HYBRIDIZED GENETIC ALGORITHM IN PREDICTIVE MODELS OF BREAST CANCER TUMORS

Abstract

Breast cancer is a prevalent and highly lethal illness that primarily affects women. In order for early diagnosis and treatment to be effective, it is necessary to have dependable predictive models. Several hybridized genetic algorithms (HGAs) are evaluated in models for predicting the development of breast cancer. Logistic regression, decision trees, and support vector machines are more often utilized prediction models compared to mixed genetic algorithms. The mixed genetic algorithm combines genetic algorithms with other methods that improve performance. The study centers on the computational efficacy, sensitivity, specificity, and accuracy. The study discovered that employing High-Grade Algorithms (HGAs) with a substantial dataset enhances the accuracy and durability of the breast cancer tumor classification model. According to the study, the implementation of HGAs has the potential to enhance predictive analytics and medical diagnosing tools. Further research on incorporating other data sources and utilizing high-dimensional genomic analyses (HGAs) for various types of cancer will authenticate and enhance the importance of these intricate algorithms in medical diagnosis.