Using artificial neural network for the prediction of anemia seen in Behcet Disease

In this study, an artificial neural network (ANN) application which predicts the role of prohepcidin and hepcidin in anemia which is frequently seen in behcet patients was developed. With ANN model, whether patients have chronic anemia linked to the disease can be determined using prohepcidin and hepcidin, the age of the patient, hemoglobin (hb), mean corpuscular volume (mcv), iron, iron binding capacity (ibc), ferritine, transferrin, sedimentation, c-reactive protein (c-rp) clusters. Although this system does not make definitive anemia diagnosis, it helps physicians to decide bone marrow biopsy by providing them information about whether patients have chronic anemia disease. In the design of the system, data from 19 behcet patient and 20 control patients were used. The definitive diagnosis corresponding to each patient and the data from ANN model results were investigated using Confusion matrix and ROC analyses. In the test data of the ANN model that was implemented as a result of these analyses, disease prediction rate was 99 % and the health ratio was 99 %. It is seen from these high predictive values that the ANN model is fast, reliable and without any risks and therefore can be of great help to physicians.