PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “User-Computer Interface”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 127 records · Page 7Linked to original sources
PubMed1992

Decision support system and medical liability.

Expert systems, which are going to be an essential tool in Medicine, are evolving in terms of sophistication of both knowledge representation and types of reasoning models used. The more efficient they are, the more often they will be used and professional liability will be involved. So after giving a short survey of configuration and working of expert systems, the authors will study the liabilities of people building and the using expert systems regarding some various dysfunctions. Of course the expert systems have to be considered only for human support and they should not possess any authority themselves, therefore the doctors must keep in mind that it is their own responsibility and as such keep their judgment and criticism. However other professionals could be involved, if they have participated in the building of expert systems. The different liabilities and the burden of proof are discussed according to some possible dysfunctions. In any case the final proof is inside the expert system by itself through re-computation of data.

Expert Systems↗
PubMed1992

A history-taking system that uses continuous speech recognition.

Q-MED is an automated history-taking system that uses speaker-independent continuous speech as its main interface modality. Q-MED is designed to allow a patient to enter her basic symptoms by engaging in a dialog with the program. Error-recovery mechanisms help to eliminate findings resulting from misrecognitions or incorrect parses. An evaluation of the natural language parser that Q-MED uses to map user utterances to findings showed an overall semantic accuracy of 87 percent; Q-MED asks more specific questions to capture findings that were not volunteered, or that were unable to be parsed in their initial, open-ended form.

Back Pain↗
PubMed1992

The integration of a continuous-speech-recognition system with the QMR diagnostic program.

We describe a continuous-speech interface for Quick Medical Reference (QMR), which allows physicians to input spoken descriptions of physical-examination findings, or observations. We analyze the difficulties in designing a continuous-speech interface for systems that use medical terminology. We present a method for matching spoken findings names expressed in natural language to QMR terms. The method is based on a semantic representation of findings that both minimize the effect of misrecognition and derive grammars that are necessary for supporting the recognition process.

Diagnosis, Computer-Assisted↗
PubMed1992

Improving the quality of emergency department documentation using the voice-activated word processor: interim results.

We examined whether voice-activated word processors provide an acceptable means for emergency physicians to create medical records. Our study addressed three areas of inquiry: whether physicians can be induced to try this new technology, whether they will continue to use it after outside technical support is withdrawn, and the factors contributing to adoption and substantial use of voice-activated computers by practicing emergency physicians. This paper presents findings from the first half of the study, reflecting physicians' reported experiences while receiving onsite training followed by technical support for three months after system installation. Based on preliminary assessments, the keys to successful use appear to include physician and group commitment, acceptance of a steep learning curve, and flexibility in adapting the computer software and/or practice habits.

Demography↗
PubMed1992

Direct physician entry of injury information and automated coding via a graphical user interface.

Injury data in the paper medical record are often inaccurate or lack adequate specificity to evaluate trauma patient care. To improve the quality of recorded injury data, we are testing a graphical, anatomic-based interface for quick collection of detailed injury information directly from the trauma physician. Navigation and data collection throughout the interface are facilitated by anatomic illustrations, menus, lists, and "dialog boxes". Using a "point and click" method, the user selects a specific anatomic structure (i.e., the spleen) from drawings. Detailed injury information, specific to the selected structure, is then collected from the user in an "intelligent" modal dialog box. The software uses SNOMED III nomenclature to create and store ICD, AIS, and trauma registry codes for each injury. Users can review and print abbreviated and detailed injury information for each patient. This demonstration will walk viewers through the injury collection and review process for injuries to the abdomen. We plan to evaluate the interface for accuracy, speed, user satisfaction and resources expended by comparing it with current methods of data collection and injury coding at our level I trauma facility.

Computer Graphics↗
PubMed1992

VA's Integrated Imaging System on three platforms.

The DHCP Integrated Imaging System provides users with integrated patient data including text, image and graphics data. This system has been transferred from its original two screen DOS-based MUMPS platform to an X window workstation and a Microsoft Windows-based workstation. There are differences between these various platforms that impact on software design and on software development strategy. Data structures and conventions were used to isolate hardware, operating system, imaging software, and user-interface differences between platforms in the implementation of functionality for text and image display and interaction. The use of an object-oriented approach greatly increased system portability.

Computer Graphics↗
PubMed1992

PC CLIN-SIM: a toolbook based clinical simulation environment.

