Year: 2025
Type: article
Abstract: Cancer mortality remains a significant challenge in developing nations, despite various preventive measures. Some cancer types still lack effective treatments. Breast cancer, one of the most prevalent forms, relies heavily on early detection for successful treatment. Accurate diagnosis plays a crucial role in managing breast cancer. Numerous studies have explored methods for predicting breast tumor types. This study utilized breast cancer tumor data from Kaggle datasets forecast tumor types. The research employed data visualization and machine learning techniques, including logistic regression and Python were used to implement these techniques and visualizations. The research aimed to conduct a comparative analysis of data visualization and machine learning applications for breast cancer detection and diagnosis. The diagnostic performance of these applications was found to be comparable in identifying breast cancers. The study demonstrated that data visualization and machine learning techniques could significantly benefit the decision-making process in cancer detection. Various machine learning and data mining techniques were proposed for breast cancer detection. The logistic regression model, incorporating all features, yielded the highest classification accuracy at 98.1%. This approach showed improved accuracy performance, suggesting potential new avenues for breast cancer detection.
Authors: Md. Shahbaz Hassan, Rishabh Kumar, Rohit Yadav
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4409617026