Applying an Optimal Feature Ranking and Selection Algorithm and Random Forest Classifier Algorithm along with K-Fold Cross validation for Classification of Blood Cancer Cells
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 11, Pages 774-789
AbstractTechnological inventions and researches have pushed various emerging fields to overwhelm information technology and its applications. Bioinformatics, medicines and drug discovery have found significance use of Artificial intelligence for aiding in various discoveries and patient centered care. One of the most critical area of medical concern is blood cancer that has limitations in detection and classification at a proper stage. By applying artificial intelligence techniques to the blood genetics, physicians and oncologists all over the world could find a solution for early detection and classification of the disease. Susceptibility, recurrence and survival rates of cancer are questions to be answered while detecting and classifying stages of cancer. Artificial intelligence techniques and models proposed by researchers for characterizing various stages of blood cancer have aided in providing treatment to certain extend. Applying artificial intelligence framework models on genetics has been found to provide results that satisfies the detection of the disease. However, an efficient methodology that focuses of selecting particular features of blood cancer and ranking these features and then classifying them into various stages is still lacking. This research focuses of using an optimal feature selection and ranking algorithm for ranking and selecting features and then employing random forest algorithm for classifying the blood cancer stages in the blood sample. This technique allows to provide better patient centered care and early classification of cancer stages.
- Article View: 15
- PDF Download: 35