Explainable machine learning for orthopedic decision-making: predicting functional outcomes of total hip replacement from gait biomechanics
Authors' conclusion
In conclusion, patients with hip osteoarthritis demonstrate distinct subpopulation-specific gait adaptations, both before and after total hip replacement.
Study context
- Population
- Patients with unilateral hip OA before and after total hip replacement, and healthy controlsthree datasets
- Participants
- 109 / 63 / 56
- Exposure
- Hip OA patients before and after total hip replacement vs healthy controls
- Pre-operativen = 109
- Post-operativen = 63
- Controlsn = 56reference
- Outcome
- Gait-biomechanics subpopulations of hip OA patients and subpopulation-specific effects of total hip replacement on gait
Methodological detailsk-means clustering, support vector machine classifiers, Shapley Additive exPlanations, statistical waveform analyses
- K-means clustering
- Support vector machine classifiers
- Shapley Additive exPlanations
- Statistical waveform analyses
Main finding
As reported in the abstract
| Group | Value | Classified as pathologic (range across subpopulations) |
|---|---|---|
| Pre-operative | 51.4% and 85.2% | between 51.4% and 85.2% |
| Post-operative | 27.8% - 51.8% | 27.8% - 51.8% |
Value
Pre-operative51.4% and 85.2%
Post-operative27.8% - 51.8%
Classified as pathologic (range across subpopulations)
Pre-operativebetween 51.4% and 85.2%
Post-operative27.8% - 51.8%
- Clustering of the pre-operative dataset revealed three distinct subpopulations with unique patterns in gait kinematics and joint moments
- 3
Observational data: associations, not effects.
Original publication
Explainable machine learning for orthopedic decision-making: predicting functional outcomes of total hip replacement from gait biomechanics. Arthritis Res Ther. Published 23 December 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →