Algorithm 1 MHA-Based Optimization for Each Training Fold Using RF Hyperparameters

1:Initialize Metaheuristic Optimization   2:Step 1: Define Search Space ($\mathcal{D}$)   3:     Hyperparameter ranges for Random Forest:   4:        ${\varphi }_1$: Number of estimators (n_estimators): 100 to 300   5:        ${\varphi }_2$: Maximum tree depth (max_depth): 3 to 10   6:        ${\varphi }_3$: Minimum samples split (min_samples_split): 2 to 20   7:        ${\varphi }_4$: Minimum samples leaf (min_samples_leaf): 1 to 10   8:        ${\varphi }_5$: Number of selected features: 1 to 38   9:     Set population size = 50 and number of iterations = 100 10:Step 2: Metaheuristic Search Process 11:for $g=1$ to 100 do 12:        Select feature subset ${\mathcal{X}}_g$ 13:        Generate parameter set ${\mathit{\varphi }}_g=\{{\varphi }_1^g,{\varphi }_2^g,{\varphi }_3^g,{\varphi }_4^g\}$ 14:        Train Random Forest using ${\mathcal{X}}_g$ and ${\mathit{\varphi }}_g$ 15:        Compute fitness using F1-score: ${\eta }_g$ 16:end for 17:Step 3: Identify Global Optimum 18:     Find best fitness: ${\eta }^{*}=max\{{\eta }_1,{\eta }_2,\dots ,{\eta }_{50}\}$ 19:     Extract optimal feature subset ${\mathcal{X}}^{*}$ and parameters ${\mathit{\varphi }}^{*}$ 20:End of Optimization