Showing papers on "Clinical decision support system published in 1992"

A layman's guide to the U.S. health care system.

Abstract: This article provides an overview of the U.S. health care system and recent proposals for health system reform. Prepared for a 15-nation comparative study for the Organization for Economic Cooperation and Development (OECD), the article summarizes descriptive data on the financing, utilization, access, and supply of U.S. health services; analyzes health system cost growth and trends; reviews health reforms adopted in the 1980s; and discusses proposals in the current health system reform debate.

The Emergence of Artificial Intelligence as a Reference Discipline for Decision Support Systems Research

Abstract: It is timely and appropriate to examine both philosophical and pragmatical issues associated with formalizing the adoption of artificial intelligence as a reference discipline for decision support systems research This paper reflects on where we were when the first special issue of Decision Sciences on expert systems and decision support systems was published, addresses the dynamics of what has taken place subsequent to the publication of that first special issue, sets forth a proposition to stimulate ongoing dialog with respect to synergies between the decision support system research agenda and the research agenda of the artificial intelligence discipline, and demonstrates how the papers appearing in this follow-up special issue of Decision Sciences are representative of an emerging, challenging, and exciting new decision support systems era

A critical appraisal of the literature on the effects of computer-based clinical decision support systems on clinician performance and patient outcomes

Abstract: OBJECTIVE: To review the evaluations of computer-based clinical decision support systems (CDSS's). DATA SOURCES: The literature collected in the MEDLARS, EMBASE, SCISEARCH and INSPEC databases was searched from 1974 to the present. The reference lists of relevant articles were reviewed as were conference proceedings. STUDY SELECTION: Prospective, controlled studies were included. Studies were rated for methodological quality. DATA EXTRACTION: Study quality was assessed and data on study setting, subjects, method of allocation, and computer system were collected and verified using a structured form. CONCLUSIONS: There is considerable heterogeneity in both systems evaluated and design features of those systems. Future evaluations of CDSS's should focus on methodological issues in order to enhance overall quality of evaluations.

A method for assessing the impact of a computer-based decision support system on health care outcomes.

Abstract: The wide variation in utilization of diagnostic resources has not been decreased by the proliferation of new diagnostic technologies. We wish to test the hypothesis that the introduction of a medical decision support system into clinical practice could potentially lead to more efficient use of diagnostic information, and therefore lead to a reduction in overall laboratory use and cost of care. We have devised and are currently implementing a randomized controlled trial of a computer based decision support system, the University of Pittsburgh version of Quick Medical Reference (QMR). The main purpose of the study is to determine the effect of the QMR program on specific outcome measures: length of hospital stay, number and types of diagnostic tests ordered, and overall charges. An important part of this evaluation is relating the initial level of diagnostic uncertainty expressed by the admitting housestaff team to utilization of diagnostic resources. The purpose of this paper is to describe the methodology for carrying out this controlled trial, and to describe our initial experiences with its implementation.

Qualitative frameworks for decision support: lessons from medicine

Abstract: Some weaknesses of current decision support technologies are discussed. Numerical methods have strong theoretical foundations but are representationally weak, and only deal with a small part of the decision process. Knowledge-based systems offer greater flexibility, but have not been accompanied by a clear decision theory. Theoretical development of symbolic decision procedures is advocated, an approach to the design of decision support systems based on first-order logic is presented, and work on this approach is reviewed. A central proposal is an extended form of inference called argumentation ; reasoning qualitatively for and against decision options from generalized domain theories. Argumentation captures a natural and familiar form of reasoning, and contributes to the robustness, flexibility and intelligibility of problem solving, while having a clear theoretical basis. Argumentation was developed initially for medical applications though it may have much wider applicability.

Strategic decision support in preventive health care.

Abstract: This nontechnical interdisciplinary paper highlights major principles of strategic decision support in preventive health care and points to selected key literature. It begins by looking at preventive health care from strategic perspectives such as determinants of health, health care costs, objectives of prevention, political order constellations and available data. Next, the paper identifies strategic decisions and decision-making to be supported. Having gained strategic perspective, it discusses tools for decision support. These tools are here related to two planning steps (i) assessment, problem and goal analysis; and (ii) design and choice of alternative interventions. Qualitative as well as quantitative aspects of computer-assisted policy analysis in preventive health care are outlined and examples presented.

The Design of a Knowledge-Based Decision Support System to Support the Information Analyst in Determining Requirements

Abstract: Decision support system (DSS) researchers and designers continue to look for unstructured organizational tasks where there is a critical need for intelligent computer-based support. One such decision task is information requirements determination. Requirements determination is recognized as the most crucial phase of the systems development life cycle. Unfortunately, most methodologies and CASE tools focus only on how to specify the requirements once they are determined. There is very little computer support for the process of determining requirements. This paper discusses the conceptual design and development of a knowledge-based DSS to support information analysts in the critical decision task of determining requirements for the design of effective information systems. The expert modeling support system has the expertise to assist the analyst in studying the organization as a whole and in modeling the system under study in the context of the overall organization's goals and needs. The focus of the paper is on the problems associated with building the knowledge base component of the intelligent decision support system. A prototype implementation of the system is described.

