Breast Cancer Classification using Metaheuristic Optimization and Machine Learning

• Published in: 2024 3rd International Conference on Artificial Intelligence For Internet of Things (AIIoT) pp. 1 - 4
• Main Authors: Chandra, Avinash, Kadam, Ayush Sangram, Jain, Palak, Kumawat, Mohit, Patil, Hemprasad Yashwant, Gawas, Mahadev Anant
• Format: Conference Proceeding
• Language: English
• Published: IEEE 03.05.2024
• Subjects: Accuracy; Ada Boost; Bayes methods; Breast cancer; Classification algorithms; machine learning; Machine learning algorithms; Medical services; naive bayes; Prediction algorithms; random forest
• DOI: 10.1109/AIIoT58432.2024.10574626

This research utilizes advanced machine learning techniques, specifically focusing on Decision Tree, Naive Bayes, Random Forest, and Ada Boost models, to conduct a thorough examination of breast cancer prognosis. Our findings reveal compelling insights into the effectiveness of diverse machine learning models in assessing breast cancer. The Decision Tree model achieves an impressive accuracy of 93.5&, accompanied by a precision rate of 86.73%. The Naive Bayes model demonstrates high accuracy, reaching 95.5%, with a precision of 91.32%. Notably, the Random Forest model stands out with exceptional performance, achieving an impressive accuracy of 98.3% and a precision of 96.5%. The Ada Boost model also proves to be robust, boasting an accuracy of 97.0% and a precision of 93.37%. After performing metahueristic hyperparameter tuning with differential evolution algorithm and derived feature engineering we have achieved accuracy of 98.83% and 98.41% precision. This study serves as a valuable resource for healthcare professionals, researchers, and policymakers, providing essential insights into the strengths and limitations of various machine learning models in the context of breast cancer prognosis.