A Comparative Analysis of Hybridized Genetic Algorithm in Predictive Models of Breast Cancer Tumors

Advancement in computer-aided tools towards accurate breast cancer early prediction models has proven to be advantageous, which in turn helps to reduce the mortality rate associated with this cancer. From the literature, random forest predictor has been observed to have high accuracy in comparison to other machine learning regressors, also genetic algorithm has been observed to be a good feature selection method in data pre-processing. In a bid to improve the accuracy of breast cancer predictive models, several studies have developed hybridized genetic algorithm models for feature selection, however, the order of hybridization may not have been taken into consideration, as this can have an impact on the hybridized model’s performance. Therefore, this paper proposes several high-performing predictive models using hybridized genetic algorithm, based on other learning models, while taking into consideration the placement order of the feature selection algorithms in the hybridized models. The Wisconsin Breast Cancer dataset was used as the test bench, while filter, wrapper and embedded feature selection algorithms were used in the proposed hybridized models. The performances of proposed hybridized models were compared with those of the individual learning models, considered in this work. These models include Fisher_Score, Mutual Information Gain, Correlation Chi-square test, Coefficient, Variance, Genetic Algorithm, Lasso and Linear Regressors with L1 regularization, Ridge Regressor with L2 regularization, Tree-based methods. From the performance evaluation results, the proposed hybridized Genetic Algorithm with Fisher_Score (GA + Fisher_Score) model showed promising results, as it had an accuracy score of 99.12%, thereby out-performing other proposed hybridized genetic algorithm models considered.