Abstract
The issue of class imbalance in medical data poses a significant challenge for developing robust machine learning models aimed at medical diagnosis. A characteristic feature of such data is the substantial dominance of instances belonging to majority classes (e.g., healthy patients or those with common diseases) over instances representing rare conditions. This disproportion leads to machine learning models trained on such data being prone to systematic classification errors, predominantly predicting the most frequent class. Consequently, the ability of models to accurately identify rare cases is severely diminished. This paper proposes a hybrid class-balancing algorithm that combines Inverse Quadratic Radial Undersampling (IQRBU) and genetic oversampling to address this issue. The integration of these two methods within a single algorithm achieves an optimal balance between preserving information and enhancing the representation of rare classes. Experimental results conducted on several medical datasets demonstrated the effectiveness of the proposed approach. The obtained results showed that the hybrid algorithm significantly improves classification metrics, such as the F1-score and accuracy. These findings underscore the potential of our approach to enhance the reliability and precision of medical diagnostic systems.