WIXLIB

1Interactive Computerized Health Care EducationBySusan W. McRoy, PhD, Alfredo Liu-Perez, MS, and Syed S. Ali, PhDDepartment of Electrical Engineering and Computer ScienceUniversity of Wisconsin-MilwaukeeP. O. Box 784, Milwaukee, WI 53201Reprint requests should be addressed to:Professor Susan W. McRoyDepartment of Electrical Engineering and Computer ScienceUniversity of Wisconsin-MilwaukeeP. O. Box 784, Milwaukee, WI 53201For communication about the manuscript contact:Professor Susan W. McRoyDepartment of Electrical Engineering and Computer ScienceUniversity of Wisconsin-Milwaukee3200 North Cramer Street, Milwaukee, WI 53211Phone: (414) 229-6695Fax: (414) 229-6958Email: mcroy@cs.uwm.eduAcknowledgments:This work has been supported by grants from the National ScienceFoundation (IRI-9523646 and IRI-9701617) and by a gift from the Universityof Wisconsin Medical School, Department of Medicine1

2AbstractThe Patient Education and Activation System (PEAS) project aims to prepare people totake a more active role in their health care decisions. In this paper, we describe our workon the Layman Education and Activation Form (LEAF). LEAF is designed to be aninteractive, Internet-based system for collecting a patient’s medical history. It is uniquein that it gives patients access to educational information when it is most pertinent, whilethey are attempting to complete a form. It avoids overwhelming the patient, by onlyproviding the information when it is likely to be relevant. The system avoids askingirrelevant questions or providing irrelevant facts by tailoring the content of the form basedon the patient’s interaction with the system. The system also uses the patient’s answers tosuggest questions that the patient might ask her doctor and provides online resources thatthe patient can browse.Keywords: health education, Internet, medical history form2

3I.IntroductionThe PEAS (Patient Education and Activation System) project aims to prepare people totake a more active role in health care decisions. With the collaboration of the Departmentof Medicine at the University of Wisconsin Medical School (Milwaukee Area ClinicalCampus), the PEAS project group has been developing a coordinated set of computerprograms for educating patients. The project is investigating strategies for helping peopleidentify their health care concerns, learn what actions they can take, and verbalize theirconcerns to health-care professionals. These strategies address the problem of how topresent relevant information efficiently and effectively. This is accomplished by a multimedia computer interface with intelligent tutoring and intelligent discourse processing.One goal of our design has been to create an architecture that would alleviate the problemof misunderstanding and miscommunication between the patient and a computer system.Ultimately, we hope this will also alleviate possible miscommunication between the patientand her physician. Such breakdowns in communication can arise because of differences invocabulary or differences in beliefs about the significance of different states of health.Moreover, errors in understanding can propagate, because people interpret each new facton the basis of their understanding of old facts. To address these concerns, computersystems (and people!) must not ask patients to make choices without allowing them theopportunity to obtain clarification [1]. In addition, systems must avoid overwhelmingtheir users with too much information at once. As in human conversations, computersystems should allow a dialog with users, where each participant takes a turn and thengives the other party a chance to accept it or to ask for clarification. In this way,misunderstandings can be detected and addressed, before communication breaks downcompletely [2].This paper discusses an architecture for patient education that we have developed for theLayman Education and Activation Form (LEAF). LEAF extends the normal activity offilling in a medical form by including educational activities that will help patients to3

4understand medical terminology and various health-care related issues. At any pointduring an interaction with LEAF, patients can access facilities for explaining theterminology of the form (Definitions) and for learning about topics that they might wantto discuss with their doctor (Dialogue). (See Figure 1.) Unlike a hypertext-based system,which presents the same information to everyone, LEAF is interactive and tailors itsinteraction with each patient. It does this by using the information that the patient providesabout herself.For example, suppose that a patient has indicated that she is female, childless, and has afamily history of heart disease. LEAF will dynamically filter irrelevant parts of the medicalhistory form, such as those related to breast feeding. (This customization is importantbecause irrelevant parts of the form are especially likely to contain terminology that isunfamiliar or confusing.) If asked for advice (via Dialogue), LEAF will offer tailoredinformation about prevention and treatment strategies for heart disease and suggestquestions for the patient to ask the doctor. Similarly, if asked for a medical definition,LEAF constructs a customized definition, based on the health history given by the patient.Figure 1: LEAF’s Interface4

