A Hybrid Estimation System for Medical Diagnosis using Modified Full Bayesian Classifier and Artificial Bee Colony

Abstract

This paper presents a hybrid approach called Modified Full Bayesian Classifier (M-FBC) and Artificial Bee Colony (MFBC-ABC) for using it to medical diagnosis support system. The datasets are taken from Iraqi hospitals, these are for the heart diseases and the nervous system diseases. The M-FBC is depended on common structure known as naïve Bayes. The structure for network is represented by D-separated for structure's variables. Each variable has Condition Probability Tables (CPTs) and each table for disease has Probability. The ABC is easy technique for implementation, has fewer control parameters and it could be easier than other swarm optimization algorithms, so that hybrid with other algorithms to reach the optimal structure. In the input stage, the symptoms and the medical history for the patient are processed through the BNs structures to obtain from Modified Full Bayesian Classifier- Artificial Bee Colony (MFBC-ABC). The proposed system inputs all medical dataset and it filters and extracts the dataset. After the evaluation of the structures, the system can select the best optimal structure by determining the accepted accuracy. The accuracy for M-FBC model is approximately (93%) for heart diseases and approximately (98%) for nervous system diseases. While in The MFBC-ABC model, the accuracy is approximately (100%) for heart diseases and is approximately (99%) for nervous model diseases. The experimental results shown that the results for MFBC-ABC is better than on M-FBC.