Diagnosis of medical data is a complex and challenging task for a medical scientist. It is almost complicated due to chaos behavior of medical data. However, since 1986 neural network based numerical modeling for the same is suggested by the world’s scientific community and shown some extent of success. In this study, comprehensive reviews of various contributions (1990 to 2016) have been done. Where different models from various contributors have been studied year wise. As a result, soft-computing i.e., neural network, deep learning technique, data mining technique such as associative classifier has been found to be successfully applied. In neural network based numerical modeling two different architectures of neural network such as BPN and RBF were found more suitable while BPN was better evaluated over RBF architecture as far as performance and complexity of implementation is concerned. Finally, it is concluded that BPN is sufficient to resolve this complex problem. It has shown 90% accuracy in modeling. However, obtaining optimum architecture for better performance is a pre-requisite. These evidences have been broadly discussed in this review paper.
