Dynamic evidence-based medicine (DEBM) is defined as the process of finding evidence about the care of individual patients automatically and dynamically in those cases when we cannot rely on any literature or guidelines. In this paper, we develop a framework for DEBM using data mining technologies that make it possible to automatically analyze huge clinical databases and to discover patterns behind them. We define the requirements of a data mining system for DEBM. The following functions are required of the system: (1) support for clinical decision making, and (2) discovery of rare patterns which human beings can hardly find. In order to support clinical decision making, rule discovery methods such as association rule mining are applied to this framework. We adopt a post-analysis approach using a rule base and queries. The discovered rules are collected into a rule base for further analysis. By submitting queries to the rule base, users can obtain keys to evidence for making decisions about clinical care. We preliminarily implement a prototype of a rule base and a post-analysis tool based on our framework. This tool can assist users in analyzing the discovered rules.

Searching for new rules and new knowledge in problem areas, where very little or almost none previous knowledge is present, can be a very long and demanding process. In our research we addressed the problem of finding new knowledge in the form of rules in the diabetes database using a combination of decision trees and association rules. The first question we wanted to answer was, if there are significant differences in sets of rules both approaches produce, and how rules, produced by decision trees behave, after being a subject of filtering and reduction, normally used in association rule approaches. In order to accomplish that, we had to make some modifications to both the decision tree approach and association rule approach. From the first results we can conclude, that the sets of rules, built by decision trees are much smaller than the sets created by association rules. We could also establish, that filtering and reduction did not effect the rules derived from decision trees in the same scale as association rules.

In this paper we describe an application of design patterns to the development of a decision tree learning system. A decision tree learning system constructs a classifier as a form of tree from a given data set. It is required to be as flexible as possible when used in real application domains. Design patterns help us construct reusable software components and construct flexible and extensible systems. The approach employed in this study is as follows. First we examine several decision tree learning systems and identify hot-spots in the systems at points we anticipate future demand for modification and extension of the system. Second we determine which design pattern to apply to each hot-spot. We evaluate the extensibility of the system experimentally. Our experience shows that using design patterns in object-oriented software design allows the easy construction of flexible systems.