Comparative Analysis of Machine Learning Methods for Breast Cancer Classification in Genetic Sequences

Area of Science:

• Oncology
• Medical Informatics
• Computational Biology

Background:

• Breast cancer is a leading cause of cancer deaths globally, necessitating advancements in early detection and diagnosis.
• Accurate classification of benign and malignant tumors is crucial for effective patient management and treatment strategies.
• Machine learning (ML) offers powerful tools for analyzing complex biological data and improving cancer prediction.

Purpose of the Study:

• To conduct a comparative analysis of four ML classifiers for breast cancer diagnosis.
• To identify the most efficient ML model for distinguishing between benign and malignant breast tumors.
• To enhance the accuracy and reliability of breast cancer detection systems.

Main Methods:

• Utilized NCBI datasets for training and evaluating ML models.
• Implemented and compared four ML classifiers: Random Forest, Decision Tree, AdaBoost, and Gradient Boosting.
• Performed rigorous performance evaluation to determine the optimal classifier.

Main Results:

• Gradient Boosting demonstrated superior performance compared to other evaluated models.
• Achieved a classification accuracy of 95.82% using the Gradient Boosting model.
• Comparative analysis highlighted the strengths and weaknesses of each ML approach for this task.

Conclusions:

• Gradient Boosting is the most effective ML model for accurate breast cancer tumor classification among the tested algorithms.
• The findings support the integration of advanced ML techniques into diagnostic workflows for improved breast cancer care.
• Further research can explore ensemble methods and feature engineering to optimize diagnostic accuracy.