John Fox

Marius Fieschi

Rolf Engelbrecht

The current scarcity of expert systems where the reasoning is based on Bayesian probability theory may be due to misconceptions about probabilities found in the literature. As argued by Cheeseman (1985), these misconceptions have led to the attitude: "The Bayesian approach doesn't work - so here is a new scheme". Several of these expert systems based on ad hoc "probability" concepts have been successful in a number of ways, demonstrating the necessity of being able to handle uncertainty in medical expert systems. They also demonstrate the need for a theoretically sound handling of uncertainty. In Andersen et al. (1986) it was postulated that knowledge organized in a causal network can be used for a unified approach to the main tasks of a medical expert system: diagnosis, planning of tests and explanations. The present paper explores this postulate in a causal probabilistic network. It also provides a practical demonstration that the problems supposedly associated with probabilistic networks are either non-existent or that practical solutions can be found. This paper reports on the methods implemented in MUNIN* -an expert system for electromyography (EMG) (Andreassen et al. 1987). EMG is the diagnosis of muscle and nerve diseases through analysis of bioelectrical signals from muscle and nerve tissue. In Andreassen et al.

European Conference on Artificial Intelligence in Medicine Marseilles, August 31st – September 3rd 1987 Proceedings

AIME 87

Peter McNair

György Surján

MIE 2002 is the XVIIth international conference of the European Federation of Medical Informatics. Today, mankind builds up the information society, enabled by the underlying rapid development in computer technology. The significance of the spread of the internet is comparable to the significance of Gutenberg's invention. On one hand it both helps dissemination of data and knowledge and sharing of ideas. On the other hand the achievements may divide the society, as did non-literacy deprive many people from knowledge throughout centuries. Today millions of people are isolated from an incredibly large amount of information because of "computer non-literacy," and a new elite mastering the information society has appeared. However, the ease of production and dissemination of information may foster thoughtless communication, and has lead to a flood of information and disinformation. We have to learn how to behave in this new situation, in which the dissemination of information - at an international level - is totally uncontrolled. In the area of medical or health informatics these questions are more serious. Lack of information, false or inadequate information, as well as improper interpretation of accurate information may seriously harm patients. And the process may go out of control of the physician, i.e. patients can "treat" themselves just by visiting some health sites on the net. Everybody may throw a message in a bottle in information flood, and everybody may pick up messages at any time. Can we do anything to ensure that all messages are valid? Can we guarantee that our messages reach the intended audience? Can we secure that content has not changed on its way? Do we know that people getting our messages will interpret them correctly? Are we able to understand the intention of a sender, when we get a message totally out of context? These questions build up the framework of MIE2002.

Proceedings of MIE2002

Health Data in the Information Society

Steen Andreassen

Jeremy Wyatt

The knowledge-based management of medical acts in NUCLEUS -- Knowledge Acquisition, Representation & Learning -- Knowledge Representation and Modelling in HYBRIKON -- Knowledge Organisation in Medical KBS Construetion -- A Framework for Modular Knowledge Bases in the Domain of Hypertension Diseases -- KAVAS-2: Knowledge Acquisition, Visualisation and Assessment System -- KAVAS's Framework for quality assessment of medical knowledge -- KAVAS's Conditioning of the Induction Algorithm -- Clinical decision-support in the field of TETANUS serology using an associative storage model implemented in LISP -- Model based learning support to knowledge acquisition: A clinical case study -- MODELS FOR MEDICAL KNOWLEDGE REPRESENTATION AND MEDICAL REASONING IN A C.A.I SYSTEM -- Case Based Reasoning in Clinical Evaluation -- Object-oriented mentality: the most suited paradigm for medical knowledge-based systems -- Applications Based on Neural Nets -- Classification of protein patterns using neural networks: pixel based versus feature based approach -- Evaluation of an epiderniological data set as an example of the application of neural networks to the analysis of large medical data sets -- A Neural Network Modular System for Object Classification in Brain MR Images -- A Neural Network Identifies Faces with Morphological Syndromes -- Grading of Gliomas in Stereotactic Biopsies with Neural Networks -- Self Organizing Maps for the Evaluation of High Resolution ECG -- AUTHOR INDEX

Proceedings of the 4th Conference on Artificial Intelligence in Medicine Europe, 3-6 October 1993, Munich

Artificial Intelligence in Medicine

A variety of topics of bio-informatics, including both medical and bio-medical informatics are addressed by MIE. The main theme in this publication is the development of connections between bio-informatics and medical informatics. Tools and concepts from both disciplines can complement each other.

Rolf Engelbrecht

Books

Your next favorite book is out there