An Intelligent Model for prediction of Breast Cancer applying Ant Colony Optimization

ABSTRACT: Breast cancer remains the most prevalent cancer among women, necessitating early and accurate detection to mitigate progression and improve outcomes. Machine learning (ML) techniques are particularly promising for analyzing vast datasets and identifying potential cases. This paper introduces an ML-based model for breast cancer prediction, leveraging classifiers such as K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest, Gradient Boosting, and XGBoost. To boost the models' accuracy, Ant Colony Optimization (ACO) was applied to optimize hyperparameters. Feature selection was conducted using the SelectKBest method, enhancing model precision and reducing computation. The dataset, sourced from the UCI Machine Learning Repository, facilitated robust model training. Notably, the highest prediction accuracy achieved by this approach is 99%, with the Random Forest classifier optimized through ACO. The dataset consisting of thirty neumeric features. This research highlights the potential of integrating ML and optimization techniques to enhance disease prediction capabilities by early prediction of disease in turn a better patient outcome.