An Optimized Diagnostic Precision Using Genetic Algorithm in Breast Cancer

The machine learning-based optimization is the most popular research nowadays which provides the best solution among set of all possible solutions. Breast cancer stands as frequent noticed cancer and a primary reason for demise of women on a global scale. The analysis delves into the efficacy of genetic algorithms (GAs) for feature selection, presenting compelling results from our proposed model. Comprehensive evaluations utilizing various GA-based classifiers including the Random Forest, Logistic, K-nearest neighbors, Linear SVM, Gradient Boosting,Radial SVM, AdaBoost, and Decision Tree classifier were performed to assess their effectiveness in feature selection for breast cancer diagnosis. The experimental outcomes highlight a substantial improvement in the classifier’s accuracy score following feature selection. Notably, this enhancement extends to both specificity and sensitivity, affirming the potential of our methodology to significantly elevate the accuracy of breast cancer diagnosis. The accuracy of the Random Forest classifier is 97.2%, which is the finest precision obtained by the GA-based classifier. This research paper contributes valuable insights into the application of genetic algorithms for feature selection and their impact on refining diagnostic outcomes in breast cancer.