A hybrid sampling combining Smote and RF algorithm for cancer chemotherapy protocols Classification

Case of Moroccan Breast Cancer

  • Houda AIT BRAHIM
  • Oumayma BANOUAR
  • Salah EL-HADAJ
  • Abdelmoutalib METRANE
DOI: https://doi.org/10.19139/soic-2310-5070-1941

Abstract

Breast Cancer (BC) is a network of cells that grow abnormally in the breast. If BC is not properly treated with the appropriate cancer chemotherapy protocols, it is at risk of causing death. This research aimed to combine Synthetic Minority Over-sampling (Smote) and Random Forest (RF) methods for BC chemotherapy protocols classification. Smote was used to balance the data, while RF was used to classify chemotherapy protocols data. The real data was produced by collecting medical and personal data from 601 patients with BC at the University Hospital Center (UHC) Mohammed VI of Marrakech in Morocco. Data of women diagnosed with BC from January 2018 at UHC were assessed. The results showed that the use of Smote for data augmentation can increase the performance of the RF classification method based on accuracy. There was an increase of 26% in accuracy. Time is an hyperparameter to be improved.
Published
2024-02-21
How to Cite
AIT BRAHIM, H., BANOUAR, O., EL-HADAJ, S., & METRANE, A. (2024). A hybrid sampling combining Smote and RF algorithm for cancer chemotherapy protocols Classification. Statistics, Optimization & Information Computing, 12(3), 617-629. https://doi.org/10.19139/soic-2310-5070-1941
Issue
Vol 12 No 3 (2024): ICECS’23
Section
Research Articles
Authors who publish with this journal agree to the following terms:

    1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
    2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
    3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).