A NEURAL-NETWORK TO PREDICT ATTENDANCE OF PEDIATRIC-PATIENTS AT OUTPATIENT CLINICS

The development of a feed-forward neural network to predict attendance and non-attendance at a hospital outpatient clinic is described. Part icular emphasis is given to the post-processing applied to the network output, and to the choice of information presented to the network. Th e effect of individual inputs on the performance of the network is exa mined, and two methods of dealing with the problem of ambiguous input data are explored. It is shown that good results (approximately 90% ac curacy) are achieved with a feedforward network - having 15 input node s, a single hidden layer of five nodes and one output node with superv ised backpropagation - even where data is limited, and that an underst anding of the problem can lead to the modification of standard procedu res and improved network performance.