An expert system for detection of leukemia based on cooperative game theory

• Main Authors: Torkaman, A., Charkari, N.M., Pour, M.A., Bahrololum, M., Hajati, E.
• Format: Conference Proceeding
• Language: English
• Subjects: Blood; Bones; Cancer; Cells (biology); Diagnostic expert systems; Expert systems; Feedforward neural networks; Game theory; Neural networks; Power system modeling
• ISSN: 2160-6986; 2160-7028
• DOI: 10.1109/NEBC.2009.4967832

Leukemia is very common and serious cancer starts in blood tissue such as the bone marrow. It causes large numbers of abnormal blood cells to be produced and enter the blood. Emphasis on diagnostic techniques and best treatments would be able to decrease the mortality rate from leukemia. This paper presents an automatic diagnosis system for classifying leukemia based on cooperative Game. In this study, cooperative game is used for classification according to different weights and power assigned to the markers. The modeling system described is versatile as there are no restrictions to what the input or output represent. This means that it can be used to model any situation and classify a population according to their contributions. In the other words, it applies equally to other groups of data. The results show that the highest classification accuracy (98.44%) is obtained for the proposed model that contains 17 features and compared to Neural Network (Feed Forward Back propagation) with (92.19%) accuracy. This research demonstrated that cooperative game is very promising to use directly for classification.