数据挖掘与乳腺癌诊断的研究进展

Progress in Data Mining Techniques of Diagnosis of Breast Cancer

数据挖掘是应用一系列技术从大型数据库中提取人们感兴趣的信息和知识,这些知识或信息是隐含的、事先未知而潜在有用的,可表示为概念、规则、规律、模式等形式。本文详尽介绍了数据挖掘技术产生的背景、概念,综述了近年数据挖掘技术在医学中以及辅助诊断乳腺癌的应用情况,并探讨了其在辅助诊断乳腺癌的应用前景、意义以及目前存在的问题。

Data mining is to extract the interested information or knowledge from large databases using a series of techniques.The information and knowledge are generally hidden,unknown,but potentially useful,which can be expressed as concepts,rules,laws,modes or other forms.This article introduces the background and concepts of data mining,and reviews its application in medicine and the diagnosis of breast cancer for the most recent years.We also discuss the significance and current problems of this application in the diagnosis of breast cancer.