Artificial neural networks - Opening the black box

Artificial neural networks now are used in many fields. They have become we ll established as viable, multipurpose, robust computational methodologies with solid theoretic support and with strong potential to be effective in a ny discipline, especially medicine. For example, neural networks can extrac t new medical information from raw data, build computer models that are use ful for medical decision making, and aid in the distribution of medical exp ertise. Because many important neural network applications currently are em erging, the authors have prepared this article to bring a clearer understan ding of these biologically inspired computing paradigms to anyone intereste d in exploring their use in medicine. They discuss the historical developme nt of neural networks and provide the basic operational mathematics for the popular multilayered perceptron. The authors also describe good training, validation, and testing techniques, and discuss measurements of performance and reliability, including the use of bootstrap methods to obtain confiden ce intervals. Because it is possible to predict outcomes for individual pat ients with a neural network, the authors discuss the paradigm shift that is taking place from previous "bin-model" approaches, in which patient outcom e and management is assumed from the statistical groups in which the patien t fits. The authors explain that with neural networks it is possible to med iate predictions for individual patients with prevalence and misclassificat ion cost considerations using receiver operating characteristic methodology . The authors illustrate their findings with examples that include prostate carcinoma detection, coronary heart disease risk prediction, and medicatio n dosing. The authors identify and discuss obstacles to success, including the need for expanded databases and the need to establish multidisciplinary teams. The authors believe that these obstacles can be overcome and that n eural networks have a very important role in future medical decision suppor t and the patient management systems employed in routine medical practice. Cancer 2001;91:1615-35. (C) 2001 American Cancer Society.