EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

The Impact of Scaling Techniques on Breast Cancer Prediction Algorithms

Oluwaseyi Ezekiel Olorunshola, Okeh Dominic Ebuka, Adeniran Kolade Ademuwagun, Fatimah Adamu-Fika, Muhammad Abdullahi Kabir

Journal of Computing and Social Informatics · 04.05.2025 · 4 (2) · 17-27

DOI: 10.33736/jcsi.8449.2025 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computing and Social Informatics, online erschienen am 04.05.2025. Verfasst von Oluwaseyi Ezekiel Olorunshola und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Breast cancer develops when the genetic material of breast cells undergoes mutations, causing the cells to grow uncontrollably and form tumors. Efforts however have been made to combat it by developing machine learning models to help clinicians with early detection. This study investigates the impact of scaling techniques on the performance of algorithms used for breast cancer prediction. Two scaling approaches were compared with models utilizing the raw, unscaled data. The result revealed that the different scaling techniques had minimal effect on the prediction performance after Hyperparameter tuning. This suggests that for the specific dataset and algorithms used, potential sources of bias were analyzed and the classifiers adapted their internal parameters to compensate for the difference in feature scaling. The model's performance was evaluated using four metrics which are Accuracy, Recall, Precision, and F1-score through the 5-fold cross-validation. The results of this study showed that the Random Forest an ensemble model outperformed all other individual classifier after hyperparameter tuning was performed, it had an Accuracy value of 0.9578, a Recall value of 0.9297, a Precision of 0.9571, and an F1-score of 0.9425.

Zitieren

APA

Olorunshola, O. E., Ebuka, O. D., Ademuwagun, A. K., Adamu-Fika, F., & Kabir, M. A. (2025). The Impact of Scaling Techniques on Breast Cancer Prediction Algorithms. Journal of Computing and Social Informatics, 4(2), 17-27. https://doi.org/10.33736/jcsi.8449.2025

Vancouver

Olorunshola OE, Ebuka OD, Ademuwagun AK, Adamu-Fika F, Kabir MA. The Impact of Scaling Techniques on Breast Cancer Prediction Algorithms. Journal of Computing and Social Informatics. 2025;4(2):17-27. doi:10.33736/jcsi.8449.2025

BibTeX
@article{Olorunshola2025,
  author = {Olorunshola, Oluwaseyi Ezekiel and Ebuka, Okeh Dominic and Ademuwagun, Adeniran Kolade and Adamu-Fika, Fatimah and Kabir, Muhammad Abdullahi},
  title = {The Impact of Scaling Techniques on Breast Cancer Prediction Algorithms},
  journal = {Journal of Computing and Social Informatics},
  year = {2025},
  volume = {4},
  number = {2},
  pages = {17--27},
  doi = {10.33736/jcsi.8449.2025}
}
Kostenlos starten →