MRI-derived radiomics-based nomogram predicts improvement in osteoarthritis knee pain

0

[ad_1]

A Derived MRI the radiomics nomogram helps predict whether patients with osteoarthritis are likely to see improvements in knee pain over 2 years

Using an MRI-derived radiomic nomogram that also includes patients’ clinical characteristics helps predict which patients with knee osteoarthritis are likely to see improvement in their pain over a 2-year period, according to a study. study conducted by Chinese researchers.

Osteoarthritis (OA) is a common condition that affects 7% of the world’s population, or more than 500 million people. Although osteoarthritis has been conventionally assessed using X-rays, an alternative is magnetic resonance imaging (MRI). In fact, MRI has been suggested to be the best imaging modality for OA to visualize multiple individual pain-related tissue pathologies and also to predict clinical course. When Chinese researchers undertook a randomized trial to examine the effect of vitamin D on osteoarthritis-related knee pain, compared to a placebo, there were no significant differences in MRI-measured tibial cartilage volume or knee pain score over 2 years. However, in a post-hoc analysis, 64% of vitamin D participants and 57% of placebo participants achieved a 20% improvement in knee pain score over 2 years.

Since one-fifth of the participants actually saw an improvement in their knee pain, the researchers wondered how it would be possible to identify patients who might benefit from vitamin D. They decided to create a radiomic nomogram based on MRI-derived features of the subchondral bone as well as clinical factors that could be used to predict 2-year improvement in osteoarthritis knee pain. The team used data from the VIDEO study of knee osteoarthritis in which participants had an MRI at baseline and after 24 months. The primary endpoint was knee pain, which was assessed using the WOMAC score. The team used MRI data to create a radiomics model that was trained and then validated with separate cohorts from the VIDEO trial. Data from the model was then used to produce a nomogram to predict improvement in osteoarthritis knee pain over two years. The model was evaluated based on the area under the receiver characteristics operating curve (AUC).

MRI-derived radiomics model and prediction of knee pain

A total of 216 patients with a mean age of 68.3 years (47% female) were included and 172 were used in the training cohort, of whom 78 had no improvement in pain and the rest were used in the validation cohort.

Only two variables, female gender and total knee pain score at baseline, were significant predictors of improvement in knee pain over 2 years and were used in the clinical model, with vitamin supplementation D. The MRI-derived model included a radiomic signature and the two clinically significant variables.

In the validation cohort, the nomogram had a higher AUC than the clinical model (0.83 vs 0.71) for predicting improvement in knee pain although this difference was not significant (p=0 ,08). Additionally, the use of decision curve analysis confirmed the clinical utility of the nomogram.

The authors concluded that their radiomics-based nomogram, which included MRI radiomic signature and clinical variables, achieved favorable predictive power and accuracy in differentiating improvement in knee pain in OA patients.

Quote
Lin T et al. 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 2022

[ad_2]
Source link

Share.

Comments are closed.