The use of artificial neural networks in biomedical technologies: an introduction.

Artificial neural networks (NN) are systems than can learn. In the most common situation, an operator trains the system on a set of input and output data belonging to a particular category. If new data of the same category, but not in the training set, are presented to the system, the NN can use the learned data to predict outcomes without any specific programming relating to the category of events involved. The fields of application of NN have increased dramatically in the past few years. Originally, the NN technique was mainly in the hands of computer programming specialists and the applications concentrated on tasks such as decision systems and signal processing. However, this picture has changed due to the emergence of user-friendly NN software for personal computers. A large variety of possible NN applications now exist for non-computer specialists. Thus, with only a very modest knowledge of the theory behind neural networks, it is possible to attack complicated problems in a researcher's own area of specialty with the NN technique. This is especially true in the field of medical technology, the topic of this review. The review is divided into three sections: 1) an elementary introduction to useful NN methods; 2) a review of the most important applications of the NN technique to this point in time; 3) a summary of available computer details that would be needed for a beginner in this field.

Neural-network applications for analysis of adverse drug reactions.

A neural-network analysis has been applied to predict adverse or side effects of drugs using a database of antidepressant agents with known effects as well as input from a database with both patient parameters and drug information. A NeuralWork software package was implemented on a Macintosh Quadra 700 and trained on a database of ten drugs with known adverse effects. Another agent (not in the database) was used to test the ability of the network to predict the relative incidence of its side effects. Despite the small number of drugs used for training, the adverse effects of some drugs, such as doxepin, were predicted with 90-100% accuracy. These results indicate that neural-network analysis can be used to predict adverse drug effects for drugs within a given class and ultimately can be extended to include patient parameters to predict the mechanisms of action of drugs from relatively large databases.