Development of indicators for quality assurance in public health medicine.

Abstract: OBJECTIVES--To develop structure, process, and outcome indicators within a quality rating index for audit of public health medicine. DESIGN--Development of an audit matrix and indicator of quality through a series of group discussions with public health physicians, from which self administered weighted questionnaires were constructed by a modified Delphi technique. SETTING--Five Scottish health boards. SUBJECTS--Public health physicians in the five health boards. MAIN MEASURES--Indicators of quality and a quality rating index for seven selected service categories for each of seven agreed roles of public health medicine: assessment of health and health care needs in information services, input into managerial decision making in health promotion, fostering multisectoral collaboration in environmental health services, health service research and evaluation for child services, lead responsibility for the development and/or running of screening services, and public health medicine training and staff development in communicable disease. RESULTS--Indicators in the form of questionnaires were developed for each topic. Three types of indicator emerged: "global," "restricted," and "specific." A quality rating index for each topic was developed on the basis of the questionnaire scores. Piloting of indicators showed that they are potentially generalisable; evaluation of the system is under way across all health boards in Scotland. CONCLUSION--Measurable indicators of quality for public health medicine can be developed.

The Physician-Computer Connection: A Practical Guide to Physician Involvement in Hospital Information Systems

Abstract: From the Publisher: To support the critical role of physicians in the successful implementation of a patient care information system (PCIS), the authors detail a plan for developing physician task forces and "physician champions" and suggest innovative ways to train physicians to use the technology effectively.This revised edition covers the influence of managed care on information systems, the benefits of clinical decision support to a PCIS, and such emerging technologies as telemedicine, wireless computing, and clinical applications of the World Wide Web.

Knowledge Engineering Issues for Decision Support

Abstract: Decision support systems (DSS) are widely used throughout the financial services industry. Unlike expert systems, which aim to replace expert decision making in narrow domains, decision support systems allow cooperation between user and system to improve the quality of decision making. In DSS a machine’s number-crunching and memory capability is coupled with human common sense, subjective judgment, and sensitivity to context. The areas in which humans are strong are generally those areas where experts systems are weak; so it seems appropriate to design cooperative systems recognizing this. Although expert systems and decision support systems have much in common, important differences between them mean that knowledge acquisition for DSS must be considered in its own right.

Introduction to Decision Support

Abstract: The best and fastest way of learning the most complex things in life is playing. Playing often involves objects as images of the real world such as a doll or a teddy bear. These objects are representations of reality which allow for experimentation without fatal consequences (Gagne 1984). MultiObjective Decision Support Systems (MODSS) can play this role in environmental management. The complexity of the environment, the time scale and the diversity of environmental effects is such that the implications of decisions affecting the environment are beyond the imagination of most people involved. Instead of trying to explain all the ins and outs of a problem to people involved in a decision, an object - in the form of a learning device - could be made available to these people that enables them to play around with the problem. By including the available knowledge on problems in Decision Support Systems (DSS) these systems can perform the role of such an object, thus allowing for experimentation without fatal consequences to the environment. A MODSS puts specific emphasis on using the results of experiments in complex decision environments involving many objectives and/or many participants. The aim of this book is to develop an instrument that makes complex environmental problems manageable by coupling the intellectual resources of individuals with the capabilities of the computer. A MODSS provides assistance in interpreting and communicating results and in using the results to invent new ideas and creative solutions.

Medical education and decision support using network-based multimedia information resources.

Abstract: We are witnessing a proliferation of information resources potentially useful to the health care professional, both for direct patient care, assistance in problem solving and decision making, and continuing medical education. Nonetheless, amid this feast of potential capability, there is little coordination, a high degree of diversity, and growing difficulty in identifying, locating and being able to use the resources needed in a particular situation. A major part of the problem is the lack of an information technology infrastructure adequate to address these issues. In this paper we characterize the information needs of professional work of the health care practitioner. We then describe a future information technology environment to meet these needs, and the relevant underlying information technologies and methodologies. We illustrate this future environment via a prototype information architecture that has been under development in our laboratory and is being used for a variety of our current applications. Finally, we discuss some of the implications of the transition to such an environment.

Linking psychiatric registers to decision support systems

Abstract: This paper discusses the concept of Psychiatric Register Integrated Support Modules (PRISM). It addresses issues around the linkage of longitudinal data held on individual patients in case register systems to expert and other decision support systems. The paper describes two developed systems which link to the SafetyNet case register system, an inexpensive and comprehensive Mental Health Information System which runs on single or networked computers and which was previously described in detail (Taylor & Bhumgara, 1989). The merits of the two approaches in aiding clinical decision making on anti-psychotic medication are discussed as are the medico-legal implications of using expert systems.

A framework for integrating decision support systems into office information systems

Abstract: Office information system is presented as a network of decision support systems where the basis of linking decision support systems between them are decision making situations. After introducing concept of the network, basic components of it are briefly described. According to this context a model of decision support system which allows integration of different today known types of decision support systems is derived. Proposed network and model could be used as a framework for researching office information systems from a decision support systems view.

