Precision Medicine–Based Machine Learning Analyses to Explore Optimal Exercise Therapies for Individuals With Knee Osteoarthritis: Random Forest-Informed Tree-Based Learning
Authors' conclusion
These results suggest that easily assessed patient characteristics including age, fear of movement, and BMI could be used to guide patients toward either home-based exercise or PT, though additional studies are needed to confirm these findings.
Study context
- Population
- Participants with knee OA from the Physical Therapy vs Internet-Based Training for Patients with Knee Osteoarthritis trial
- Participants
- 303 participants
- Comparison
- Physical therapy (PT) vs internet-based exercise training (IBET) vs usual care/wait list control
- Primary endpoint
- WOMAC total score
- Follow-up
- 12-month follow-up
Methodological detailsprecision medicine-based machine learning, random forest-informed tree-based learning
- Precision medicine-based machine learning
- Random forest-informed tree-based learning
Primary result
As reported in the abstract
Average WOMAC at 12 months: model-based treatment assignment (6 subgroups by baseline age, BMI, BFOM) vs single best treatment for all
- Assigning treatments according to the models resulted in greater improvements of the average WOMAC than assigning a single best treatment to all patients
- P = 0.01
Original publication
Precision Medicine–Based Machine Learning Analyses to Explore Optimal Exercise Therapies for Individuals With Knee Osteoarthritis: Random Forest-Informed Tree-Based Learning. J Rheumatol. Published 1 August 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →