Prediction of knee pain improvement over two years for knee osteoarthritis using a dynamic nomogram based on magnetic resonance imaging (MRI)-derived radiomics: a proof-of-concept study
Authors' conclusion
The radiomics-based nomogram comprising the MR radiomics signature and clinical variables achieves a favorable predictive efficacy and accuracy in differentiating improvement in knee pain among OA patients.
Study context
- Population
- Participants with knee osteoarthritis (OA) from the Vitamin D Effects on Osteoarthritis (VIDEO) study, administered vitamin D or placebo
- Participants
- 216 participants
- Comparison
- Training vs Validation
- Outcome
- 20% improvement of knee pain score
- Follow-up
- 2 years
Methodological detailsproof-of-concept, secondary use of the VIDEO study, random 8:2 split into training and validation cohorts, least absolute shrinkage and selection operator (LASSO) regression, multivariable logistic regression nomogram
- Proof-of-concept
- Secondary use of the VIDEO study
- Random 8:2 split into training and validation cohorts
- LASSO regression
- Multivariable logistic regression nomogram
Performance
As reported in the abstract
Nomogram discrimination (AUC) for knee pain improvement
| Test or model | AUC |
|---|---|
| Training | 0.79 (95% CI: 0.72-0.79) |
| Validation | 0.83 (95% CI: 0.70-0.96) |
AUC
Training0.79 (95% CI: 0.72-0.79)
Validation0.83 (95% CI: 0.70-0.96)
Further findings
| Outcome | Training | Validation |
|---|---|---|
| Added value of fusion radiomics signature to the nomogram | ||
| NRI | 0.23 | 0.29 |
| IDI | 0.14 | 0.18 |
| P | P < 0.001 | P < 0.05 |
Decision curve analysis
- Confirmed the clinical usefulness of nomogram
Original publication
Prediction of knee pain improvement over two years for knee osteoarthritis using a dynamic nomogram based on MRI-derived radiomics: a proof-of-concept study. Osteoarthritis Cartilage. Published 2 November 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →