Skip to main content

Table 4 Multiple Imputation Data

From: Machine learning models predicting risk of revision or secondary knee injury after anterior cruciate ligament reconstruction demonstrate variable discriminatory and accuracy performance: a systematic review

Multiple Imputation Data Set

  

Author

Concordance (95 CI)

Calibration

Martin (2023)

1 year:

Cox Lasso 0.59 (0.56–0.61)

RSF: 0.66 (0.64–0.69)

GB: 0.68 (0.65–0.70)

SL: 0.67 (0.65–0.70)

2 year:

Cox Lasso 0.59 (0.56–0.61)

RSF: 0.67 (0.65–0.70)

GB: 0.67 (0.65–0.70)

SL: 0.67 (0.65–0.70)

5 year:

Cox Lasso 0.58 (0.56–0.61)

RSF: 0.67 (0.65–0.70)

GB: 0.67 (0.65–0.69)

SL: 0.67 (0.65–0.70)

1 year:

Cox Lasso 8.35, p = 0.039

RSF:4.17, p = 0.244

GB: 7.57, p = 0.056

SL: 7.99, p = 0.046

2 year:

Cox Lasso 8.81, p = 0.032

RSF: 8.96, p = 0.030

GB: 8.98, p = 0.030

SL: 8.34, p = 0.039

5 year:

Cox Lasso: 8.30, p = 0.040

RSF: 8.95, p = 0.030

GB: 11.53, p = 0.009

SL: 14.05, p = 0.003

Original Data Set

  

Martin (2023)

1 year:

Cox Lasso 0.59 (0.56–0.61)

RSF: 0.67 (0.64–0.69)

GB: 0.67 (0.65–0.70)

SL: 0.67 (0.65–0.69)

2 year:

Cox Lasso 0.58 (0.56–0.61)

RSF: 0.67 (0.64–0.69)

GB: 0.67 (0.64–0.69)

SL: 0.67 (0.64–0.69)

5 year:

Cox Lasso 0.58 (0.56–0.61)

RSF: 0.67 (0.65–0.69)

GB: 0.67 (0.64–0.69)

SL: 0.67 (0.64–0.69)

1 year:

Cox Lasso 7.19, n.s

RSF: 5.54, n.s

GB: 7.48, n.s

SL: 8.67, p = 0.034

2 year:

Cox Lasso 8.17, p = 0.043

RSF: 6.42, n.s

GB: 4.53, n.s

SL: 4.10, n.s

5 year:

Cox Lasso: 11.37, p = 0.01

RSF: 9.27, p = 0.026

GB: 11.07, p = 0.011

SL: 11.82, p = 0.008

  1. KOOS: knee osteoarthritis and outcome score, CI: confidence interval, GB: gradient boosted regression model, RSF: random survival forest, SL: super learner, GAM: generalized additive model, n.s: not significant