Finding Silent Fractures: The Economics and Evidence of AI Spine Screening

NICE recently evaluated AI tools designed to opportunistically detect vertebral fragility fractures on routine scans. We explore why 5 were approved for evidence generation, why 3 were sidelined, and what the downstream impact on radiology and DEXA services really looks like.

Key points

• NICE recommends 5 AI tools for opportunistic vertebral fracture detection on CT scans for a 3-year evidence generation period, while 3 X-ray tools require more research.
• Clinical evidence shows the AI technologies can detect moderate to severe fractures with a specificity above 90%, though robust comparisons to UK standard care are lacking.
• Economic modelling suggests the tools could be cost-effective, using a generic AI cost of £7.36 per scan, despite uncertainties around the short-term impact on patient quality of life.
• Downstream resource impact is a major concern, as increased detection will likely drive up demand for DEXA scans and specialist radiologist reviews.
• NICE flags potential equality risks, noting that AI algorithms might underperform in younger patients, ethnic minorities, or other groups underrepresented in the training data.

Source: Artificial intelligence (AI) technologies to aid opportunistic detection of vertebral fragility fractures: early value assessment - National Institute for Health and Care Excellence

This spot is available. Reach clinicians, health-system leaders and medtech and pharma teams following AI in medicine. Sponsor the show

This episode is an AI-generated conversation summarising a public document; the hosts' voices are synthetic. It is for information only and is not medical advice. Always refer to the original source.

Full transcript: https://ai-in-medicine-podcast.vercel.app/episodes/finding-silent-fractures-the-economics-and-evidence-of-ai-spine-screen-18b543