Conexiant’s news site is now MDSpire News. Learn more
Advertisement
Knee vibrations may signal cartilage damage
Machine-learning models distinguished healthy knees from those with osteoarthritis-related cartilage damage, but age and BMI performed as well as or better than the vibration-based models.
To evaluate the potential of vibroarthrography combined with machine learning as a noninvasive method for identifying osteoarthritis-related cartilage damage.
Approach:
Participants: 97 participants were evaluated, including 48 healthy controls and 49 patients with symptomatic knee osteoarthritis or cartilage damage.
Methodology: Vibroarthrography signals were recorded using an accelerometer while participants completed movements under closed and open kinetic chain conditions. Machine learning classifiers were applied to analyze the data.
Key Findings:
Under closed kinetic chain conditions, Random Forest achieved an AUC of 0.917, XGBoost 0.912, and AdaBoost 0.910.
Under open kinetic chain conditions, Random Forest achieved an AUC of 0.857 and XGBoost 0.846.
Demographic differences, particularly age and BMI, were significant confounding factors affecting diagnostic performance.
Interpretation:
The findings indicate that while vibroarthrography shows promise as a noninvasive screening method for knee joint degeneration, its diagnostic contribution may not exceed that of demographic characteristics alone.
Limitations:
The cohort size was relatively small.
Demographic differences between groups may confound results.
The accelerometer was attached to the skin, potentially affecting signal quality.
Conclusion:
Further validation across different sensor types, mounting configurations, and measurement setups is required.
Supervised rehabilitation and exercise-based therapies may improve function, pain, and bone health in ankylosing spondylitis, according to a new review.
