Predicting target lesion failure following percutaneous coronary intervention through machine learning risk assessment models

Figures

• 

  Figure 1. Receiver operating characteristic curves and performance metrics on test sets. AUC, area under the curve; GBC, gradient boosting classifier; LDA, linear discriminant analysis; LR, logistic regression; NB, Naïve Bayes; KNN, K-nearest neighbours; ROC, receiver operating characteristic; TLF1Y, target lesion failure at 1-year follow-up.

• 

  Figure 2. Probability calibration curves on the test set. GBC, gradient boosting classifier; LDA, linear discriminant analysis; LR, logistic regression; NB, Naïve Bayes; KNN, K-nearest neighbours; TLF1Y, target lesion failure at 1-year follow-up.

• 

  Figure 3. Predicted vs. observed frequency of events per risk deciles. Decile 1 represents 10% of the population with the lowest predicted risk score, Decile 10 represents 10% of the population with the highest predicted risk score. GBC, gradient boosting classifier; LDA, linear discriminant analysis; LR, logistic regression; NB, Naïve Bayes; KNN, K-nearest neighbours; TLF1Y, target lesion failure at 1-year follow-up.