<?xml version="1.0" standalone="yes"?>
<Paper uid="P00-1043">
  <Title>Extracting Causal Knowledge from a Medical Database Using Graphical Patterns</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Vast amounts of textual documents and dat a bases are now accessible on the Internet and the World Wide Web. However, it is very difficult to retrieve useful information from this huge disorganized storehouse. Programs that can identify and extract useful information, and r e late and integrate information from multiple sources are increasingly needed. The World Wide Web presents tremendous opportunities for developing knowledge extraction and know l edge discovery programs that automatically e x tract and acquire knowledge about a domain by integrating information from multiple sources.</Paragraph>
    <Paragraph position="1"> New knowledge can be discovered by relating disparate pieces of information and by infe r encing from the extracted knowledge.</Paragraph>
    <Paragraph position="2"> This paper reports the first phase of a project to develop a knowledge extraction and know l edge discovery system that focuses on causal knowledge. A system is being developed to identify and extract cause-effect information from the Medline database - a database of a b stracts of medical journal articles and conference papers. In this initial study, we focus on cause-effect information that is explicitly expressed (i.e. indicated using some linguistic marker) in sentences. We have selected four medical areas for this study - heart disease, AIDS, depression and schizophrenia.</Paragraph>
    <Paragraph position="3"> The medical domain was selected for two reasons: 1. The causal relation is particular important in medicine, which is concerned with deve l oping treatments and drugs that can effect a cure for some disease 2. Because of the importance of the causal r e lation in medicine, the relation is more likely to be explicitly indicated using linguistic means (i.e. using words such as result , e f fect , cause , etc.).</Paragraph>
  </Section>
class="xml-element"></Paper>