Summary Objectives: Now that the National Library of Medicine has made SNOMED-CT widely available, we are trying to manage the terminology of a whole suite of medical applications and map our terminology into that in SNOMED. Methods: This paper describes the design and implementation of the Java Dynamic Tree that provides structure to our medical terminology and explains how it functions as the core of our system. Results: The tree was designed to reflect the stages in a patient interview, so it contains components for identifying the patient and the provider, a large set of chief complaints, review of systems, physical examination, several history modules, medications, laboratory tests, imaging, and special procedures. The tree is mirrored in a commercial DBMS, which also stores multi-encounter patient data, disorder patterns for our Bayesian diagnostic system, and the data and rules for other expert systems. The DBMS facilitates the import and export of large terminology files. Conclusions: Our Java Dynamic Tree allows the health care provider to view the entire terminology along with the structure that supports it, as well as the mechanism for the generation of progress notes and other documents, in terms of a single hierarchical structure. Changes in terminology can be propagated through the system under the control of the expert. The import/ export facility has been a major help by replacing our original terminology by the terminology in SNOMED-CT.

We have been working on a new version of text generation component of the Intelligent Medical Record (IMR), a patient simulation program. The new text generator is based on American Bar Foundation (ABF) generation system to support the production of text for progress notes and for form letters. The old IMR produced a text report of patient encounters and also created a list of patient features, but this text contained a number of grammatical errors and disfluencies. The new ABF-based text generator runs on a variety of platforms, fixes the old generator errors, and incorporates standard vocabulary from the Systematized Nomenclature of Medicine Clinical Terms (SNOMED-CT).

The Disorder Pattern Toolbox helps medical experts create and maintain the collection of disorder patterns and translate the existing vocabulary into the terminology bank of the SNOMEDCT (Systematized Nomenclature of Medicine Clinical Terms). The disorder patterns were initially designed for use in MEDAS (the Medical Emergency Decision Assistance System), a Bayesian diagnostic expert system, but they are now used as well in a test selection system and for building patient cases in a multimedia patient simulation system. This toolbox allows the expert to open a web page or a treatment guideline or a scientific paper, to select a phrase with a mouse, and to add the phrase into an opened disorder pattern. This toolbox then asks for probability estimates and integrates this information into the collection of disorder patterns. It also connects the expert to the Java Dynamic Tree, our vocabulary management tool, which helps users identify appropriate labels for patient features in the SNOMED-CT terminology bank.

The major problem in the evaluation of expert systems is the selection of the appropriate statistical measures of performance consistent with the parameters of the system domain. The objective of this paper is to develop the statistical evaluation methodology needed to assess the performance of medical expert systems including MEDAS - the Medical Emergency Decision Assistance System. The measures of performance are selected so as to have an operational interpretation and also reflect the predictive diagnostic capacity of a medical expert system. Certain summary measures are used that represent the sensitivity, specificity, and system response of a medical expert system. Measures of agreement such as the kappa statistic and the measure of conditional agrement are used to measure the agreement between the medical expert system and the physician. Goodman and Kruskal's lambda and tau measures of predictive association are introduced to evaluate the predictive capacity of a medical expert system. This methodology has been partially implemented in the performance evaluation of MEDAS.

Research has shown that physicians find a medical expert system much more attractive if the system can provide in addition to diagnostic support some relief from the heavy burden of responsibility for daily record keeping required in hospital practice. This paper introduces a sophisticated interactive system for generating daily progress notes designed to function as an integral part of MEDAS (the Medical Emergency Decision Assistance System). MEDAS is a pattern-recognition expert system, using multi-membership Bayesian inference. At hospital admission, the MEDAS diagnosis module and severity module produce a problem list and assign a severity code to each problem. In many hospitals, physicians are expected to provide daily progress notes discussing the patient's condition with respect to each problem area. For each problem, they need to consider subjective and objective information, assessment and make a plan for handling the problem. The items to be considered depend on the specific problem: remembering these items is a huge memory load; writing it all down is very time-consuming. Our system presents the physician with a series of problem-specific menus, making data entry easy and rapid. Finally, it automatically generates the necessary output for the patient record.

