Knowledge Discovery in Incomplete Medical Data Using Flow-Graph Networks

Abstract:

Clinical data are inevitably incomplete, and most knowledge discovery algorithms lack the capability to contend with missing data. Flow-graph confers some distinct advantages in data mining and knowledge discovery. However, flow-graph methodology is not able to comprehensively solve the incomplete data problem. This paper proposes a flow-graph network approach for extracting knowledge from incomplete medical data. The concept of incomplete-medical-diagnosis-flow-graph (IMDFG) was defined. To evaluate the diagnosis rules within the IMDFG, the computing method for the certainty factor and coverage factor are presented. Moreover, the application of flow-graph network can be useful for extracting comprehensibility knowledge from the incomplete medical data. In an illustrative medical example, the clinical diagnosis rules are induced and interpreted in accordance to the generated flow graphs.

• Periodical: Applied Mechanics and Materials (Volumes 713-715)
• Pages: 2133-2138
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.713-715.2133
• Online since: January 2015
• Authors: Yan Wang*, Lu Bin Hang, Feng Liu, Bin Jiang
• Keywords: Flow-Graph, Incomplete Medical Data, Knowledge Discovery

References

[1] K.C. Tan, Q. yu, C.M. Heng, T.H. Lee. Evolutionary computing for knowledge discovery in medical diagnosis. Artificial Intelligence in Medicine, 27(2003): 129-154.

DOI: 10.1016/s0933-3657(03)00002-2

[2] N. Esfandiari, M.R. Babavalian, A.M.E. Moghadam. Knowledge discovery in medicine: Current issue and future trend. Expert Systems with Applications. 41(2014): 4434-4463.

DOI: 10.1016/j.eswa.2014.01.011

[3] M. Ohsaki, H. Abe, S. Tsumoto, et al. Evaluation of rule interestingness measures in medical knowledge discovery in databases. Artificial Intelligence in Medicine, 41(2007): 177-196.

DOI: 10.1016/j.artmed.2007.07.005

[4] D. F Wong, L.S. Chao, Xiao Dong Zeng. A supportive attribute-assisted discretization model for medical classification. Bio-Medical Materials and Engineering, 24(2014): 289-295.

DOI: 10.3233/bme-130810

[5] G.I. Joseph, C. Ming-Hui, R.L. Stuart, H.H. Amy, Missing-data methods for generalized linear models: a comparative review. Journal of the American Statistical Association 100(2005): 332-346.

[6] M. A. Boujelben, Y. D. Smet, A. Frikha, and H. Chabchoub. Building a binary outranking relation in uncertain, imprecise and multi-experts contexts: the application of evidence theory. International Journal of Approximate Reasoning, 50(2009).

DOI: 10.1016/j.ijar.2009.06.001

[7] A. S. Salama, Topological solution of missing attribute values problem in incomplete information table. Information Sciences, 180(2010): 631-639.

DOI: 10.1016/j.ins.2009.11.010

[8] M. Ghannad-Rezaie, H. Soltanian-Zadeh, H. Ying, et al. Selection-fusion approach for classification of datasets with missing values. Pattern Recognition. 43(2010): 2340-2350.

DOI: 10.1016/j.patcog.2009.12.003

[9] Pawlak, Z.: Rough Sets and Flow Graphs. Rough sets, Fuzzy sets , Data Mining and Granular Computing, Springer, 2005: 1-11.

DOI: 10.1007/11548669_1

[10] awlak, Z.: Some Issues on Rough Sets. Transactions on Rough sets I, 2004: 1-58.

[11] http: /www. ics. uci. edu/~mlearn/MLRepository. html.