What type of study is this?

September 10, 2025JMIR Medical InformaticsOpen Access

Deep Learning Radiomics Model Based on Computed Tomography Image for Predicting the Classification of Osteoporotic Vertebral Fractures: Algorithm Development and Validation

View Full Paper

Ask AI

Bookmark

Authors

JLJiayi LiuNanjing Medical University LZLincen Zhang YYYousheng YuanNanjing Medical University

Discussion

Member takes

Implication

Observational analysis demonstrates improved classification accuracy for osteoporotic vertebral fractures using deep learning radiomics, suggesting enhanced clinical decision-making.

Key Points

The RadImageNet-based fused model achieved a macro-average AUC of 0.934, outperforming the ImageNet-based model.
Machine learning classifiers, including multilayer perceptron and LightGBM, showed significant efficacy in classifying osteoporotic vertebral fractures using CT imaging.
Feature importance analysis with SHAP highlighted top predictors like cluster shade and mean, providing insights into model predictions.
Deep learning technologies in radiomics can potentially transform clinical approaches to managing osteoporotic vertebral fractures.

Cite This Study

Liu et al. (2025) studied this question.

synapsesocial.com/papers/68c1d7fe54b1d3bfb60fa567 https://doi.org/10.2196/75665

View Full Paper

Ask AI

Bookmark

Implication

Observational analysis demonstrates improved classification accuracy for osteoporotic vertebral fractures using deep learning radiomics, suggesting enhanced clinical decision-making.

Deep Learning Radiomics Model Based on Computed Tomography Image for Predicting the Classification of Osteoporotic Vertebral Fractures: Algorithm Development and Validation

Discussion

Member takes

Implication

Key Points

Cite This Study

Deep Learning Radiomics Model Based on Computed Tomography Image for Predicting the Classification of Osteoporotic Vertebral Fractures: Algorithm Development and Validation

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider