Classification of Breast Cancer with Implementation of Principal Component Analysis Techniques

Breast cancer is one of the leading causes of mortality in women worldwide, underscoring the importance of implementing accurate and efficient diagnostic tools. This study evaluated the performance of several machine learning algorithms for breast tumor classification using the Wisconsin Breast Cancer Dataset. Principal Component Analysis (PCA) was applied to reduce the dimensionality of the dataset, improving computational efficiency while maintaining critical information for classification. The models evaluated included Logistic Regression, Support Vector Machines (SVM), Neural Networks, reaching maximum AUC-ROC values of 0.96, 0.95 and 0.99, respectively. The results were compared with previous studies, evidence of the robustness and applicability of the proposed approach. Although the findings are promising, the study acknowledges limitations, such as the use of a single dataset, and suggests integrating additional clinical features in future research. This work demonstrates the ability of machine learning to improve early diagnosis of breast cancer, with potential for applications in clinical settings.

• Yazar: León-Alarcón, José (author)
• Diğer Yazarlar: Cedeño-Menéndez, Roly (author)
• Materyal Türü: article
• Dil: spa
• Baskı/Yayın Bilgisi: 2026
• Konular: procesamientos de datos; cáncer; inteligencia artificial; aplicación informática; data processing; cancer; artificial intelligence; computer applications
• Online Erişim: https://revistadigital.uce.edu.ec/index.php/INGENIO/article/view/8194