5A prototype implementation of LEAF has been built using the JAVA programminglanguage, and is publicly available over the World Wide Web.1 This prototypedemonstrates the functionality of LEAF and its ability to tailor the information that itprovides. It also demonstrates the portability of LEAF. Along with the form itself,LEAF provides a short questionnaire that allows users to participate in an informal (andanonymous) evaluation of LEAF. This informal information has given us insight into howreal patients might react to LEAF and where design improvements should be focused. Theobjectives of the prototype are limited in scope (to establish the proof-of-concept). Forexample, the current project does not address the problems of verifying the accuracy ofthe medical information that is provided. Any medical information provided is forillustrative purposes only, and should not be taken to represent the views of any of thePEAS project participants. The LEAF prototype demonstrates the feasibility and costeffectiveness of patient-tailored computerized interfaces to medical information.II.BackgroundA.Motivations for LEAFLEAF aims to help bridge the communication gap that exists between patients and theirdoctors. Patients are being asked to take a more active role in their health care. Patientsmust therefore be prepared for the increasing amount of information that they will receivedescribing their options and possible courses of action. This preparation includes a betterunderstanding of medical terminology. Although the resources available to health careprofessionals may be limited, computers can help by giving people access to medicalinformation outside the doctor’s office and by adapting the presentation of information tosuit the individual’s interests or expertise.To adapt the presentation of medical (or any type of) information to each user, a systemmust have information about the user and must be able to reason about which parts of its1It can be reached by pointing a JAVA-capable network browser tohttp://tigger.cs.uwm.edu/ alp/LEAFV1.1/leaf.html.5

6knowledge apply to a given situation. Ideally, a system will monitor each patient’sinteraction with the system and build a profile (called a user model) of the patient. As thesystem collects this information, it can use it (as well as the current state of the task) tomodify the questions that it asks and to customize the educational materials that itpresents. For example, it may choose to elaborate the core definition of a concept withspecific information relevant to a health condition that the patient has. This customizationis facilitated by organizing the knowledge base into small units of text that are indexed byfacts about the patient or goals that the patient might have. LEAF’s design provides thistype of flexibility.In designing LEAF, we considered previous methods for collecting medical histories frompatients and presenting educational materials to them. The results of our investigationsupported the need for a system such as LEAF and motivated some additional designconstraints that have been incorporated into the prototype. In the remainder of thissection, we consider some of the lessons learned from prior work. We then will discussthe architecture that has been developed.B.Traditional Medical History FormsFor reasons of generality, typical medical history forms contain questions and sections thatmight be irrelevant to any particular patient. They can also be confusing if they areworded awkwardly or contain medical terminology that is unfamiliar to patients. At thestart of this project, we evaluated a number of such forms. We found questions about thehealth of the patient's spouse, which are irrelevant if the patient is single. We foundsections that were intended “for administrative use only”. We found potentiallyambiguous questions, such as one that asked patients “To what extent are youexperiencing difficulty in the area of:” and presented “apathy, lack or interest in things” asan area. Our evaluator found this confusing, because he felt that he could either respond“no difficulty”, because he never feels apathetic, or he could respond “no difficulty”,because he found it easy to be apathetic. (This confusion is especially easy for non-nativespeakers of English.) Finally, none of the medical forms that we examined provided6

7explanations of the diseases or medical terms used, relying on the strategy that if a patienthas not heard of a disease then she has not had it. However, this is not a good assumptionfor non-native speakers. Moreover, even native speakers may confuse terms that soundalike, such as “constipation” and “obstipation”.C.Computerized Medical FormsComputer programs for collecting patients’ medical history offer the possibility ofsuppressing parts of the form that are unnecessary for patients and for includinginformation that will help patients respond to the questions more accurately. Researchersand clinicians have been experimenting with computerized medical forms since the 1960’s[3-7]. This and subsequent work confirms that medical interviewing by computer can be asreliable as the traditional medical form and that patients will enjoy using it.For example, HealthQuiz is a computer program, developed by the Clinical PracticeEnhancement Project (CPEP), that gathers health-risk data from patients and providesfeedback to both the patient and physician concerning guideline-based suggestions [8,9].These suggestions include possible immunizations or diagnostic tests. In experiments withHealthQuiz, 89% of patients found the computer enjoyable to use and 85% consideredHealthQuiz important to their care. Previous studies by CPEP examined the reliability ofdifferent methods for gathering various types of health information from patients. Theyfound that consistent preventive care information can be obtained when patients use acomputer. In addition, patients were more likely to be candid about risky health behaviorswhen communicating with a computer than with a human interviewer. As in LEAF,HealthQuiz filters questions on the basis of responses to earlier ones. Unlike LEAF,however, it does not support questions from patients about the terminology that it uses.D.Customized Medical ExplanationsAnother potential benefit of computerization of medical history forms and educationalmaterials is the possibility of customizing the content of these materials to individualpatients. Several studies have shown that customized information is more effective thangeneric information. For example, in a study targeting smoking cessation, 30.7% of7