Related Experiment Video
Updated: Jul 18, 2026
07:44
Practical Considerations in Studying Metastatic Lung Colonization in Osteosarcoma Using the Pulmonary Metastasis Assay
Published on: March 12, 2018
10.6K
Nomograms Based on X-Ray Radiomics for Predicting Pain Progression in Knee Osteoarthritis Using Data From the
Yingwei Sun1, Jing Liu2, Chunbo Deng3
1Department of Radiology, Affiliated Hospital of Liaoning University of Traditional Chinese Medicine, Shenyang, China.
JMIR Medical Informatics
|January 14, 2026
Summary
This study developed a predictive model using x-ray radiomics to identify individuals likely to experience worsening knee osteoarthritis (KOA) pain. The nomogram demonstrated strong accuracy in forecasting KOA pain progression, aiding early intervention for at-risk patients.
Area of Science:
- Radiology
- Medical Imaging
- Osteoarthritis Research
Background:
- Knee osteoarthritis (KOA) is a common musculoskeletal disorder in older adults.
- Early identification of patients at risk for rapid KOA progression is crucial for effective management.
- Predictive models can improve treatment strategies and patient prognosis.
Purpose of the Study:
- To develop and validate a nomogram model utilizing x-ray radiomics.
- To accurately identify individuals experiencing progression of KOA pain.
- To aid in early intervention for KOA patients.
Main Methods:
- Utilized data from 600 participants, classifying them as pain progressors or non-progressors.
- Extracted radiomics features from subchondral bone regions of tibia and femur.
- Employed Least Absolute Shrinkage and Selection Operator (LASSO) regression for feature selection and nomogram construction.
- Validated model performance using receiver operating characteristic (ROC) curves, calibration, and decision curve analysis.
Main Results:
- A total of 450 participants were included in the final analysis.
- The primary radiomics feature identified was Wavelet-HH_gldm_HighGrayLevelEmphasis.
- Nomograms achieved areas under the curve (AUC) of 0.766 and 0.753, indicating good predictive performance.
- Subgroup analyses showed AUCs of 0.795 and 0.740 for specific nomograms.
Conclusions:
- X-ray radiomics-based nomograms show significant potential for predicting KOA pain progression.
- The developed models demonstrated excellent accuracy and predictive capability.
- These findings support the use of radiomics in clinical decision-making for KOA management.
