RESUMEN
The growth of abnormal cells in the brain causes human brain tumors. Identifying the type of tumor is crucial for the prognosis and treatment of the patient. Data from cancer microarrays typically include fewer samples with many gene expression levels as features, reflecting the curse of dimensionality and making classifying data from microarrays challenging. In most of the examined studies, cancer classification (Malignant and benign) accuracy was examined without disclosing biological information related to the classification process. A new approach was proposed to bridge the gap between cancer classification and the interpretation of the biological studies of the genes implicated in cancer. This study aims to develop a new hybrid model for cancer classification (by using feature selection mRMRe as a key step to improve the performance of classification methods and a distributed hyperparameter optimization for gradient boosting ensemble methods). To evaluate the proposed method, NB, RF, and SVM classifiers have been chosen. In terms of the AUC, sensitivity, and specificity, the optimized CatBoost classifier performed better than the optimized XGBoost in cross-validation 5, 6, 8, and 10. With an accuracy of 0.91±0.12, the optimized CatBoost classifier is more accurate than the CatBoost classifier without optimization, which is 0.81± 0.24. By using hybrid algorithms, SVM, RF, and NB automatically become more accurate. Furthermore, in terms of accuracy, SVM and RF (0.97±0.08) achieve equivalent and higher classification accuracy than NB (0.91±0.12). The findings of relevant biomedical studies confirm the findings of the selected genes.
RESUMEN
Cancer can be considered as one of the leading causes of death widely. One of the most effective tools to be able to handle cancer diagnosis, prognosis, and treatment is by using expression profiling technique which is based on microarray gene. For each data point (sample), gene data expression usually receives tens of thousands of genes. As a result, this data is large-scale, high-dimensional, and highly redundant. The classification of gene expression profiles is considered to be a (NP)-Hard problem. Feature (gene) selection is one of the most effective methods to handle this problem. A hybrid cancer classification approach is presented in this paper, and several machine learning techniques were used in the hybrid model: Pearson's correlation coefficient as a correlation-based feature selector and reducer, a Decision Tree classifier that is easy to interpret and does not require a parameter, and Grid Search CV (cross-validation) to optimize the maximum depth hyperparameter. Seven standard microarray cancer datasets are used to evaluate our model. To identify which features are the most informative and relative using the proposed model, various performance measurements are employed, including classification accuracy, specificity, sensitivity, F1-score, and AUC. The suggested strategy greatly decreases the number of genes required for classification, selects the most informative features, and increases classification accuracy, according to the results.