The Patient Simulation system has been developed as part of a medical education system, which generates simulated patients for given disorders. We are trying to build an Intelligent Information Retrieval System (IIRS) to support this system by providing five categories of learning resources, including text passages, class notes, articles, Web resources, and learning programs, to teach basic science to medical students in a problem-based learning environment. A customizable thesaurus is a major part of the IIRS system. With this thesaurus instructors can have flexibility to add new concepts to the system, but we need to develop concept-feature relationships to build this thesaurus. This paper discusses how to build these relationships using the index of a basic science textbook and a clinical text. Our goal is to associate names of basic science concepts from the index of a medical textbook on a particular topic with relevant disorders.

We propose a treatment protocol delivery system for Emergency Medical Technicians and combat medics in situations when patients are unable to obtain medical care from physicians with sufficient facilities, such as casualties in a battlefield environment. In such situations, patients are often in emergency condition and time is a critical factor for them. Telemedicine with wireless communication support has an important role to play in alleviating this problem. By using advanced computer technology in both hardware and software, telemedicine can help medics provide better care for these patients.

This paper introduces a Knowledge Engineering System, the Disorder Toolbox (DT), which assists physicians to build, test, and verify the knowledge base for the Medical Emergency Decision Assistance System (MEDAS). DT is designed using a hypertext/hypermedia system and gives physicians an intelligent and user-friendly tool to streamline the disorder pattern creation process. DT reads the Portable Patient File (PPF) generated by the Intelligent Medical Record Entry (IMR-E) System, and allows the medical expert to enter prior and conditional probabilities, and test the posterior probabilities for disorders during the knowledge creation time. After building the disorder patterns, the physician can load a PPF and produce a differential diagnosis using the multimembership Bayesian inference engine. The process of building the Disorder Toolbox and its use are described.< >

This paper describes an automated medical record designed to allow providers to enter patient data at the point of care. The system runs on PCs and Macintoshes and uses a graphical user interface and object-oriented programming to take advantage of current mouse and pen technologies. The provider acquires all relevant patient data by pointing and clicking at selections on input screens, many of which contain anatomical drawings to help the provider quickly and accurately describe patient findings. The system also generates a grammatically correct progress note using the problem-oriented structure. Furthermore, items identified in the assessment and plans portion of the program can be ported to expert systems for medical decision assistance or to billing systems. The system allows the provider to obtain the necessary information on a focused patient visit in less than 5 min or to enter a complete history and physical.

The authors introduce a novel patient severity measurement model using neural networks. A three layer, fully connected backpropagation neural network was used in the pilot experiment. The results are promising and demonstrate that the backpropagation neural network technique is capable of assessing the severity value by learning from raw data. The neural network is easy to improve and of relatively low cost. It saves the expert's valuable time used in assigning numerical values to variables.<>

Describes the implementation methodology of an intelligent progress note system which is designed to support physicians in writing problem-oriented progress notes. The authors are currently developing their system on PCs in Microsoft Windows 3.0 by using Spinnaker Plus. The conversion of the system from a PC base to Macintosh or OS/2 has proven to be easy. The design applies cognitive models of memory as well as hypermedia to provide a creative and productive environment for the physician. The basis of the work is observation of practicing physicians writing progress notes in today's paper-driven world. The hope is to simulate some of the more routine parts of the thinking processes that physicians devote to producing the progress note, to save time, and to provide useful reminders, so that the users can concentrate on the more complex parts of the task

