Performance of the baseline model across five cross-validation folds (I-V). Reported metrics are Accuracy, Balanced Accuracy, Recall (TPR), Specificity (TNR), Precision (PPV), NPV, F1-Score, and Cohen’s Kappa. The averages of each metric are shown in the last column. Results indicate consistent performance across folds, with average accuracy of 72.4 % and strong specificity (96.8 %). This reflects robustness of the model but also highlights limited sensitivity compared to specificity.

Performance of the baseline model across five cross-validation folds (I-V). Reported metrics are Accuracy, Balanced Accuracy, Recall (TPR), Specificity (TNR), Precision (PPV), NPV, F1-Score, and Cohen’s Kappa. The averages of each metric are shown in the last column. Results indicate consistent performance across folds, with average accuracy of 72.4 % and strong specificity (96.8 %). This reflects robustness of the model but also highlights limited sensitivity compared to specificity.