Experiment and Results Evaluation of Medical Diagnostic System Developed Through Artificial Feed Forward Neural Networks Using Optimal Back Propagation Algorithm

In its previous part, contribution reviews over the application of artificial neural networks to medical diagnosis and characterizes its advantages and problems in the context of the medical background. Then paradigm of neural networks is introduced and the main problems of medical data base and the basic approaches for training and testing a network by medical data are described. Additionally, the problem of interfacing the network and its result is given and the optimal Back propagation algorithm approach with its flow diagram is presented. On one hand growing neural network and on the other rules based systems works for Medical diagnosis purposes. Diagnostic capabilities of artificial neural network using optimal back propagation based medical diagnosis system is less error prone than fuzzified system of medical diagnosis so it is more advantageous than fuzzification based approach. Proposed diagnosis system has the capabilities to take intelligent decision based on given symptoms of diseases takes as a input and outcomes shows the bacterial infection level so this concept can be used for the purpose of developing Efficient medical diagnosis system and definitely will help to overcome the problems of lack of Experts in Medical fields, wrong diagnosis decisions due to human experts stress also it would help to enhance healthy population amount if such a system will reach to common peoples and use by them.