Medical education and decision support using network-based multimedia information resources.
Explore the source record for details and available documents.
Computer Communication Networks↗
Biomedical subjects
R A Greenes
Publications and source records attributed to R A Greenes.
Rule set reduction using augmented decision table and semantic subsumption techniques: application to cholesterol guidelines.
Clinical practice guidelines must comprehensively address all logically possible situations, but this completeness may result in sizable and cumbersome rule sets. We applied rule set reduction techniques to a 576-rule set regarding recommendations for medication treatment of hypercholesterolemia. Using decision tables augmented with information regarding test costs and rule application frequencies, we sorted the rule sets prior to identifying irrelevant tests and eliminating unnecessary rules. Alternatively, we examined the semantic relationships among risk factors in hypercholesterolemia and applied a subsumption technique to reduce the rule set. Both methodologies resulted in substantial rule set compression (mean, 48-70%). Subsumption techniques proved superior for compacting a large rule set based on risk factors.
Adult↗
The findings--diagnosis continuum: implications for image descriptions and clinical databases.
As part of the Unified Medical Language System (UMLS) project, we have been exploring the use of semantic net representation to build a medical ontology that can adapt to the needs and perspective of differing kinds of users with varying purposes. A principal objective is to facilitate indexing and retrieval of objects in a variety of target databases, using their own source vocabularies, while maintaining the representation of concepts to which these source vocabularies refer in a single consistent form, so that retrievals that span resource types can be accommodated. In addition, a particular area of deficiency of the existing UMLS Metathesaurus is that of clinical findings, a part of the problem being the multiple alternative views and granularity levels at which clinical findings are described in different target databases. The problem is particularly obvious when one examines the way in which image findings are described, which may be at a purely perceptual level, or at varying levels of aggregation into higher level observations or interpretations. We have developed a recursive model for representing observations and interpretations in a semantic net along a continuum of degree of aggregation, that appears to lend itself well to adaptation to varying perspectives.
Diagnosis, Computer-Assisted↗
Enhancing the Metathesaurus with clinically relevant concepts: anatomic representations.
To create a comprehensive taxonomy for medical concepts it is necessary to identify gaps and reconcile differences that exist between clinical, bibliographic, and other source vocabularies. As part of the Unified Medical Language System project, we have proposed enhancements to the Metathesaurus by the inclusion of terms from two source vocabularies with different unique perspectives or views. This process has disclosed a number of issues that arise as complexity increases. These issues must be resolved if the resultant Metathesaurus is to support the variety of uses for which it is intended.
Abstracting and Indexing↗
Form-based clinical input from a structured vocabulary: initial application in ultrasound reporting.
Ultra-STAR (Ultrasound Structured Attribute Reporting) allows a sonographer to record reports using a hierarchic standardized vocabulary. Reports are constructed interactively by using checkboxes and radio buttons in a graphical user interface to select concepts from the vocabulary. Concepts are presented in small windows that open when needed to record further detail. Preliminary reports are printed for the referring physician. Reports are later finalized by an attending radiologist and uploaded to the hospital's information system. Clinicians involved so far prefer an outline report to a natural language format.
Medical Records Systems, Computerized↗
Realistic viewing and manipulation of radiographic images on a personal computer--a user interface for educational applications.
The authors have designed a user interface for the display and manipulation of radiographic images that is intended for use in digitized teaching files and computer-aided instruction (CAI) applications. By making the way the viewer interacts with a set of digitized images on the computer screen as similar as possible to the interaction with conventional films on a view-box the authors have tried to create a system that combines the directness of the conventional teaching file with the power and flexibility of CAI. This is accomplished on readily available personal computer workstations.
Computer-Assisted Instruction↗
A "building block" approach to application development for education and decision support in radiology: implications for integrated clinical information systems environments.
Education and decision-support resources useful to radiologists are proliferating for the personal computer/workstation user or are potentially accessible via high-speed networks. These resources are typically made available through a set of application programs that tend to be developed in isolation and operate independently. Nonetheless, there is a growing need for an integrated environment for access to these resources in the context of professional work, during clinical problem-solving and decision-making activities, and for use in conjunction with other information resources. New application development environments are required to provide these capabilities. One such architecture for applications, which we have implemented in a prototype environment called DeSyGNER, is based on separately delineating the component information resources required for an application, termed entities, and the user interface and organizational paradigms, or composition methods, by which the entities are used to provide particular kinds of capability. Examples include composition methods to support query, book browsing, hyperlinking, tutorials, simulations, or question/answer testing. Future steps must address true integration of such applications with existing clinical information systems. We believe that the most viable approach for evolving this capability is based on the use of new software engineering methodologies, open systems, client-server communication, and delineation of standard message protocols.