The Departments of Computer Medicine, Health Care Sciences, Medicine, and Electrical Engineering & Computer Science at the George Washington University have joined forces to create a clinical simulation program. The purpose of this program is to provide experience in the management of complex patient populations (eg geriatrics). A number of simulation programs are available commercially, however none provide adequate geriatric content, or were deemed to lack functionality important to the developers. The immediate goal of this effort was to create a computer-based, core curriculum in geriatric medicine for medical and allied health students. The curriculum includes case simulations linked to a comprehensive reference database. The development objectives were to create an intuitive, friendly, consistent user interface which could serve as a shell for additional content areas. In order to increase fidelity, free text entry and time simulation were included.

Computer Graphics↗
PubMed1992

Testing spatial understanding of anatomy.

A system was designed to test the medical student's ability to recognize and locate anatomical cross-sections. The computer was used to prepare the data, present the test and track the user's responses. The nature of the test was such that it could be prepared, presented and used much more easily on the computer than on paper. The system was used successfully by anatomists and medical students.

Anatomy↗
PubMed1992

MailMinder: taming DHCP's mailman interface.

While the Department of Veteran's Affairs Decentralized Hospital Computer Program (DHCP) is one of the most widely disseminated and successful hospital information systems in existence, it currently is accessed through a user interface which is not as mature as the rest of the system. This interface is a VT-100 compatible, character oriented interface using menus accessed by typed commands for feature access. This project demonstrated that a mature graphical user interface (MailMinder) can be successfully used as a "front-end" to DHCP. MailMinder is completely compatible with the existing unmodified DHCP electronic mail program, Mailman. MailMinder allows the user to be more efficient than the current interface and offers additional features over the current mail system. The program has undergone evaluation and limited deployment at five separate sites. The feature set of this program and its operation will be shown at this demonstration. The demonstration has implications for all current hospital information systems.

Computer Graphics↗
PubMed1992

M NET: a statewide referring physician computer network.

M NET, the Referring Physician Computer Network, is a joint project between the University of Michigan Medical Center (UMMC) and IBM. A graphical user interface was developed to allow referring physicians easy access to a variety of patient, clinical, and institutional data. File transfer mechanisms were created and current clinical database files and programs were enhanced and restructured to facilitate remote data transmission. M NET is currently installed in referring physician office sites across the state, with additional physician sites identified and program enhancements under development.

Computer Communication Networks↗
PubMed1992

Professional DOC (PDOC): a software environment for authoring and consulting of electronic documentation. INTERACTIVE DIAGNOSIS and THERAPY: a medical application.

Professional DOC (PDOC) is a software environment for electronic documentation authoring and consulting based on the Hypermedia technology. It allows to manage different kinds of information (pictures, sounds, texts, graphics, video) organized according to hyperstructures. The user-friendliness and effectiveness of its man-machine interface, and its availability on the most common hardware platforms makes it a suitable product for a very broad category of users. INTERACTIVE DIAGNOSIS AND THERAPY is an electronic medical book designed to help general practitioners to make diagnosis and treat patients in their daily clinic practice.

Diagnosis, Computer-Assisted↗
PubMed1992

SCUT: clinical data organization for physicians using pen computers.

The role of computers in assisting physicians with patient care is rapidly advancing. One of the significant obstacles to efficient use of computers in patient care has been the unavailability of reasonably configured portable computers. Lightweight portable computers are becoming more attractive as physician data-management devices, but still pose a significant problem with bedside use. The advent of computers designed to accept input from a pen and having no keyboard present a usable computer platform to enable physicians to perform clinical computing at the bedside. This paper describes a prototype system to maintain an electronic "scut" sheet. SCUT makes use of pen-input and background rule checking to enhance patient care. GO Corporation's PenPoint Operating System is used to implement the SCUT project.

Handwriting↗
PubMed1992

Development of the cardiovascular system: an interactive video computer program.

The major aim of this project is to provide interactive video computer based courseware that can be used by the medical student and others to supplement his or her learning of this very important aspect of basic biomedical education. Embryology is a science that depends on the ability of the student to visualize dynamic changes in structure which occur in four dimensions--X, Y, Z, and time. Traditional didactic methods, including lectures employing photographic slides and laboratories employing histological sections, are limited to two dimensions--X and Y. The third spatial dimension and the dimension of time cannot be readily illustrated using these methods. Computer based learning, particularly when used in conjunction with interactive video, can be used effectively to illustrate developmental processes in all four dimensions. This methodology can also be used to foster the critical skills of independent learning and problem solving.

Cardiology↗
PubMed1992

SCOUT: information retrieval from full-text medical literature.

