<?xml version="1.0" standalone="yes"?>
<Paper uid="A94-1021">
  <Title>Upholding the Maxim of Relevance during Patient-Centered Activities</Title>
  <Section position="4" start_page="125" end_page="127" type="metho">
    <SectionTitle>
2 The Representational Framework
</SectionTitle>
    <Paragraph position="0"> In TraumAID, a plan is a set of procedures, each of which comprises one or more actions. Procedures are used to address diagnostic and therapeutic management goals motivated by what is currently known about the patient. A particular action can participate in more than one procedure, and thus can be used in addressing more than one goal. As noted earlier, TraumAID uses a rule-based reasoner to derive a set of relevant goals from the currently available knowledge about the patient and a planner to choose appropriate procedures to address those goals and schedules the actions they involve.</Paragraph>
    <Paragraph position="1"> TraumAID's reasoner controls information acquisition using a conservative, staged strategy for diagnosis and treatment (Rymon, 1993): expensive, definitive tests are not included in a plan until they are justified by less costly tests or observations, and  definitive treatment is not recommended without the results of sufficient evidence from diagnostic tests. 3 These strategies are reflected in the knowledge base by the occurrence of related management goals, such as a goal to diagnose hematuria (blood in the urine), which if present, triggers a goal to diagnose bladder injury, which in turn can lead to a goal to treat bladder injury. Goals that do not participate together in a coherent strategy may still be connected by test results. For example, the goal of finding a bullet in the mediastinum leads to doing a lateral chest x-ray.</Paragraph>
    <Paragraph position="2"> While this might also reveal a fractured sternum, there is no strategic relationship between the goal of finding a bullet in the mediastinum and the goal of treating a fractured sternum.</Paragraph>
    <Paragraph position="3"> Once a set of relevant goals has been determined, the planner's choice of how address each goal is based on both local and global considerations. Goals and procedures are linked via a goal-procedure mapping which lists alternative procedures for addressing each goal. The procedures in a mapping are listed in order of preference so that, all else being equal, the first procedure will be chosen to address the goal. Less preferred procedures may be selected if they would result in a globally more optimal (less costly) plan. Figure 1 shows three possible configurations for a portion of a plan addressing two goals. (Section 4 discusses the consequences for plan recognition, evaluation and critiquing, of the ability to create plans in which actions and/or procedures are shared between goals.) Actions are scheduled according to both logistical and clinical considerations. Logistical considerations mean that patients are only moved in one direction through the Trauma Center - from the emergency center, optionally to the radiology suite, then optionally to the operating suite, and finally to the 3The one case where this is not true is when a patient comes in near death, with catastrophic chest wounds.</Paragraph>
    <Paragraph position="4"> Surgery is recommended immediately, without attempting to diagnose what specific injuries may have been sustained.</Paragraph>
    <Paragraph position="5">  trauma unit. Since actions may have constraints on where they can be performed, they are scheduled so as to avoid transferring the patient back to a place he has already been.</Paragraph>
    <Paragraph position="6"> Clnical considerations have to do with the urgency and priority of each action, which it inherits from the goals it is being used to address. The urgency can be either calastrophic, unstable, or stable, representing the patient's condition and thus the amount of time available in which to address that goal. Catastrophic goals must be addressed immediately. Unstable goals must be addressed before stable goals. Priorities represent standard practices of trauma care: if there are no differences in urgency, problems involving the airway are addressed before those involving breathing, which are addressed before those involving circulation, etc. (the &amp;quot;ABCs of trauma care&amp;quot;).</Paragraph>
  </Section>
  <Section position="5" start_page="127" end_page="128" type="metho">
    <SectionTitle>
3 Interpreting and Reacting to
Orders
</SectionTitle>
