Association of Machine Learning–Based Predictions of Medial Knee Contact Force With Cartilage Loss Over 2.5 Years in Knee Osteoarthritis
Bibliographic record
Abstract
Objective The relationship between in vivo knee load predictions and longitudinal cartilage changes has not been investigated. We undertook this study to develop an equation to predict the medial tibiofemoral contact force (MCF) peak during walking in persons with instrumented knee implants, and to apply this equation to determine the relationship between the predicted MCF peak and cartilage loss in patients with knee osteoarthritis (OA). Methods In adults with knee OA (39 women, 8 men; mean ± SD age 61.1 ± 6.8 years), baseline biomechanical gait analyses were performed, and annualized change in medial tibial cartilage volume (mm 3 /year) over 2.5 years was determined using magnetic resonance imaging. In a separate sample of patients with force‐measuring tibial prostheses (3 women, 6 men; mean ± SD age 70.3 ± 5.2 years), gait data plus in vivo knee loads were used to develop an equation to predict the MCF peak using machine learning. This equation was then applied to the knee OA group, and the relationship between the predicted MCF peak and annualized cartilage volume change was determined. Results The MCF peak was best predicted using gait speed, the knee adduction moment peak, and the vertical knee reaction force peak (root mean square error 132.88N; R 2 = 0.81, P < 0.001). In participants with knee OA, the predicted MCF peak was related to cartilage volume change (R 2 = 0.35, β = −0.119, P < 0.001). Conclusion Machine learning was used to develop a novel equation for predicting the MCF peak from external biomechanical parameters. The predicted MCF peak was positively related to medial tibial cartilage volume loss in patients with knee OA.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".