<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-0704">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics Situated Question Answering in the Clinical Domain: Selecting the Best Drug Treatment for Diseases</Title>
  <Section position="3" start_page="24" end_page="24" type="intro">
    <SectionTitle>
2 Considerations for Clinical QA
</SectionTitle>
    <Paragraph position="0"> We begin our exploration of clinical question answering by first discussing design constraints imposed by the domain and the information-seeking environment. The practice of evidence-based medicine (EBM) provides a well-defined process model for situating our system. EBM is a widelyaccepted paradigm for medical practice that involves the explicit use of current best evidence, i.e., high-quality patient-centered clinical research reported in the primary medical literature, to make decisions about patient care. As shown by previous work (De Groote and Dorsch, 2003), citations from the MEDLINE database maintained by the National Library of Medicine serve as a good source of evidence.</Paragraph>
    <Paragraph position="1"> Thus, we conceive of clinical question answering systems as fulfilling a decision-support role by retrieving highly-relevant MEDLINE abstracts in response to a clinical question. This representsadeparturefromprevioussystems, whichfocus on extracting short text segments from larger sources. The implications of making potentially life-altering decisions mean that all evidence must becarefullyexaminedincontext. Forexample,the efficacy of a drug in treating a disease is always framed in the context of a specific study on a sample population, over a set duration, at some fixed dosage, etc. The physician simply cannot recommend a particular course of action without considering all these complex factors. Thus, an &amp;quot;answer&amp;quot; without adequate support is not useful. Given that a MEDLINE abstract--on the order of 250 words, equivalent to a long paragraph--generally encapsulates the context of a clinical study, it serves as a logical answer unit and an entry point to the information necessary to answer the physician's question (e.g., via drill-down to full text articles).</Paragraph>
    <Paragraph position="2"> In order for a clinical QA system to be successful, it must be suitably integrated into the daily activities of a physician. Within a clinic or a hospital setting, the traditional desktop application is not the most ideal interface for a retrieval system.</Paragraph>
    <Paragraph position="3"> In most cases, decisions about patient care must be made by the bedside. Thus, a PDA is an ideal vehicle for delivering question answering capabilities (Hauser et al., 2004). However, the form factor and small screen size of such devices places constraints on system design. In particular, since the physician is unable to view large amounts of text, precision is of utmost importance.</Paragraph>
    <Paragraph position="4"> In summary, thissection outlinesconsiderations for question answering in the clinical domain: the necessity of contextualized answers, the rationale for adopting MEDLINE abstract as the response unit, and the importance of high precision.</Paragraph>
  </Section>
class="xml-element"></Paper>