Introduction to artificial neural networks for physicians: Taking the lid off the black box

BACKGROUND. Over the past 5 years, a steady stream of publications has disc ussed the use of artificial neural networks (ANNs) for urologic and other m edical applications. The pace of this research has increased recently, and deployed products based on this technology are now appearing. Before these tools can be widely accepted by clinicians and researchers, a deeper level of understanding of ANNs is necessary. This article attempts to lay some of the groundwork needed to facilitate this familiarity. METHODS. A short discussion of neural network history is included for backg round. This is followed by an in-depth discussion of how and why ANNs work. This discussion includes the relationship between ANNs and statistical reg ression; An investigation of issues associated with neural networks follows , applicable to both general and urologic-specific applications. RESULTS. Neural networks are computer models that have been studied extensi vely for over 50 years, with prostate cancer applications since 1994. From a biological viewpoint, ANNs are artificial analogues of data structures th at exist in nervous systems. From a numeric viewpoint, ANNs are matrices of numbers whose values comprise knowledge that is distilled from historic da tabases. Many types of neural networks are analogous to well-known statisti cal methods. CONCLUSIONS. ANNs are complex numeric constructs, but no more complex than similar statistical methods. However, several issues associated with neural network derivation demand that developers apply rigorous engineering pract ices in their studies. Prostate 46:39-44, 2001. (C) 2001 Wiley-Liss, Inc.