Predicting the onset of end-stage knee osteoarthritis over two- and five-years using machine learning
Authors' conclusion
Our study unveils a robust, externally validated machine learning tool proficient in predicting the onset of esKOA over the next 2 to 5 years.
Study context
- Population
- Participants of the Osteoarthritis Initiative (OAI; development and internal validation) and the Multicentre Osteoarthritis Study (MOST; external validation)3,114 training, 606 validation
- Outcome
- Onset of end-stage knee OA (end-stage KOA (esKOA)): severe radiographic knee osteoarthritis (KOA) with moderate/severe symptoms or mild/moderate radiographic KOA with persistent/intense symptoms
- Follow-up
- 2-to-2.5 years and 4-to-5 years
Methodological detailsmachine learning, external validation
- Machine learning
- External validation
Performance
As reported in the abstract
External validation (MOST) of esKOA prediction, AUC
Right knee, 2.5 years: AUC
0.847
95 % CI 0.811 to 0.882
Right knee, 5 years: AUC
0.853
95 % CI 0.823 to 0.881
Left knee, 2.5 years: AUC
0.824
95 % CI 0.782 to 0.857
Left knee, 5 years: AUC
0.807
95 % CI 0.768 to 0.843
Further findings
Models with fewer predictors
- Comparable performance
Original publication
Predicting the onset of end-stage knee osteoarthritis over two- and five-years using machine learning. Semin Arthritis Rheum. Published 16 March 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →