Robust Breast Cancer Detection Model Based on Machine Learning

Ruiz R.; Ramos G.; Ticona W. · Lecture Notes in Networks and Systems (2025) · DOI: 10.1007/978-3-031-96798-6_37

Resumen

Breast cancer is one of the most prevalent oncological diseases worldwide, and it has a significant impact on public health and the quality of life of those affected. The objective of this study was to identify the stages of breast cancer using Machine Learning algorithms. The proposed methodology consists of 5 phases: obtaining dataset; preprocessing (One-hot Encoding; Label Encoding; Data Scaling; Data Imputation, Data Balancing and Feature Engineering) and model implementation (SVM, RF, DT, KNN, RL and XGBoost); evaluation (Accuracy, Recall, Precision, F1-Score, Specificity, ROC and Confusion Matrix) and validation. Superior results were obtained with the SVM model, with an Accuracy of 82.72%, Specificity of 85.11%, and the following hyperparameters: C (1), gamma (scale), and kernel (linear). The results demonstrate that it is possible to identify breast cancer stages using Machine Learning models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Instituciones: Universidad ESAN; Universidad Tecnológica del Perú