Knowledge discovery in clinical databases based on rough set model

由于大量的临床数据被电子化存储，从这样的临床数据库中发现知识是医学信息学中日益增长的重要研究领域之一。为此，我们开发了一个基于变精度粗糙集模型的知识发现和机器学习实验系统KDD-R(A System For Knowledge Discovery In Base Using Rough Sets)，它是对原有粗糙集模型的扩展。该系统在以下步骤中工作。首先，它对数据库进行预处理，并将连续数据转换为离散化数据。其次，KDD-R检查属性之间的依赖关系，减少虚假数据。第三，系统从简化的数据库中计算规则。最后，第四，对决策进行评估。将该系统应用于脑膜脑炎临床数据库的计算结果表明，在临床数据库中的知识发现是医学信息学的一个重要研究领域。大多数医疗数据，如患者记录、实验室数据，现在都是电子化存储的，临床数据库的数量将过于庞大，以至于即使是医学专家也无法处理如此庞大的数据库。因此，一种基于计算机的方法有望解决这一困难局面。在本研究中，我们介绍了一个基于变精度粗糙集模型的知识发现系统KDD-R。首先，它对数据库进行预处理，并将连续数据转换为离散化数据。其次，KDD-R检查属性之间的依赖关系，减少虚假数据。第三，系统从简化的数据库中计算规则。作为评价，我们将KDD-R应用于脑膜脑炎临床数据库，其计算结果表明，从临床数据库中获得了几个新的发现。

Since a large amount of clinical data are being stored electronically, discovery of knowledge from such clinical databases is one of the important growing research area in medical Informatica. For this purpose, we develop KDD-R (a system for knowledge Discovery in Databases using Rough sets), an experimental system for knowledge discovery and machine learning research using variable precision rough sets (VPRS) model, which is an extension of original rough set model. This system works in the following steps. First, it preprocesses databases and translates continuous data in to discretized ones. Second, KDD-R checks dependencies between attributes and reduces spurious data. Third, the system computes rules from reduced databases. Finally, fourth, it evaluates decision making. For evaluation, this system is applied to a clinical database of meninigenecephalitis, whose computational results show that everal new findings are obtained.Knowledge discovery in clinical databases is an important research area in medical informatics. Most of medical data, such as patient records, laboratory data, are now being stored electronically, and the amount of clinical databases will be too huge, so that even medical experts cannnot deal with such large databases. Thus, a computer-based approach is promising to solve this difficult situation. In this study, we introduce a system KDD-R (a system for Knowledge Discovery in Databases using Rough sets), based on Variable Precision Rough Set (VPRS) model.This system works as follows. First, it preprocesses databases and translates continuous data into discretized ones. Second, KDD-R checks dependencies between attributes and reduces spurious data. Third, the system computes rules from reduced databases. Finally, fourth, it evaluates decision making.For evaluation, we apply KDD-R to a clinical database of meningoencephalitis, whose computational results show that several new findings are obtained from clinical databases.