Health Care and Decision Making

Abstract: The status of the elderly in American society has changed remarkably within the last fifty years. People live longer and they appear to be in better health than their elders in earlier years.’ The elderly also comprise a larger proportion of the population than ever before.’

Critical Care Decision Support Systems

Abstract: It is not enough to merely manage medical information. It is difficult to justify the cost of hospital information systems (HIS) or intensive care unit (ICU) patient data management systems (PDMS) on this basis alone. The real benefit of an integrated HIS or PDMS is in decision support. We recently went to the bedside of a critically ill patient and counted the current information categories (not repeated measures) that were reviewed for physician decision making. The total was in excess of 236! Dr. Eddy summarized it best: “It is simply unrealistic to think that individuals can synthesize in their head scores of pieces of evidence, accurately estimate the outcomes of different options, and accurately judge the desirability of those outcomes for patients…. All confirm what would be expected from common sense: The complexity of modern medicine exceeds the inherent limitations of the unaided human mind.” Although there are a variety of HIS and ICU PDMS systems available there are few that provide ICU decision support.

Decision support in medicine — Where, when, how?

Abstract: The development of decision support systems in medical domains has encountered problems both with the research agenda and usability and utility of the empirical results. This paper discusses the problems briefly and points out some issues concerning where, when and how medical decision support systems could be successfully designed. Also the potential contribution of a new discipline, Computer Supported Cooperative Work for the development work is briefly outlined.

Soft systems approach to information problems at the structural level of health care

Abstract: Different forces are increasing the need for improved methods that measure quality in health care. Elements of structure, process, and outcome need to be identified, defined, and monitored in order to assess quality of health care. Systems theory and methodology have been applied to a broad spectrum of health care problems. Much of the analytical work has taken place at the process/operational level. Accordingly, the information/decision processes are usually supported at the operational/managerial level. The information bases for decisions and action-taking at the structure and policy level however, require further analysis and research. In this research, a problem situation regarding information access and use was identified at the structure level of a "health care system". The problem focused on the barriers, values, and impact of scientific and technical information, as assessed by 36 physicians who play the role of regional coordinators for conducting activities on health education and research within the "system". The hypothesis underlying this work is that a Soft Systems approach can be used as a methodology to understand and learn about the information problems that exist at the structure level of a "health care system". It is estimated that through the inquiry process of Soft Systems Methodology, results can contribute to identify a pathway whereby the role of information access and use on quality of health, at the structure-process and process-outcome levels of health care be established. Soft Systems Methodology was useful both (1) to tackle information problems at the structure level of health care; and (2) to enrich the different concepts of human activity systems that participate in the delivery of health care at the structure, process, and outcome levels. This research provided a model to such approach. Recommendations and further lines of research are also proposed.

Intelligent health care information systems: are they appropriate?

Abstract: The application of artificial intelligence (AI) in health care has had a long history of great promise. Striking success has been claimed in areas such as computer aided diagnosis, although contradictory evidence has also appeared. The progression toward intelligent decision support systems (IDSS) appears to be a logical, and perhaps inevitable, one. The author, however, is not convinced that IDSS is an appropriate technology at this stage in the development of health care systems. The concern is that IDSS may not encourage good software development practice. The enthusiasm for delivering mechanisms of AI may seriously detract from the mundane, but essential, tasks of ensuring: match with user and organisational requirements, good design, reliability, robustness, maintainability, and scaleability. The author recommends the increasing use of DBMS technology for health care ISs before IDSS is considered further.

Causal probabilistic modelling for clinical decision support in the high dependency environment

Abstract: A physiologically-based model of the relevant cardiovascular, respiratory and associated processes of a patient resident in a high dependency environment is described. The model will be implemented using a Causal Probabilistic Network, and will be tuned to represent the individual patient. It will provide advice, for instance regarding changes in ventilator therapy, and the model will also be used to detect and correct equipment malfunction and operator error.

Perspectives on Health Reporting for the European Community

Abstract: The steps towards more integration of the European Community will affect health systems and health care in a number of ways. To support policy development and decision-making, health and health system information is needed on Community level. We discuss the role.of the Community in health and health care. We examine the state of health-related information for health policies and the relevant dimensions of a reporting system. At present, wide gaps exist between information needs and availability. Information on ongoing health-related activities is not co-ordinated. Comparative data can only be drawn from differing national sources or non-Community international compilations. For a future reporting system, the political decisions on the role of health in the Community and its administrative implementation are a major determinant. The development of a health reporting system is a comprehensive management task that requires significant input of resources, including research.

Decision Support Systems in Intensive Care

Abstract: The concept of decision support is probably not familiar to the majority of physicians working in intensive care. According to Shortliffe [1], a medical decision support system is “any computer program designed to help health care professionals to make clinical decisions”. The definition includes all decision aids dealing with medical data or knowledge necessary to interpret such data regardless of the computer-science technology used.