Algorithm 2 Logistic regression Algorithm to differentiate Benign or Malignant tumor

1:Identification: Disease 2:Data-set: WBCD from Kaggle 3:D ← Dataset (699 entries) 4:Input: Training set $\left\{\left({\mathbf{x}}_1,y_1\right),\dots ,\left({\mathbf{x}}_m,y_m\right)\mid \right.$, learning rate $\eta >0$, maximum number of iterations T, initial hyper-plane ${\mathbf{w}}_1$, initial bias $b_1$ 5:Set ${\tilde{w}}_1=\left[\begin{array}{c}{b}_1{w}_1\hfill \end{array}\right]\in {\mathbb{R}}^{d+1}$ 6:Construct augmented training features: ${\tilde{x}}_1,\dots ,{\overline{x}}_m$ 7:for  $t=1,2,\dots ,T$  do 8:   Calculate value of objective function: $ob{j}_t={\sum }_{i=11}^{m}ln\left(1+exp\left(-y_i{\tilde{w}}_t^{\top }{\overline{x}}_i\right)\right)$ 9:   Compute gradient: ${\tilde{\mathbf{g}}}_t=-{\sum }_{i=1}^m\frac{y_i}{1+exp\left({\underset{\_}{x}}_i,{\overline{x}}_i\right)}\in {\mathbb{R}}^{d+1}$ 10:   Gradient descent step: ${\tilde{w}}_{t+1}={\tilde{w}}_t-\eta {\overrightarrow{g}}_t$ 11:end for 12:return Output: Extract $w_{T+1}$ and $b_{T+1}$ from ${\overline{\mathbf{w}}}_{T+1}$ and return them