Association, statistical, mathematical and neural approaches for mining breast cancer patterns

Using several association and classification approaches to study breast can cer patterns, this study illustrates how these approaches can be used to pr edict and diagnose the occurrence of breast cancer. The results of the stud y, based on data obtained hom a large medical facility in western Pennsylva nia, show that data mining can be a viable tool for breast cancer diagnosis . (C) 1999 Elsevier Science Ltd. All rights reserved.