Adaptive Dynamic Dipper Throated Optimization for Feature Selection in Medical Data

The rapid population growth results in a crucial problem in the early detection of diseases in medical research. Among all the cancers unveiled, breast cancer is considered the second most severe cancer. Consequently, an exponential rising in death cases incurred by breast cancer is expected due to the rapid population growth and the lack of resources required for performing medical diagnoses. Utilizing recent advances in machine learning could help medical staff in diagnosing diseases as they offer effective, reliable, and rapid responses, which could help in decreasing the death risk. In this paper, we propose a new algorithm for feature selection based on a hybrid between powerful and recently emerged optimizers, namely, guided whale and dipper throated optimizers. The proposed algorithm is evaluated using four publicly available breast cancer datasets. The evaluation results show the effectiveness of the proposed approach from the accuracy and speed perspectives. To prove the superiority of the proposed algorithm, a set of competing feature selection algorithms were incorporated into the conducted experiments. In addition, a group of statistical analysis experiments was conducted to emphasize the superiority and stability of the proposed algorithm. The best-achieved breast cancer prediction average accuracy based on the proposed algorithm is 99.453%. This result is achieved in an average time of 3.6725 s, the best result among all the competing approaches utilized in the experiments.