    <Paragraph position="0"> We have claimed that in patient-centered activities, the effectiveness of a &amp;quot;by-stander&amp;quot; decision-support system depends on focusing its clinical role on the immediate needs of physicians rather than intervening with information that, while correct and apropos, would not make a significant difference to patient management. In order to achieve this, our approach is largely reactive rather than proactive.</Paragraph>
    <Paragraph position="1"> As noted in Section 1, instead of presenting TraumAID's recommended management plan, TraumaTIQ waits for the physician's orders, which are treated as intentions to perform those actions. TraumaTIQ interprets and evaluates these intentions, and generates a comment if it would be relevant to do so.</Paragraph>
    <Paragraph position="2"> TraumaTIQ also interprets the lack of an ordered action within an appropriate time frame as indicating the physician's lack of intention to perform that action and evaluates it as such. This approach is a form of critiquing, early examples of which are (Langlotz and Shortliffe, 1983; Miller, 1986).</Paragraph>
    <Paragraph position="3"> TraumaTIQ's critiquing process is triggered whenever new information is entered by the scribe nurse and delivered to TraumAID. This information can be in the form of (1) bedside findings, (2) diagnostic test results (indicating both that a diagnostic action has been performed and what the results of that action were), (3) therapeutic actions performed, or (4) diagnostic or therapeutic actions ordered by the physician. TraumaTIQ interprets the physician's orders in a goal-directed manner, using TraumAID's representation of goals, procedures and actions, so that the critique can address the likely reasons underlying any discrepancies and can suggest alternative means of addressing a particular goal. Figure 2 shows the architecture of Trauma-TIQ, comprising plan recognition, plan evaluation, and critique generation.</Paragraph>
    <Section position="1" start_page="127" end_page="127" type="sub_section">
      <SectionTitle>
3.1 Plan Recognition
</SectionTitle>
      <Paragraph position="0"> In order to judge when it is relevant to comment on a physicians orders or lack thereof, it is useful to consider not only what actions have been ordered, but also why. For example, this can allow comments to be withheld if an ordered action that differs from TraumAID's choice would nevertheless satisfy pertinent management goals. TraumaTIQ's plan recognition component aims to infer the underlying goal structure motivating the physician's orders for actions to be performed. Note that this is an example of keyhole recognition, rather than intended recognition (Kautz, 1990). The physician does not intend to provide enough information to allow others to infer his plans. Like other members of the trauma team, TraumaTIQ must infer the plan incrementally based on what is known about the patient and what has been ordered so far.</Paragraph>
      <Paragraph position="1"> Trauma management poses particular problems for plan recognition. First, there is no fully pre-set sequence in which actions are ordered and done. Secondly, multiple diagnostic and therapeutic goals may simultaneously be active, and a single action can often be used to address several related or unrelated goals. In this domain, it would thus be incorrect to simplify search by minimizing the number of top-level goals in the inferred plan, as Kautz and others have proposed (Kautz, 1990). Third, a plan recognition strategy cannot assume that the physician's plan is correct: management of trauma patients must often be done late at night and under time pressure, conditions that can lead to less than optimal decision-making even in trained professionals. Since the number of possible incorrect plans is too large to encode a priori, we must make certain assumptions about physicians' plans: * The head of a trauma team will have expert or near-expert knowledge of trauma, and will usually develop plans that are similar to Traum-AID's. Thus, if an action has been ordered that is also in TraumAID's plan, TraumaTIQ assumes that it is being done for the same reason(s). We call this giving the physician the &amp;quot;benefit of the doubt.&amp;quot; * The physician is more likely to have appropriate goals but be addressing them in a sub-optimal way, than to be pursuing the wrong goals altogether. null * While TraumAID follows a conservative strategy for pursuing diagnosis and treatment from observations, physicians may proceed more rapidly, pursuing a goal that may be involved in a current strategy but for which TraumAID does not yet have enough evidence to conclude its relevance. An understanding of the strategic relationships between goals should help to recognize examples of this difference.</Paragraph>
