Deep longitudinal centile features
Biomarker1 paper1 finding
- In silico1
Associations
1Incident radiographic knee osteoarthritis
upin humans1
1 study
Incident radiographic knee osteoarthritis
upin humans1
Deep longitudinal centile features predict incident radiographic knee osteoarthritis in humans (AUC 0.954 (95% CI 0.931–0.974); balanced accuracy 0.917).
“Deep centile features achieved the best AUCs (0.954 [95% CI 0.931-0.974] at 12 months and 0.969 [0.949-0.985] at 24 months; balanced accuracy 0.917 and 0.931)”
HumansParticipant-separated nested cross-validationknee cartilage12 months
Tracking knee cartilage improved osteoarthritis prediction · bioRxiv · 8 Oct 2026 · Preprint
Latest
1bioRxivIn silicoPreprint
Tracking knee cartilage improved osteoarthritis prediction
Prediction scores reached 0.954 at 12 months and 0.969 at 24 months, outperforming features from unadjusted cartilage maps.Prediction scores reached 0.954 at 12 months and 0.969 at 24 months, outperforming features from unadjusted cartilage maps.