By Topic

Intelligent Decision Support Systems and Medicine, IEE Colloquium on

Date 15 Jun 1992

Filter Results

Displaying Results 1 - 12 of 12
  • IEE Colloquium on `Intelligent Decision Support Systems and Medicine' (Digest No.143)

    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (16 KB)  

    The following topics were dealt with: practical and theoretic applications of AI in medicine, including fuzzy logic and neural networks; medical decision support systems; intelligent tutoring systems for medicine; frameworks for system development; predictive data entry in medical records; and medical diagnostic systems View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An expert system for the mechanical ventilator settings

    Page(s): 1/1 - 1/3
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (144 KB)  

    An expert system is described which has been designed to provide a prototype system for the development and management of mechanical ventilator settings, by using the system more effectively to support human knowledge processing. The principal objective is to build and implement an expert system for a mechanically controlled ventilator used on patients in the intensive care unit (ICU), and to assist the clinician by adding a measurement interpretation and evaluation capability to the existing monitoring system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A family therapy expert system: a practical application of expert systems in the area of psychological diagnosis

    Page(s): 2/1 - 215
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (368 KB)  

    A discussion is given on a psychiatric expert system that has been in use for over two and a half years at the Family Therapy Unit of Springfield Hospital in London. The article begins by describing briefly the kind of work that is conducted by the unit and the computing needs that this work involves. It then goes on to describe the system itself and closes by offering some comments about the possibilities for future development of the system and by making some concluding remarks View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent health care information systems: are they appropriate?

    Page(s): 3/1 - 3/3
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (132 KB)  

    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 View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The application of unsupervised artificial neural networks to the sub-classification of subjects at-risk of Huntington's Disease

    Page(s): 5/1 - 5/9
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (404 KB)  

    The contingent negative variation (CNV), which is an evoked response in the human electroencephalogram (EEG), was measured for a number of Huntington's disease patients (HDs) and subjects at-risk of developing HD (ARs), and for equal numbers of matched normal subjects. The sampled voltage response values and the duration of the CNV were then used as input data to Kohonen and ART2 unsupervised artificial neural networks to classify the subjects. The two methods gave similar results for the HDs vs normals which also agreed with the results of a cluster analysis. The results of attempting to identify abnormal ARs showed that the ART2 results showed partial agreement with the results of the Kohonen network and cluster analysis. The application of these unsupervised neural networks to the sub-typing of clinical categories appears to offer a relatively simple tool suitable for hardware implementation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IMPLANTOR-an intelligent tutoring system for orthopaedic repair

    Page(s): 11/1 - 11/4
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (224 KB)  

    The research reported is centred on the development of an intelligent tutoring system called IMPLANTOR (intelligent medical planning techniques for orthopaedic repair). IMPLANTOR has been designed to assist novice orthopaedic surgeons practice and develop their skills in decision making and management processes. The application domain is focused on the methods of treatment for orthopaedic repair, giving special attention to internal fixation. IMPLANTOR provides an experiential learning environment through a computer-based simulation, using a combination of artificial intelligence methods and computer-aided design CAD techniques. IMPLANTOR is structured as a syllabus, presenting case-studies of progressively increasing complexity to be solved by the learner. The system critiques acceptable decisions by indicating positive and negative aspects as well as potential risks. Unacceptable solutions are refuted with an analysis of the reasons for that. Some of the difficulties for knowledge elicitation for IMPLANTOR are described View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Predictive data entry in medical records

    Page(s): 8/1 - 8/3
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (124 KB)  

    Work on predictive data entry arises out of the PEN&PAD(GP) project which is developing a clinical workstation for use by general practitioners. Recently, this approach has been extended to the hospital-based care of elderly patients-PEN&PAD(Geriatrics). The goal of PEN&PAD is to develop systems which can be routinely used by doctors, nurses, physiotherapists etc, and which will replace paper medical records. To achieve this goal, the system must be able to capture all significant clinical information. Furthermore, this information must be held in a structured format so that the system can organise the information for the healthcare professional as well as being able to generate valid aggregation of data. At the same time, experience is that the system must be quick and intuitive to use so that healthcare professionals can enter data directly without this interrupting their dialogue with the patient. Predictive data entry emerged from user centred design studies with GPs as the only technique which offered solutions to the dual problems of expressive adequacy on the one hand, and speed and ease of use on the other View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy logic-based and neural network-based reasoning with application to blood pressure management

    Page(s): 4/1 - 4/3
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (160 KB)  

    Two distinctive approaches to the implementation of approximate reasoning in rule-based fuzzy decision-making and control systems are presented. While the first approach, based on possibility theory, bears some resemblance to a traditional event-driven inference system with the incorporation of fuzzy concepts, the second scheme, based on the technique of neural networks, represents a substantial departure from the traditional one and shows some promise in dealing with these fundamental issues. To demonstrate the applicability of the proposed approaches, a problem of multivariable fuzzy management of blood pressure has been studied using the simulation method View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy hypothesis trees and decision making

    Page(s): 6/1 - 6/4
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (148 KB)  

    A new interpretation of decision tree induction is provided. A method is suggested to infer the class of an object using fuzzy relations. It is shown that this new method has several advantages over previous ones in knowledge representation. It can handle vague and incomplete evidence to correctly classify the objects. The problem of unknown evidence is also representable in a uniform way View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of the inconsistency in assessing the probability of subjective events

    Page(s): 7/1 - 7/3
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (116 KB)  

    The problems underlying the interrogation of experts and the presentation of knowledge are evident in the vivid polemic now underway among AI researchers about the best way of acquisition, presentation and processing of knowledge in an atmosphere of uncertainty in knowledge-based systems. This controversy is of vital importance in view of the fact that most human decisions are taken in an environment of uncertainty. The author defines problems necessitating a subjective judgment, such as the problems whose solution involves the services of a human expert. The vast majority of evaluations are based on the expert's personal experience. An empirical implementation from the field of medical diagnostics is presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent medical multimedia-based tutoring systems: design issues

    Page(s): 101 - 103
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (152 KB)  

    The application of computer technology to the teaching of medicine has been attempted with varying success over the years, but newer technology and better development tools suggest that a change in the style of application software is about to take place and that computer assisted learning may soon be commonplace in medical schools. The authors address some of the design features of two intelligent medical tutoring systems developed by the research group. The first is in regular use as part of an undergraduate curriculum and the second currently under development. The main emphasis of the authors on the second system for its use of multimedia resources View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A model based toolkit for building medical diagnostic support systems in developing countries

    Page(s): 9/1 - 916
    Save to Project icon | Click to expandQuick Abstract | PDF file iconPDF (432 KB)  

    One of the most appealing potential applications for artificial intelligence in developing countries is the construction of medical expert systems for use in areas where medical expertise is unavailable or thin on the ground. What is needed is a tool that provides knowledge structuring facilities that can be used by local experts in developing countries and does not require them to become knowledge engineers. This tool is for them, to build and maintain medical diagnostic support systems easily which are locally appropriate in both form and content. The author describes a knowledge acquisition system for medical diagnosis which uses a model-based approach. The system is in the form of a toolkit which is used to construct medical diagnostic support systems with appropriate domain and task knowledge. The toolkit has two main elements; a tool for building a task model and a tool for structuring and fleshing out a domain model. The emphasis is on providing the local expert with facilities which will enable them to enter their knowledge in a familiar form, rather than forcing them to learn a new and alien methodology View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.