Development of Explainable Machine Learning Models to Predict Outcomes After Platelet-Rich Plasma Injections for Knee Osteoarthritis
ML models effectively predicted a clinically meaningful improvement at 6 months after PRP injection for knee osteoarthritis. The EBM was the algorithm with the best performance, with the PROMIS Mental and Physical scores and the KOOS Jr score being the most influential predictors. Additional independent studies are needed to externally validate this model.
Authors
- Antonio Ibarra (ORCID: https://orcid.org/0000-0003-2489-4689)
- Mark Alan Fontana (ORCID: https://orcid.org/0000-0002-0529-9035)
- Jessica Andres Bergos
- Miguel Otero (ORCID: https://orcid.org/0000-0002-4945-2994)
- Scott Alan Rodeo (ORCID: https://orcid.org/0000-0002-0745-9880)
- Brian Halpern
- Mert Marcel Dagli (ORCID: https://orcid.org/0000-0002-5201-6720)
- Felix Conrad Oettl (ORCID: https://orcid.org/0000-0001-9721-685X)
- Ophelie Loblack
Institutions
- Hospital for Special Surgery (US)
- University of Pennsylvania (US)
Publication Details
- Journal
- Orthopaedic Journal of Sports Medicine
- Published
- 2025-08-01
- DOI
- https://doi.org/10.1177/23259671251349743
- Citations
- 1
- Primary Topic
- Periodontal Regeneration and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 1.84