Computer Systems↗
Composing user models through logic analysis.
The evaluation of tutorial strategies, interface designs, and courseware content is an area of active research in the medical education community. Many of the evaluation techniques that have been developed (e.g., program instrumentation), commonly produce data that are difficult to decipher or to interpret effectively. We have explored the use of decision tables to automatically simplify and categorize data for the composition of user models--descriptions of student's learning styles and preferences. An approach to user modeling that is based on decision tables has numerous advantages compared with traditional manual techniques or methods that rely on rule-based expert systems or neural networks. Decision tables provide a mechanism whereby overwhelming quantities of data can be condensed into an easily interpreted and manipulated form. Compared with conventional rule-based expert systems, decision tables are more amenable to modification. Unlike classification systems based on neural networks, the entries in decision tables are readily available for inspection and manipulation. Decision tables, descriptions of observations of behavior, also provide automatic checks for ambiguity in the tracking data.
Decision Making↗
Use of augmented decision tables to convert probabilistic data into clinical algorithms for the diagnosis of appendicitis.
Decision table techniques have been shown to be useful for ensuring logical completeness, eliminating ambiguity, and optimizing the translation of logic into flowcharts or computer programs. Nevertheless, they have not been widely applied in medicine. We have used decision table techniques to demonstrate the derivation of two sets of rules for determining whether to operate on patients with suspected appendicitis based on patterns of observed signs and symptoms. One rule set is based on a diagnostic threshold whereby morbidity is minimized; the other rule set minimizes mortality. For this purpose, we have developed an augmented decision table format that allows the incorporation of probability and utility data.
Algorithms↗
A computational model of approximate Bayesian inference for associating clinical algorithms with decision analyses.
The lack of rationale or explanation is a major deficiency of clinical algorithms. To address this issue, the authors present a computational model for associating decision analyses with clinical algorithms. Automata theory is used to model categorical reasoning with approximate Bayesian inference based on probability intervals. This approximation reduces the number of computations to linear-order instead of the exponential-order combinations of clinical findings in exact Bayes. The linkage of decision analyses and clinical algorithms by means of this model exploits a new concept of "regular" clinical algorithms and their equivalency in theory and provides valuable perspectives in practice for developers of clinical algorithms.
Algorithms↗
The DeSyGNER data access element: a readily reusable component for the construction of data-compatible multimedia programs.
Dynamic assembly of applications from diverse and possibly disparate collections of information components is a key element for powerful information management environments. Traditional methods of application development hinder flexible integration of information components because they treat computer programs as single, isolated units of functionality where inter-application connections and sharing of intra-application information components are achieved only by special cooperation between program authors. Although many programmers strive to develop re-usable program code, it is rare that independently developed components can be readily combined into new applications. One of the major reasons for this is that there is no overall agreement as to the types of segments written, how the segments communicate, or how their data is stored. We have created a multimedia applications development architecture called DeSyGNER (the Decision Systems Group Nucleus of Extensible Resources) that provides a type-independent definition of the fundamental information-bearing unit for the construction of data-compatible applications. By incorporating a common high-level architecture and an intrinsically modular object-oriented design, DeSyGNER applications process information in smaller, isolatable, and more mobile and reusable units than do monolithic computer programs.
Computer Graphics↗
Authoring multimedia clinical problem-solving exercises with CaseBase.
Explore the source record for details and available documents.
Authorship↗
Application development in the DeSyGNER environment: dynamic assembly of independent information resources via direct manipulation authoring.
Dynamic assembly of applications from diverse and possibly disparate collections of information components is a key element for powerful information management environments. Traditional methods of application development hinder flexible integration of information components because they treat computer programs as single units of functionality; inter-application connections and sharing of intra-application information components are achieved only by special cooperation between program authors. We have created a multimedia applications development architecture called DeSyGNER (the Decision Systems Group Nucleus of Extensible Resources) that provides a generalized framework for the inter-connection of independently developed units into applications. By focusing on composition methods or paradigms for constructing applications from modular, reusable units, DeSyGNER fosters sharing and cooperation in application development.