      <Paragraph position="2"> Reflecting these assumptions, the plan recognition algorithm works as follows:  1. When an action, a, is ordered by the physician, check whether ~ is currently a part of TraumAID's recommended plan as a means of satisfying all or part of goal 7, or all or part of each member of a set of goals F.</Paragraph>
      <Paragraph position="3"> 2. If so, add 3' or F to the representation of the physician's plan.</Paragraph>
      <Paragraph position="4"> 3. If a is not currently in TraumAID's plan, determine whether there is a relevant goal that a might address: (a) If any of the goals that might lead to doing are present in TraumAID's current set of active goals, assume that c~ is being done to address that goal or goals.</Paragraph>
      <Paragraph position="5"> (b) In the case that there is no relevant goal to explain why the physician is ordering a, check whether any of the possible goals motivating a are part of a currently active diagnostic strategy (cf. Section 2).</Paragraph>
      <Paragraph position="6"> (c) If no relevant goal or strategy is found,  leave the goal unspecified and add the intention to do a to the representation of the physician's plan with no goal attached.</Paragraph>
      <Paragraph position="7"> There is one exception to this rule: (d) If the system only knows of one possible goal that would lead to performing c~, TraumaTIQ assumes that a is being done to address that goal, even though it does not consider the goal to be relevant.</Paragraph>
    </Section>
    <Section position="2" start_page="127" end_page="128" type="sub_section">
      <SectionTitle>
3.2 Plan Evaluation
</SectionTitle>
      <Paragraph position="0"> After attempting to infer the goal(s) underlying the physician's actions, TraumaTIQ attempts to identify whether commentary is warranted on any aspects of his plan. Plan evaluation begins by comparing the plan attributed to the physician with the plan produced by TraumAID, looking for four types of discrepancies:  * Omission: A goal that TraumAID considers relevant is not being addressed by the physician in a timely manner. This can be further analyzed as to whether (1) the goal is not being addressed at all, or (2) the goal is only being partially addressed - some but not all the actions in the procedure addressing the goal have been ordered.</Paragraph>
      <Paragraph position="1"> * Commission: An action is present in the physician's plan that does not address a relevant goal.  If a unique goal can be inferred to explain this discrepancy, that goal can be further categorized as to whether (1) it is unwarranted, (2) it is not fully proven, or (3) it has already been addressed.</Paragraph>
      <Paragraph position="2"> * Procedure choice: A relevant goal is being addressed, but not using the procedure preferred by TraumAID.</Paragraph>
      <Paragraph position="3"> * Scheduling: Actions are not being done in the order recommended by Traumaid, e.g., satisfying urgent goals before non-urgent ones. TraumaTIQ upholds the Maxim of Relevance by attempting to avoid comments that may later prove irrelevant. Errors of omission are not critiqued until a sufficient period of time has elapsed during which the physician might order the action. The amount of time allowed depends on the urgency of the goal that the action is intended to address - the rule of thumb TraumaTIQ uses is that a comment should be produced after approximately 10% of the time period has passed that is available to address the goal without significant consequences. Furthermore, comments are only made with respect to goals that cannot be made irrelevant by actions scheduled to be done before those goals are addressed.</Paragraph>
      <Paragraph position="4"> Discrepancies of all types are then evaluated in terms of their potential clinical significance. Currently this is only a rough estimate based on approximate cost and whether or not a procedure is invasive. For example, an unnecessary chest x-ray is considered insignificant while an unnecessary (and invasive) laparotomy is considered clinically significant and worth drawing to the physician's attention. We are currently in the process of developing more objective criteria for classifying errors according to their potential impact on the outcome of the case. Each discrepancy will be classified as either: (1) tolerable, probably harmless, (2) non-critical, but potentially harmful, or (3) critical, potentially fatal. Anything in the second or third category will be considered significant enough to be reported in the critique, while tolerable errors will not be mentioned. The output of plan