Rule-based NLP algorithm accurately confirms vertebral fractures from spine imaging reports

A rule-based NLP algorithm reviewing spine imaging reports identified vertebral fractures with a PPV of 95.7% and NPV of 100% vs physician adjudication. Applied to 14,172 older adults with a diagnosis code, the algorithm confirmed fracture in 88.5%.

• The rule-based NLP tool was developed and validated using a random sample of 219 radiology reports with physician adjudication as the reference standard.
• In those without a prior vertebral fracture diagnosis, 90.2% were confirmed as true fractures.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.