Development of a nursing diagnosis system using a back-propagation neural network model: an application for stomach...

Neural networks have recently attracted considerable attention in the field of classification and in other areas. This paper discusses an experiment using a back-propagation neural network model applied to nursing diagnosis. The network's structure has three layers: 1) an input layer for representing signs and symptoms, 2) an output layer for nursing diagnosis, 3) a hidden layer. A first prototype of a nursing diagnosis system for stomach cancer patients was developed with 87 nodes for the input layer and 5 nodes for the output layer of 23 nursing diagnoses. It turned out that a model that learned 10,000 times as fast and had 5 nodes of hidden layers, a 0.5 momentum, and a 0.5 learning coefficient is the optimal one with a hitting ratio 0.76.