Neural network model for transient ischemic attacks diagnostics

In this paper the neural network model for transient ischemic attacks (TIA) recognition is described. The proposed approach is based on integration of nonlinear principal component analysis (NPCA) neural network and multilayer perceptron (MLP). The data set from clinic was used for experiments performing. At combining the two different neural networks (NPCA and MLP) it is possible to produce efficient performance in terms of transient ischemic attacks detection and recognition. The main advantages of using the neural network techniques are the ability to recognize “novel” TIA instances, quickness and ability to assist a doctor in making decision.