Improving Breast Cancer Classification Using an Adaptive Voting Ensemble Learning Algorithm

Breast cancer is still one of the leading and most life-threatening diseases in the world for women. Diagnosis of early disease is necessary for improved treatment chances and survival. This paper presents a novel approach to classifying breast cancer based on an adaptive ensemble learning algorithm, which is used to improve prediction accuracy. The proposed methodology combines the strengths of the Decision Tree and Random Forest classifiers to create a more robust and accurate classification model. It uses a weighted voting mechanism that dynamically adjusts the influence of each classifier according to its performance, prioritizing the models that are most accurate for the final prediction. The main objective of this framework is to formulate an accurate and reliable breast cancer classification system to increase diagnostic precision, enable earlier detection, and optimize treatment planning to improve patient outcomes.