ARTIFICIAL NEURAL NETWORKS WITHIN MEDICAL DECISION-SUPPORT SYSTEMS

Artificial neural networks offer a way to actively assimilate both pas t and present knowledge, to extract information, to map correlations a nd to produce inferences from available data; all tasks which have rel evance to the clinical laboratory. In this paper, we describe one usef ul artificial neural network technique, backpropagation, and describe some of the practical considerations which need to be taken account of when using such methods. Examples are presented of the application of artificial neural networks in medicine and, particularly, in clinical chemistry. The paper goes on to describe the use of these methods wit hin medical decision support. We conclude that artificial neural netwo rks are useful multivariate techniques which are well able to play an important role in a decision support system. Further, that their prope rties as function approximators could be utilised in other areas of cl inical chemistry. We conclude by pointing out that the pattern recogni tion ability of artificial neural networks holds out the promise of ex tracting useful information from currently available data which is at present seen as being of little diagnostic utility.