Araştırma Makalesi

An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction

Cilt: 16 Sayı: 3 30 Ağustos 2026
Şeyma Aymaz *
PDF İndir
Gümüşhane Üniversitesi Fen Bilimleri Dergisi Kapak Gümüşhane Üniversitesi Fen Bilimleri Dergisi
EN

An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction

Öz

Breast cancer recurrence after treatment remains a critical clinical problem that directly affects patient management and survival outcomes. In this study, a machine learning–based classification framework is proposed to predict breast cancer recurrence risk. Experiments were conducted on the Wisconsin Prognostic Breast Cancer and Recurrent Breast Cancer datasets. During the data preprocessing stage, missing values were imputed, categorical variables were transformed into numerical representations, and all features were standardized using z-score normalization. The class imbalance problem was addressed using the Synthetic Minority Over-sampling Technique. To systematically investigate the effect of feature selection on classification performance, several scenarios were evaluated, including no feature selection, embedded feature selection using L1-regularized Logistic Regression, and different metaheuristic optimization-based wrapper feature selection methods. These optimization-based methods included Particle Swarm Optimization, Teaching–Learning-Based Optimization, Whale Optimization Algorithm, Genetic Algorithm, Ant Colony Optimization, and Artificial Bee Colony. The selected feature subsets were evaluated using Support Vector Machine, Random Forest, and Extreme Gradient Boosting classifiers. All experiments were performed using a 10-fold cross-validation strategy, and the Wilcoxon signed-rank test was applied to statistically compare the performance differences among the feature selection methods. The experimental results show that optimization-based feature selection methods can improve classification performance while producing more compact feature subsets. In particular, the Genetic Algorithm-based feature selection approach achieved balanced and competitive results across different datasets and classifiers. The findings indicate that feature selection strategies have an important effect on both model performance and model complexity in breast cancer recurrence prediction. In this regard, the proposed framework provides an applicable and interpretable machine learning–based approach for decision support systems aimed at assessing breast cancer recurrence risk.

Anahtar Kelimeler

Breast cancer recurrence, Machine learning, Optimization

Kaynakça

  1. Abdu-Aljabar, R. D. A., Aljafaara, K. D., Ameen, Z. J. M., & Naman, H. A. (2025). A comparative study of breast cancer detection and recurrence prediction using CatBoost classifier. Acta Polytechnica, 65(2), 136–142. https://doi.org/10.14311/AP.2025.65.0136
  2. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953
  3. El Rahman, S. A. (2021). Predicting breast cancer survivability based on machine learning and feature selection algorithms: A comparative study. Journal of Ambient Intelligence and Humanized Computing, 12(8), 8585–8623.
  4. Gupta, S. R. (2022a). Time based prediction of breast cancer tumor recurrence using machine learning. International Journal of Clinical Biostatistics and Biometrics, 8(1), 046. https://doi.org/10.23937/2469-5831/1510046
  5. Gupta, S. R. (2022b). Prediction time of breast cancer tumor recurrence using machine learning. Cancer Treatment and Research Communications, 32, 100602. https://doi.org/10.1016/j.ctarc.2022.100602
  6. Hasan, R., & Shafi, A. S. M. (2023). Feature selection based breast cancer prediction. International Journal of Image, Graphics and Signal Processing, 15(2), 13–23. https://doi.org/10.5815/ijigsp.2023.02.02
  7. Kumari, D., Naidu, M. V. S. S., Panda, S., & Christopher, J. (2025). Predicting breast cancer recurrence using deep learning. Discover Applied Sciences.
  8. Mikhailova, V., & Anbarjafari, G. (2022). Comparative analysis of classification algorithms on the breast cancer recurrence using machine learning. Medical & Biological Engineering & Computing, 60, 2589–2600. https://doi.org/10.1007/s11517-022-02623-y
  9. Negi, J., & Bansal, K. L. (2021). Comparative analysis of classification algorithms on breast cancer dataset. International Research Journal of Engineering and Technology (IRJET), 8(12), 1125-1127.
  10. Noman, S. M., Fadel, Y. M., Henedak, M. T., Attia, N. A., Essam, M., Elmaasarawii, S., Fouad, F. A., Eltasawi, E. G., & Al-Atabany, W. (2025). Leveraging survival analysis and machine learning for accurate prediction of breast cancer recurrence and metastasis. Scientific Reports, 15(1), 3728. https://doi.org/10.1038/s41598-025-87622-3

Ayrıntılar

Birincil Dil

İngilizce

Konular

Makine Öğrenmesi Algoritmaları, Memnuniyet ve Optimizasyon

Bölüm

Araştırma Makalesi

Yazarlar

Yayımlanma Tarihi

30 Ağustos 2026

Gönderilme Tarihi

19 Şubat 2026

Kabul Tarihi

27 Ağustos 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 16 Sayı: 3

DOI

https://doi.org/10.17714/gumusfenbil.1893178

IZ

https://izlik.org/JA99LC92MR

Kaynak Göster

RIS / Bibtex
APA
Aymaz, Ş. (2026). An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction. Gümüşhane Üniversitesi Fen Bilimleri Dergisi, 16(3), 913-927. https://doi.org/10.17714/gumusfenbil.1893178
AMA
1.Aymaz Ş. An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction. Gümüşhane Üniversitesi Fen Bilimleri Dergisi. 2026;16(3):913-927. doi:10.17714/gumusfenbil.1893178
Chicago
Aymaz, Şeyma. 2026. “An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction”. Gümüşhane Üniversitesi Fen Bilimleri Dergisi 16 (3): 913-27. https://doi.org/10.17714/gumusfenbil.1893178.
EndNote
Aymaz Ş (01 Ağustos 2026) An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction. Gümüşhane Üniversitesi Fen Bilimleri Dergisi 16 3 913–927.
IEEE
[1]Ş. Aymaz, “An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction”, Gümüşhane Üniversitesi Fen Bilimleri Dergisi, c. 16, sy 3, ss. 913–927, Ağu. 2026, doi: 10.17714/gumusfenbil.1893178.
ISNAD
Aymaz, Şeyma. “An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction”. Gümüşhane Üniversitesi Fen Bilimleri Dergisi 16/3 (01 Ağustos 2026): 913-927. https://doi.org/10.17714/gumusfenbil.1893178.
JAMA
1.Aymaz Ş. An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction. Gümüşhane Üniversitesi Fen Bilimleri Dergisi. 2026;16:913–927.
MLA
Aymaz, Şeyma. “An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction”. Gümüşhane Üniversitesi Fen Bilimleri Dergisi, c. 16, sy 3, Ağustos 2026, ss. 913-27, doi:10.17714/gumusfenbil.1893178.
Vancouver
1.Şeyma Aymaz. An ablation analysis of feature selection strategies for machine learning–based breast cancer recurrence prediction. Gümüşhane Üniversitesi Fen Bilimleri Dergisi. 01 Ağustos 2026;16(3):913-27. doi:10.17714/gumusfenbil.1893178

e-ISSN: 2146-538X   Yayın Modeli: Sürekli Yayın   Atıf Dizinleri: TR Dizin , SCOPUS