Table 2 Performance of the models on training data with cross-validation
Indication | Model | Mean absolute percentage error (%) | Root mean squared error (min) | Mean absolute error (min) |
|---|---|---|---|---|
Hip (n = 1,578) | XGBoost | 22.55 (21.60-23.52) | 17.53 (16.64–18.46) | 12.60 (12.10-13.11) |
Linear multivariable regression | 24.56 (23.50-25.66) | 18.52 (17.56–19.50) | 13.26 (12.72–13.81) | |
Knee (n = 1,200) | XGBoost | 20.94 (20.07–21.84) | 18.04 (17.11-19.00) | 13.21 (12.64–13.79) |
Linear multivariable regression | 22.96 (21.92–24.04) | 19.24 (18.19–20.34) | 14.05 (13.43–14.67) |