This presentation will be done using the IMR-Entry (Intelligent Medical Record Entry) system. IMR-Entry is a software program developed as a front-end to our diagnostic consultant software MEDAS (Medical Emergency Decision Assistance System). MEDAS (the Medical Emergency Diagnostic Assistance System) is a diagnostic consultant system using a multimembership Bayesian design for its inference engine and relational database technology for its knowledge base maintenance. Research on MEDAS began at the University of Southern California and the Institute of Critical Care in the mid 1970's with support from NASA and NSF. The MEDAS project moved to Chicago in 1982; its current progress is due to collaboration between Illinois Institute of Technology, The Chicago Medical School, Lake Forest College and NASA at KSC. Since the purpose of an expert system is to derive a hypothesis, its communication vocabulary is limited to features used by its knowledge base. The development of a comprehensive problem based medical record entry system which could handshake with an expert system while creating an electronic medical record at the same time was studied. IMR-E is a computer based patient record that serves as a front end to the expert system MEDAS. IMR-E is a graphically oriented comprehensive medical record. The programs major components are demonstrated.

MEDRIS (The Medical Record Interface System) is an object oriented HyperCard interface designed to help physicians enter patient information as comfortably and naturally as possible. It can function as a stand alone system producing its own reports or serve as an interface to a medical expert system (e.g., MEDAS). MEDRIS plays an important role in the clinical education of medical students at the Chicago Medical School. MEDRIS portrays an intuitive, graphically oriented system that will provide a learning environment for the problem oriented medical record (POMR) that forms the basis of the structure of the history and physical exam. The enthusiasm shown by the medical students for this project has garnered support for including MEDRIS in the curriculum of the Introduction to Clinical Medicine course this semester. MEDRIS, developed using HyperCard, can be used as a tool not only for teaching POMR and physical diagnosis, but also computer literacy.

We present our concept of the comprehensive medical information system needed to support practicing physicians. Existing expert systems and automated medical record systems address only part of the information management needs of clinicians. What is needed is a comprehensive, integrated, modular approach toward medical information systems. Our system includes a recognized, tested medical expert system (MEDAS) combined with modules that address physician needs for an automated medical record, test selection capability, severity assessment, evaluation techniques, treatment protocols and reference to the medical literature. Each module has been designed to function as a stand alone entity or as part of an integrated system. In addition, we have developed knowledge creation tools allowing expert physicians with little computer expertise to create disorder patterns for the diagnostic inference (MEDAS), enter treatment protocols, and add features to the Feature Dictionary.

MEDRIS (The Medical Record Interface System) is an object oriented HyperCard interface designed to help physicians enter patient information as comfortably and naturally as possible. It can function as a stand alone system producing its own reports or serve as an interface to a medical expert system (e.g., MEDAS). MEDRIS plays an important role in the clinical education of medical students at the Chicago Medical School. MEDRIS portrays an intuitive, graphically oriented system that will provide a learning environment for the problem oriented medical record (POMR) that forms the basis of the structure of the history and physical exam. The enthusiasm shown by the medical students for this project has garnered support for including MEDRIS in the curriculum of the Introduction to Clinical Medicine course this semester. MEDRIS, developed using HyperCard, can be used as a tool not only for teaching POMR and physical diagnosis, but also computer literacy.

Medical expert systems require comprehensive evaluation of their diagnostic accuracy. The usefulness of these systems is limited without established evaluation methods. We propose a new methodology for evaluating the diagnostic accuracy and the predictive capacity of a medical expert system. We have adapted to the medical domain measures that have been used in the social sciences to examine the performance of human experts in the decision making process. Thus, in addition to the standard summary measures, we use measures of agreement and disagreement, and Goodman and Kruskal's λ and τ measures of predictive association. This methodology is illustrated by a detailed retrospective evaluation of the diagnostic accuracy of the MEDAS system. In a study using 270 patients admitted to the North Chicago Veterans Administration Hospital, diagnoses produced by MEDAS are compared with the discharge diagnoses of the attending physicians. The results of the analysis confirm the high diagnostic accuracy and predictive capacity of the MEDAS system. Overall, the agreement of the MEDAS system with the “gold standard” diagnosis of the attending physician has reached a 90% level.