Fig. 1

Hyperparameter Optimization Across Different Machine Learning Models. A-D Performance metrics obtained from a 10-fold cross-validation grid search. A K-Nearest Neighbors (KNN) model accuracy as a function of the number of neighbors, with optimal performance at k = 1. B Boosted Logistic Regression model accuracy across boosting iterations, peaking at nIter = 30. C Random Forest model accuracy in relation to the number of randomly selected predictors, optimal at mtry = 6. D Gradient Boosting Machine model accuracy influenced by the number of boosting iterations and maximum tree depth, with the highest accuracy achieved at a depth of 15 and 450 trees. The selection of k = 1 for the KNN model suggests a potential overfitting issue that warrants further evaluation