Multimodal X-ray deep learning model accurately stages vertebral compression fractures

In a study of 2,129 patients, an X-ray-based multimodal deep learning and radiomics model achieved AUC 0.988 (95% CI 0.975–0.990) for staging vertebral compression fractures.

• The best-performing model fused deep learning features from VGG16 with radiomics and clinical data, classified by logistic regression.
• Decision curve analysis indicated high net clinical benefit across a wide range of probability thresholds.

Automated summary

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