A hybrid sampling combining Smote and Random Forest algorithm for cancer chemotherapy regimen Classification: A Case of Moroccan breast cancer patients.

Breast cancer causes the highest number of deaths weekly. It is the most common type of cancer and the leading cause of death in women in the world. Deep learning and machine learning are a way to predict perfect therapeutic protocols for patients. This paper presents different models to perform the prediction of breast cancer chemotherapy protocol and the number of cycles of cure using deep learning and machine learning algorithms. The database of therapeutic protocols related to 600 patients with breast cancer pathology was constructed at the University Hospital Center of Marrakesh, Morocco, it was treated following three distinct procedures before being used. In the first procedure, even though it is imbalanced, the database was left as it was. In the second procedure, the database was divided into three equal classes of 200 samples (Three balanced classes). As for the third, a database augmentation was realized, so that the minority classes have the same number of samples as the majority classes to have a balanced database. The main objective is to determine with our restricted database that we have collected since 2018, the best algorithm for the prediction of the therapeutic protocol and number of cycles, in accuracy terms, balanced accuracy, time, and precision. The results show that machine learning algorithms, especially Random Forest and XGBoost gave the best scores when the database was amplified. [ABSTRACT FROM AUTHOR]