evaluation is a set of communicative goals containing (1) a propositional content (PC) indicating the type of discrepancy and the particular TraumAID concepts involved, and (2) an illocutionary force (IF), such as URGE, INFOrtM or aEMIND, indicating how the information should be realized linguistically. For example, the goal:  would be produced in a situation in which the physician has ordered a CT-scan of the abdomen, which TraumaTIQ has inferred is intended to address the goal of diagnosing a compound fracture of the lumbar vertebra, which TraumAID has instead chosen to address with a considerably less costly, less time-consuming lateral abdominal X-ray. The illocutionary force of SUGGEST indicates that this is a non-critical error. Had it been evaluated as a critical error, the illocutionary force would have been URGE.</Paragraph>
    </Section>
    <Section position="3" start_page="128" end_page="128" type="sub_section">
      <SectionTitle>
3.3 Critique Generation
</SectionTitle>
      <Paragraph position="0"> Critique generation serves to organize TraumaTIQ's communicative goals according to the management goals they address and to translate them into Natural Language utterances. This is currently the least sophisticated part of the process: each IF-PC pair indexes a sentential template with syntactically marked slots to be filled in with the appropriate phrasal translation of a TraumAID concept. For example, the template indexed by (SUGGEST, PROCE-DURE CHOICE) is: &amp;quot;TraumAID suggests (ARG1 GERUN-DIVE) rather than (ARG2 GERUN-DIVE). The former is preferred for (ARG3 GERUNDIVE).&amp;quot; The first and second slots are filled in with gerundive phrases corresponding to GET-X-RAY-LAW-ABD and GET-CT-SCAN-ABD, while the third slot is filled in with an untensed verb phrase corresponding to R,O-COMPOUND-FRACTURE-LUMBAR-VERTEBRA, resulting in the sentence: &amp;quot;TraumAID suggests getting a lateral X-Ray of the abdomen rather than getting a CT-sean of the abdomen. The former is preferred for checking for fracture of the lumbar vertebrae.&amp;quot; Critiques can be delivered directly to the trauma bay through synthesized speech or to the scribe nurse for subsequent delivery to the trauma team.</Paragraph>
    </Section>
  </Section>
  <Section position="6" start_page="128" end_page="128" type="metho">
    <SectionTitle>
4 Action Overloading
</SectionTitle>
    <Paragraph position="0"> As mentioned earlier, it is possible for a single action to participate in addressing more than one management goal. This strategy of doubling-up the use of plan elements is called intention overloading by Pollack (Pollack, 1991), who argues that it can simplify the process of computing optimal plans. It can, however, complicate the process of recognizing and evaluating them. Our strategy in TraumaTIQ is to assume that overloading occurs in the physician's plan whenever it would be beneficial. In other words, if an action ordered by the physician can be used to address two or more relevant goals, it is assumed that that is what the physician intends. This assumption makes sense because as long as both goals are being addressed, there is no need to produce a critique, even if the physician did not have both goals in mind.</Paragraph>
    <Paragraph position="1"> If, on the other hand, there is a possibility for overloading that the physician does not exploit, it may be clinically relevant to mention it. For example, consider a patient with a gunshot wound to the abdomen, loss of sensation in both legs, and hematuria (Figure 3a). From the first two findings, TraumAID derives a goal of diagnosing a compound fracture of the lumbar vertebra, and from the type of wound and the finding of hematuria it derives a goal of diagnosing renal injury. Both goals can be addressed by a single abdominal CT-scan.</Paragraph>
    <Paragraph position="2"> Figure 3b shows the plan that is inferred from the physician's order of a lateral abdominal x-ray, which is appropriate for the goal of diagnosing a fractured vertebra, but not for diagnosing renal injury. In this situation, two points are clinically relevant: (1) the goal of diagnosing renal injury should be addressed, and (2) both goals can be addressed with the single action of an abdominal CT-scan, obviating the need to do an X-ray to address one'of them. In this case a comment such as the following would be produced: &amp;quot;TraumAID suggests getting an abdominal CT-scan rather than a lateral abdominal X-ray. The former can be used both to diagnose renal injury and to diagnose a compound fracture of the lumbar vertebrae.&amp;quot;</Paragraph>
  </Section>
class="xml-element"></Paper>