SCOUT is an expert system designed to aid the practicing physician in searching a full-text database of biomedical literature for information in the domain of oncology. In the clinical setting, an information-retrieval system needs to provide only a few relevant documents that address a patient-specific query. SCOUT models the expertise of an oncologist and an information specialist in a probabilistic inference system; it applies expert heuristics both in selecting the best source of information for a particular question and in developing an effective, source-specific search statement that retrieves only a minimal number of pertinent documents.

Expert Systems↗
PubMed1992

High-performance computing, high-speed networks, and configurable computing environments: progress toward fully distributed computing.

The next several years will see the maturing of a collection of technologies that will enable fully and transparently distributed computing environments. Networks will be used to configure independent computing, storage, and I/O elements into "virtual systems" that are optimal for solving a particular problem. This environment will make the most powerful computing systems those that are logically assembled from network-based components and will also make those systems available to a widespread audience. Anticipating that the necessary technology and communications infrastructure will be available in the next 3 to 5 years, we are developing and demonstrating prototype applications that test and exercise the currently available elements of this configurable environment. The Lawrence Berkeley Laboratory (LBL) Information and Computing Sciences and Research Medicine Divisions have collaborated with the Pittsburgh Supercomputer Center to demonstrate one distributed application that illuminates the issues and potential of using networks to configure virtual systems. This application allows the interactive visualization of large three-dimensional (3D) scalar fields (voxel data sets) by using a network-based configuration of heterogeneous supercomputers and workstations. The specific test case is visualization of 3D magnetic resonance imaging (MRI) data. The virtual system architecture consists of a Connection Machine-2 (CM-2) that performs surface reconstruction from the voxel data, a Cray Y-MP that renders the resulting geometric data into an image, and a workstation that provides the display of the image and the user interface for specifying the parameters for the geometry generation and 3D viewing. These three elements are configured into a virtual system by using several different network technologies. This paper reviews the current status of the software, hardware, and communications technologies that are needed to enable this configurable environment. These interdependent technologies include: (1) user interface and application program construction methodologies, (2) the interprocess communication (IPC) mechanisms used to connect the software modules of the application, (3) the network protocols and interface hardware used by the IPC for communicating between modules running on separate and independent computing system elements, (4) the telecommunications infrastructure that provides the low-level data transfer functions for the networks that connect the geographically distributed elements used by the application, and (5) the nature of the functional elements that will be connected to form virtual systems.

Computer Communication Networks↗
PubMed1992

Visualization of bioelectric phenomena.

Biomedical investigators are currently able to acquire and analyze physiological and anatomical data from three-dimensional structures in the body. Often, multiple kinds of data can be recorded simultaneously. The usefulness of this information, either for exploratory viewing or for presentation to others, is limited by the lack of techniques to display it in intuitive, accessible formats. Unfortunately, the complexity of scientific visualization techniques and the inflexibility of commercial packages deter investigators from using sophisticated visualization methods that could provide them added insight into the mechanisms of the phenomena under study. Also, the sheer volume of such data is a problem. High-performance computing resources are often required for storage and processing, in addition to visualization. This chapter describes a novel, language-based interface that allows scientists with basic programming skills to classify and render multivariate volumetric data with a modest investment in software training. The interface facilitates data exploration by enabling experimentation with various algorithms to compute opacity and color from volumetric data. The value of the system is demonstrated using data from cardiac mapping studies, in which multiple electrodes are placed in an on the heart to measure the cardiac electrical activity intrinsic to the heart and its response to external stimulation.

Algorithms↗
PubMed1992

High-performance computing in radiation cancer treatment.

In 1989 a consortium of the Radiation Oncology and Computer Science Departments at the University of North Carolina, BellSouth Corporation, GTE, and the MCNC was formed in response to the high-speed network initiative proposed by the National Science Foundation and the Defense Advanced Research Projects Agency. One of the purposes of this effort has been to demonstrate that applications exist that require gigabit per second networks. Our consortium, known as VISTAnet, proposed to use real-time radiation therapy treatment planning as the application that would require the use of a gigabit network. The plan was to develop a system that could rapidly calculate and display a three-dimensional radiation dose distribution for any configuration of radiation beams. The gigabit network would be used to tie the dose calculations done with the Cray Y-MP at the Research Triangle to the graphics engine at the Department of Computer Science (Pixel-Planes 5) and the medical workstation at Radiation Oncology. The system would then provide the radiation physician with the capability of considering hundreds of potential treatment plans, instead of the usual two or three, with the goal of arriving at a highly optimized plan within a few minutes.

Computer Communication Networks↗