Application of Machine Learning Algorithms in Breast Cancer Diagnosis and Classification

Area of Science:

• Oncology
• Medical Informatics
• Biostatistics

Background:

• Breast cancer is a leading cause of female cancer deaths globally, despite advances in diagnosis and treatment.
• Accurate differentiation between benign and malignant breast lesions is crucial for effective patient management.
• Machine learning (ML) shows promise for improving the accuracy of breast cancer prediction and diagnosis.

Purpose of the Study:

• To explore the application of ML algorithms for classifying breast cancer.
• To analyze breast mass fine-needle aspiration (FNA) data using ML for diagnostic classification.
• To evaluate the effectiveness of ML in distinguishing benign from malignant breast tumors.

Main Methods:

• Utilized a scientific dataset of 569 breast cancer patients from Kaggle.
• Applied ML algorithms to analyze ten real-valued features from digitized breast mass FNA images.
• Features included radius, texture, perimeter, area, smoothness, compactness, concavity, concave points, symmetry, and fractal dimension.

Main Results:

• The ML models successfully classified breast cancer based on FNA features.
• Out of 569 patients, 63% were diagnosed with benign breast cancer and 37% with malignant breast cancer.
• The analysis demonstrated the capability of ML to differentiate between benign and malignant breast lesions.

Conclusions:

• ML approaches can accurately classify breast cancer using FNA data.
• Feature analysis via ML provides a reliable method for distinguishing benign from malignant breast masses.
• This technology offers a valuable tool to enhance breast cancer diagnosis and patient care.