Hybrid model based on Decision Trees and Fuzzy Cognitive Maps for Medical Decision Support System

For medical decision making processes (diagnosing, classification, etc.) all decisions must be made effectively and reliably. Conceptual decision making models with the potential of learning capabilities are more appropriate and suitable for performing such hard tasks. Decision trees are a well known technique, which has been applied in many medical systems to support decisions based on a set of instances. On the other hand, the soft computing technique of Fuzzy Cognitive Maps (FCMs) is an effective decision making technique, which provides high performance with a conceptual representation of gathered knowledge and existing experience. FCMs have been used for medical decision making with emphasis in radiotherapy and classification tasks for bladder tumour grading. This paper proposes and presents an hybrid model derived from the combination and the synergistic application of the above mentioned techniques. The proposed Decision Tree-Fuzzy Cognitive Map model has enhanced operation and effectiveness based on both methods giving better accuracy results in medical decision tasks.