Applying High-level Agreement Ensemble Classification Voting Techniques to Distinguish Inflammatory Bowel Disease

Due to the complexity of medical decisions, there is a growing interest in the application of intelligence systems to support these decisions. In this paper, accordingly, the potential of several algorithms such as K Nearest Neighbor, Support Vector Machine, Random Forest, Naive Bayes, and Decision Tree was used to create an ensemble classification. Then, to obtain the voting result, high level agreement voting was used to evaluate the performance and make prediction. According to the involvement of body organs with this disease, the problem of diagnosing and differentiating various types of bowl inflammation was investigated. We should mention that higher prediction accuracy was obtained using the proposed model. The results and the comparisons of these methods showed that the proposed model indicates the highest prediction accuracy which is 98%. In the final step, the proposed model was evaluated applying the receiver operating characteristic curve model (ROC), and the area under the curve (AUC) was calculated.