JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Development and validation of a predictive model for vertebral fracture risk in osteoporosis patients

  • 0Department of Radiology, Shanghai Tenth People's Hospital, Clinical Medical College of Nanjing Medical University, 301 Middle Yanchang Road, Shanghai, 200072, People's Republic of China.
European Spine Journal : Official Publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society +

|

July 2, 2024

|

July 2, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

A new model integrating bone density, CT imaging, and deep learning radiomics accurately predicts osteoporotic vertebral fractures (OVFs) risk. This fusion approach enhances prediction accuracy for better patient management.

Area Of Science

  • Radiology and Medical Imaging
  • Artificial Intelligence in Healthcare
  • Osteoporosis Research

Background

  • Osteoporotic vertebral fractures (OVFs) pose a significant health burden.
  • Accurate risk prediction is crucial for timely intervention and prevention.
  • Existing models may not fully leverage advanced imaging and AI techniques.

Purpose Of The Study

  • To develop and validate a predictive model for OVFs risk.
  • To integrate demographic, bone mineral density (BMD), CT imaging, and deep learning radiomics features.
  • To assess the model's performance and clinical utility.

Main Methods

  • A cohort of 169 osteoporosis patients was analyzed.
  • Deep transfer learning (DTL) with ResNet-50 and radiomics features were employed.
  • A fusion model combining clinical, radiomics, and DTL features was constructed and validated using AUC, C-index, and decision curve analysis (DCA).

Main Results

  • BMD, paravertebral muscle CT values, and cross-sectional area were significant predictors.
  • The fusion model achieved the highest predictive performance (C-index: 0.839 training, 0.795 test).
  • The developed nomogram demonstrated clinical utility for OVFs risk prediction.

Conclusions

  • A robust predictive model for OVFs risk was successfully developed.
  • The model integrates BMD, CT data, and radiomics-DTL features, offering high accuracy.
  • This tool can inform OVFs prevention and treatment strategies.

Keywords: