DEVELOPMENT OF MACHINE LEARNING MODEL FOR PREDICTION OF BREAST CANCER

Breast cancer is one of the most prevalent and life-threatening diseases affecting women worldwide. Early detection is crucial for improving survival rates and reducing the severity of treatment. In recent years, machine learning has emerged as a powerful tool in medical diagnostics, offering high accuracy and efficiency in disease prediction. This project focuses on the development and deployment of a machine learning model for breast cancer prediction using the Random Forest algorithm. The study utilizes the Wisconsin Breast Cancer Dataset (WBCD), a publicly available dataset comprising 569 instances, each characterized by 30 numerical features extracted from digitized images of fine needle aspirate (FNA) of breast masses. The dataset includes labeled outcomes-benign or malignant-enabling supervised learning. Data preprocessing involved cleaning, label encoding, feature scaling, and splitting the dataset into training and testing subsets in an 80:20 ratio. Exploratory Data Analysis (EDA) was conducted to identify significant patterns, feature correlations, and class distributions. Visualizations such as heatmaps, histograms, and boxplots helped in understanding feature behavior and separability. Feature importance analysis using the trained Random Forest model highlighted variables such as worst concavity, mean radius, and mean area as key indicators of malignancy. The Random Forest classifier was selected for its robustness, interpretability, and high performance in non-linear classification tasks. Hyperparameter tuning was performed using GridSearchCV with cross-validation, yielding an optimal model configuration. Evaluation metrics showed excellent results, including an accuracy of over 96%, high precision and recall, and a ROC-AUC score of 0.99. Finally, the model was deployed through a user-friendly web application built with Streamlit, allowing real-time predictions via manual input or CSV upload. This system demonstrates the potential of machine learning in supporting clinical decision-making and highlights its applicability in early breast cancer detection. Keywords: development, machine learning, model, prediction, breast, cancer