Authorship↗
Medical informatics. An emerging academic discipline and institutional priority.
Information management constitutes a major activity of the health care professional. Currently, a number of forces are focusing attention on this function. After many years of development of information systems to support the infrastructure of medicine, greater focus on the needs of physicians and other health care managers and professionals is occurring--to support education, decision making, communication, and many other aspects of professional activity. Medical informatics is the field that concerns itself with the cognitive, information processing, and communication tasks of medical practice, education, and research, including the information science and the technology to support these tasks. An intrinsically interdisciplinary field, medical informatics has a highly applied focus, but also addresses a number of fundamental research problems as well as planning and policy issues. Medical informatics is now emerging as a distinct academic entity. Health care institutions are considering, and a few are making, large-scale commitments to information systems and services that will affect every aspect of their organizations' function. While academic units of medical informatics are presently established at only a few medical institutions in the United States, increasing numbers of schools are considering this activity and many traditional departments are seeking and attracting individuals with medical informatics skills.
Career Choice↗
SAPHIRE--an information retrieval system featuring concept matching, automatic indexing, probabilistic retrieval, and hierarchical relationships.
SAPHIRE (Semantic and Probabilistic Heuristic Information Retrieval Environment) is an experimental computer program designed to test new techniques in automated information retrieval in the biomedical domain. A main feature of the program is a concept-finding algorithm that processes free text to find canonical concepts. The algorithm is designed to handle a wide variety of synonyms and convert them to canonical form. This allows natural language to be used for query input and also serves as the basis for a new approach to automatic indexing based on a combination of probabilistic and linguistic methods.
Abstracting and Indexing↗
Knowledge management as a decision support method: a diagnostic workup strategy application.
We have explored the potential of a computer-based approach called "knowledge management" to aid in clinical problem solving and education. The major features of the approach are its ability to support flexible and immediate access by a user to relevant knowledge and annotation and organization of the knowledge for personal use and subsequent retrieval. We illustrate this approach with its application to diagnostic workup strategy problems. In this application, knowledge may be in the form of static narrative text, diagrams, pictures, graphs, tables, flow charts, or bibliographic citations. Other more dynamic forms of knowledge may be the result of simulations, "what if" analyses or modeling, quantitative mathematical or statistical calculation, or heuristic inference. User assessment has demonstrated the system's ease of use and user perception of its desirability, but underscores the need for a "critical mass" of knowledge before such an approach will be widely utilized.
Decision Support Techniques↗
"Desktop knowledge": a new focus for medical education and decision support.
Physicians today are faced with "data overload" and, paradoxically, "information underload"--the inability to locate pertinent, needed knowledge in a sea of data with which they are inundated. Increasingly, the professional functions of the physician are becoming focused on the desktop workstation, in terms of its ability to provide "windows" into local databases and knowledge resources, and to serve as an access port to other networked resources. A challenge we now face is to develop means for structuring the vast potentially available knowledge resources in such a manner that access to pertinent knowledge can be facilitated, and to develop acceptable interfaces to the knowledge resources so that a user can effectively navigate through them. The complexity of this task is due to the nature of the knowledge resources--knowledge can be in a variety of forms, ranging from textual and pictorial material, to structured representations, to more dynamic embodiments in the form of procedures. In the Decision Systems Group we have focused on the development of a prototype desktop knowledge management environment known as Explorer-2, with the objective of providing a consistent interface for access to a wide variety of knowledge. Our accomplishments to date encompass the incorporation into the Explorer-2 environment of adaptations of textbook chapters and books, image data bases, simulations, and expert systems. Navigational aids are provided by a semantic net browser using both MeSH and augmented taxonomies and by a graphical overview map.(ABSTRACT TRUNCATED AT 250 WORDS)
Artificial Intelligence↗
Breast immobilization for occult mass aspiration.
Percutaneous needle aspiration of occult, presumably fluid-filled masses with ultrasound guidance is more difficult when the abnormality is in a deep location or when the breasts are pendulous or flaccid. The fenestrated compression plate available on dedicated mammographic units provides easy access for needle insertion and immobilizes the breast, permitting accurate puncture and aspiration.
Biopsy, Needle↗