Norberto Ulises Roman Concha, ULISES CONCHA, RONALD SOLIS, Luis Romero-Untiveros, Ericka Arboleda-Sanchez, Anthony Yucra-Tintaya, Jhair Figueroa-Estrella, Alexander Zavala-Tapia, Luis Soto-Vargas, José Piedra Isusqui, Jeremy Luera-Collazos and Carlos Herrera-Chavez
Adv. Artif. Intell. Mach. Learn., 5 (3):4397-4417
1. Norberto Ulises Roman Concha: National University of San Marcos
2. ULISES CONCHA: Universidad Nacional Mayor de San Marcos
3. RONALD SOLIS: Universidad Privada del Norte
4. Luis Romero-Untiveros: Private University of the North UPN Lima – Perú
5. Ericka Arboleda-Sanchez: Faculty of Systems Engineering and Computer Science UNMSM Lima-Peru
6. Anthony Yucra-Tintaya: Faculty of Systems Engineering and Computer Science UNMSM Lima-Peru
7. Jhair Figueroa-Estrella: Faculty of Systems Engineering and Computer Science UNMSM Lima-Peru
8. Alexander Zavala-Tapia: Faculty of Systems Engineering and Computer Science UNMSM Lima-Peru
9. Luis Soto-Vargas: UNFV Graduate School Lima-Peru
10. José Piedra Isusqui: Faculty of Systems Engineering and Computer Science UNMSM Lima-Peru
11. Jeremy Luera-Collazos: Faculty of Systems Engineering and Computer Science UNMSM Lima-Peru
12. Carlos Herrera-Chavez: Faculty of Systems Engineering and Computer Science UNMSM Lima-Peru
DOI: 10.54364/AAIML.2025.53244
Article History: Received on: 29-Jun-25, Accepted on: 23-Sep-25, Published on: 30-Sep-25
Corresponding Author: Norberto Ulises Roman Concha
Email: nromanc@unmsm.edu.pe
Citation: Ronald Melgarejo-Solis, Ulises Roman-Concha, Luis Romero-Untiveros, Ericka Arboleda-Sanchez, Anthony Yucra-Tintaya, Jhair Figueroa-Estrella, Alexander Zavala-Tapia, Luis Soto-Vargas, José Pied . Application of SVM with Python and Machine Learning for Effective Breast Cancer Detection. Advances in Artificial Intelligence and Machine Learning. 2025;5 (3):244.
This study presents a machine learning- based solution for the early detection of breast cancer using mammographic images. SVM was used in Python, achieving an accurate and robust model thanks to rigorous clinical data preprocessing, cleaning, normalization, and statistical analysis. Cross-validation and data visualization techniques ( boxplots , histograms, correlation matrices) were applied to identify key variables and reduce redundancies. This allowed optimizing the model's performance and improving its predictive capacity. Finally, the model was integrated into a web platform with Django, enabling its practical use in clinical settings. The work demonstrates the effectiveness of data science applied to automated medical diagnosis.