Gait, physical activity, and tibiofemoral cartilage damage: A longitudinal machine learning analysis in the Multicenter Osteoarthritis Study

ABSTRACT Objective To 1) develop and evaluate a machine learning model incorporating gait and physical activity to predict medial tibiofemoral cartilage worsening over two years in individuals without or with early knee osteoarthritis and 2) identify influential predictors in the model and quantify their effect on cartilage worsening. Design An ensemble machine learning model was developed to predict worsened cartilage MRI Osteoarthritis Knee Score at follow-up from gait, physical activity, clinical and demographic data from the Multicenter Osteoarthritis Study. Model performance was evaluated in repeated cross-validations. The top 10 predictors of the outcome across 100 held-out test sets were identified by a variable importance measure statistic, and their marginal effect on the outcome was quantified by g-computation. Results Of 947 legs in the analysis, 14% experienced medial cartilage worsening at follow-up. The median (2.5 th -97.5 th percentile) AUC across the 100 held-out test sets was 0.73 (0.65-0.79). Presence of baseline cartilage damage, higher Kellgren-Lawrence grade, greater pain during walking, higher lateral ground reaction force impulse, greater time spent lying, and lower vertical ground reaction force unloading rate were associated with greater risk of cartilage worsening. Conclusions An ensemble machine learning approach incorporating gait, physical activity, and clinical/demographic features showed good performance for predicting cartilage worsening over two years. While identifying potential intervention targets from the model is challenging, these results suggest that lateral ground reaction force impulse, time spent lying, and vertical ground reaction force unloading rate should be investigated further as potential early intervention targets to reduce medial tibiofemoral cartilage worsening. Summary box What are the findings? Machine learning models predicted cartilage worsening in persons without or with early knee osteoarthritis from gait, physical activity, and clinical and demographic characteristics with a median AUC of 0.73 across 100 held-out test sets. High lateral ground reaction force impulse, more time spent lying, and low vertical ground reaction force unloading rate were associated with increased risk of cartilage worsening over two years. How might it impact on clinical practice in the future? Gait and physical activity are some of the only modifiable risk factors for knee osteoarthritis; this study identified three potential intervention targets to slow early knee osteoarthritis progression.