Knee acoustic emissions as a noninvasive biomarker of articular health in patients with juvenile idiopathic arthritis: a clinical validation in an extended study population
Authors' conclusion
Joint acoustic emissions can serve as an inexpensive and easy-to-use digital biomarker to distinguish JIA from healthy controls.
Study context
- Population
- Children with Juvenile Idiopathic Arthritis (JIA) and healthy controls
- Participants
- 116 children
- Comparison
- Knee acoustic emission classifier, JIA vs healthy control knees
- JIAn = 86
- Healthy controlsn = 30reference
- Outcome
- Classification of JIA vs healthy knees by joint acoustic emissions
Methodological detailsmachine learning classifier (XGBoost), leave-one-leg-out cross-validation, training and testing data sets
- Machine learning classifier (XGBoost)
- Leave-one-leg-out cross-validation
- Training and testing data sets
Performance
As reported in the abstract
Classifier performance (JIA vs healthy knees)
- Accuracy, training set validation
- 81.1%
- Accuracy, testing set validation
- 87.7%
- Sensitivity / specificity, training validation
- 88.6% / 72.3%
- Sensitivity / specificity, testing validation
- 88.1% / 83.3%
- AUC of ROC curve
- 0.81
Further findings
Joint scores, active vs inactive JIA knees
- Distributions of joint scores of active and inactive knees significantly different
Original publication
Knee acoustic emissions as a noninvasive biomarker of articular health in patients with juvenile idiopathic arthritis: a clinical validation in an extended study population. Pediatr Rheumatol Online J. Published 20 June 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →