Table 3.

Detailed performance metrics for the Multi-Layer Perceptron (MLP) model trained with the SMOTE dataset.

Measurement	Value	Derivation
Sensitivity	0.9182	TPR = TP/(TP + FN)
Specificity	0.7436	SPC = TN/(FP + TN)
Precision	0.7710	PPV = TP/(TP + FP)
Negative Predictive Value	0.9063	NPV = TN/(TN + FN)
False Positive Rate	0.2564	FPR = FP/(FP + TN)
False Discovery Rate	0.2290	FDR = FP/(FP + TP)
False Negative Rate	0.0818	FNR = FN/(FN + TP)
Accuracy	0.8382	ACC = (TP + TN)/(P + N)
F1-Score	0.8382	F1 = 2TP/(2TP + FP + FN)
Matthews Correlation Coefficient	0.6695	TP × TN − FP×FN/sqrt((TP + FP) × (TP + FN) × (TN + FP) × (TN + FN))

This table comprehensively evaluates the MLP model’s performance across multiple metrics, including sensitivity, specificity, precision, and accuracy. TP = true positive, TN = true negative, FP = false positive, FN = false negative.