Hierarchical AI model on X-rays classifies acute vs. chronic osteoporotic vertebral fractures

A hierarchical deep learning model on X-rays detected acute osteoporotic vertebral fractures with 91% sensitivity (95% CI 84.8-95.0%) and 98.8% NPV.

• The initial three-class step (Normal-Chronic, Acute, Indeterminate) achieved 91% accuracy.
• The hierarchical approach outperformed end-to-end and alternative alignment models.
• Limitation: single-institution retrospective design.

Automated summary

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