MicroRNA signature for early prediction of knee osteoarthritis structural progression using integrated machine and deep learning approaches
Authors' conclusion
This study introduces a novel miRNA prognosis model for knee OA patients at risk of structural progression.
Study context
- Population
- Osteoarthritis Initiative (OAI) participants with knee osteoarthritis (OA); baseline serum microRNAs (miRNAs)development set
- Participants
- 152 participants
- Comparison
- Progressors vs non-progressors
- Progressorsn = 91
- Non-progressorsn = 61reference
- Outcome
- Performance (AUC, accuracy) of a miRNA prognosis model identifying knee OA structural progressors/non-progressors
Methodological detailsmachine/deep learning, Monte Carlo cross-validation, independent validation set
- Machine/deep learning
- Monte Carlo cross-validation
- Independent validation set
Performance
As reported in the abstract
ANN model (age + 4 miRNAs: hsa-miR-556-3p, hsa-miR-3157-5p, hsa-miR-200a-5p, hsa-miR-141-3p), development
AUC
0.94
95% CI 0.89, 0.97
Accuracy
0.84
95% CI 0.77, 0.89
Further findings
Model validation, independent set of 30 OAI baseline plasma samples (14 progressors, 16 non-progressors)
- AUC
- 0.81 (95% CI 0.63, 0.92)
- Accuracy
- 0.83 (95% CI 0.66, 0.93)
Feature clustering
- miRNAs selected
- 107
- Elastic Net chosen for feature selection
Original publication
MicroRNA signature for early prediction of knee osteoarthritis structural progression using integrated machine and deep learning approaches. Osteoarthritis Cartilage. Published 29 November 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →