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

Two independent assessment reports support the benefit.

Compared with

Original radiology reports (standard care). Measured.

The system’s part
Thirteen studies compared the tools with standard care, mostly the original radiology report, against a reference standard. Most were retrospective and done outside the UK.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
AI tools for opportunistic detection of vertebral fragility fractures on CT: BriefCase-Triage, CINA-VCF Quantix, HealthVCF, HealthOST and IB Lab FLAMINGO
Made by
Aidoc Medical (BriefCase-Triage), Avicenna.AI (CINA-VCF Quantix), Nanox AI (HealthVCF and HealthOST) and IB Lab (IB Lab FLAMINGO)
Used by
Hospitals in the studies reviewed by NICE and NHS radiology services in England during the evidence generation period
Where
England, United Kingdom (guidance), with studies in several countries
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Assessment report, by authors with no tie to the system.

    National Institute for Health and Care Excellence. Artificial intelligence (AI) technologies to aid opportunistic detection of vertebral fragility fractures: early value assessment. HealthTech guidance HTG760 (formerly HTE34), section 3: Committee discussion. 14 October 2025.

    The committee concluded that, overall, the evidence suggests that the AI technologies can detect additional moderate to severe vertebral fractures (as confirmed by a reference standard) that were not reported in the original radiology report. Generally, the technologies could detect these fractures with a specificity above 90%.

  2. Assessment report, by authors with no tie to the system.

    National Institute for Health and Care Excellence. HTG760, section 1: Recommendations. 14 October 2025.

    Five artificial intelligence (AI) technologies can be used in the NHS during the evidence generation period as options to aid the opportunistic detection of vertebral fragility fractures (VFFs).

Details

AI system

Workflow

The tools analyzed chest and abdominal CT scans taken for other reasons. Radiologists still reviewed every scan in the usual way.

Follow-up

Conditions for replication

Local protocols refer people with a newly found fracture for assessment and treatment. Radiology and bone density scanning services can absorb the extra referrals.

Entry details

Sector

Healthcare (radiology and osteoporosis).

Purpose

Aidoc Medical, Avicenna.AI, Nanox AI and IB Lab built their tools to flag vertebral fractures on CT scans taken for other reasons.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). AI tools spot spinal fractures missed in routine scan reports (AIBD-0739). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0739.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions