<?xml version="1.0" standalone="yes"?>
<Paper uid="A94-1021">
  <Title>Upholding the Maxim of Relevance during Patient-Centered Activities</Title>
  <Section position="3" start_page="0" end_page="125" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Ordinary use of Natural Language adheres to what Grice has called the &amp;quot;cooperative principle of conversation&amp;quot; (Grice, 1975). Four categories of &amp;quot;maxims&amp;quot; elaborate this principle. Under the category of Relation, Grice places the single maxim &amp;quot;Be relevant&amp;quot;, noting that this terse formulation conceals a number of unsolved problems, including that of &amp;quot;what different kinds and focuses of relevance there may be&amp;quot;.</Paragraph>
    <Paragraph position="1"> This paper addresses &amp;quot;kinds and focuses of relevance&amp;quot; that a language-generating clinical decision-support system should adhere to during patient-centered activities - that is, activities in which a health care provider's (HCP) attention is on his or her patient and not on a computer screen. 1 Such activities include surgery, childbirth, and emergency medical care (including the responsibilities of Emergency Medical Technicians). During patient-centered activities, utterances generated by a computer system intrude on patient management. They must be seen by HCPs as having immediate clinical relevance, or, like the continual ringing of ICU monitors, they will be ignored. Utterances that would not make a clinically significant difference to patient management must be avoided. This paper describes how plan recognition and plan evaluation can be used to achieve this end.</Paragraph>
    <Paragraph position="2"> This work is being done in the context of the TraumAID project (Clarke et al., 1993; Clarke et al., 1994; Rymon et al., 1993; Webber et al., 1992), a In this sense, our emphasis differs from Sperber and Wilson (Sperber and Wilson, 1986), who are concerned with the problem of inferences that can be made under the assumption of relevance.</Paragraph>
    <Paragraph position="3">  whose overall goal is to improve the delivery of quality trauma care during the initial definitive phase of patient management. Initial definitive management scopes a complex range of diagnostic and therapeutic procedures. Resolving often conflicting demands for managing multiple injuries requires global reasoning that can exceed the restricted locality of rule-based systems. The modular architecture of the current system, TraumAID 2.0, consists of two complementary processes: (1) a rule-based reasoner able to draw diagnostic conclusions and identify what goals each of them implies; and (2) a planner that takes the set of currently relevant goals and constructs a management plan - a partially-ordered sequence of actions - that is most appropriate at that point in time.</Paragraph>
    <Paragraph position="4"> TraumAID 2.0 has been retrospectively validated against actual trauma management plans for 97 nonpregnant adult patients presenting consecutively to the Medical College of Pennsylvania (MCP) Trauma Center with penetrating injuries to the chest and/or abdomen. A blinded comparison of management plans was carried out by a panel of three experienced trauma surgeons. They preferred TraumAID 2.0% plans to actual management to a statistically significant extent (Clarke et al., 1993).</Paragraph>
    <Paragraph position="5"> A decision support system will not be clinically viable without solving its interface problems. For us, this means (1) getting TraumAID the information it needs for its reasoning and planning, and (2) getting the results of TraumAID's reasoning to the members of the trauma team (in particular, to the chief surgical resident) during the course of care.</Paragraph>
    <Paragraph position="6"> To get information into TraumAID, we have developed an electronic version of a standard trauma flow sheet, so that information can be entered by the scribe nurse during the trauma resuscitation. 2 The electronic trauma flow sheet is implemented in HyperCard, supported by a FoxPro database. Relevant information entered by the scribe nurse is automatically passed to TraumAID 2.0.</Paragraph>
    <Paragraph position="7"> The focus of this paper is the problem of delivering the results of TraumAID's deliberations, given an early pilot study that showed that physicians using TraumAID disliked the continuous presentation of its entire management plan. (Currently, this is displayed on the nurse's monitor in a separate window.) The reasons for physician dissatisfaction appear to be that (1) much of the time, TraumAID's recom2One member of the trauma team is a nurse who functions as a scribe, documenting all the findings, tests, and treatments in chronological order for the record. The multiple page trauma flow sheet has designated areas for specific information, such as demographics, mechanism of injury, physician response times, trauma score, Glasgow coma score, vital signs, location of wounds, results of primary assessment, intravenous therapy, diagnostic and therapeutic procedures, medications given, fluid intake and output, and disposition.</Paragraph>
    <Paragraph position="8"> mendation coincided with the physicians' own plans, and (2) having the entire plan presented made it difficult for the physicians to determine what, if anything, they should focus on. To put it another way, presenting the entire plan violates Grice's Maxim of Relevance.</Paragraph>
    <Paragraph position="9"> We decided to explore how TraumAID could restrict commentary to only those situations in which a comment would be clinically relevant in terms of its potential for making a clinically significant difference to patient management. We took advantage of the fact that actions that involve resources that need to be brought to the trauma bay or that can only be done elsewhere must be ordered. Since orders can be rescinded, comments pointing out problems with an order can potentially make a clinically significant difference to patient management. Our prototype interface for TraumAID produces commentary when an order differs significantly from what TraumAID would recommend. It also generates commentary when the physician fails to order something that TraumAID thinks should be done within the immediate time frame. The interface, TraumaTIQ (Gertnet, 1994; Gertner, 1994b), uses plan inference and plan evaluation to recognize both such errors of commission and errors of omission. In this paper, we describe TraumAID's knowledge of management goals and actions that are used in plan inference and evaluation (Section 2), the plan recognition and evaluation strategies that allow TraumaTIQ to recognize clinically significant differences in patient management(Section 3), and the additional problems for plan recognition, plan evaluation and critique generation caused by a planner's ability to optimize plans through what Pollack has called &amp;quot;overloading intentions&amp;quot; (Pollack, 1991) (Section 4). We conclude with mention of our planned prospective evaluations of TraumAID and TraumaTIQ and a summary of our main points (Section 5).</Paragraph>
  </Section>
class="xml-element"></Paper>