| 1 |
Front Matter |
|
|
Abstract
|
| 2 |
Possibility-Probability Relation in Medical Models |
A. Bolotin |
|
Abstract
Medical models based on possibility theory are usually much simpler than those based on probability theory, but they lack foundations. The most foundational question is: How to obtain a possibility distribution for a modeling process? As one of the solutions, a simple framework is proposed built on the conjecture that a probability distribution for an uncertain process can be predicted by the process’s possibility distribution. The case of the perfect prediction and the case of possibility and probability distributions related less than perfect (modeling ”ideal body weight”) are considered in this paper.
|
| 3 |
How Exactly Do We Know Inheritance Parameters? |
Karl-Ernst Biebler,Bernd Jäger,Michael Wodny |
|
Abstract
There are different concepts to quantify the information contained in a data set. The classic result is from R.A.Fisher: Regarding a sample over a random variable. The Fisher-Information is defined under certain assumptions as the inverse of the Rao-Cramer barrier in the well known inequality of the same name. The Fisher-Informations are considered for the simplest genetic models of intheritance. This applies to medically relevant ranges of the inheritance model parameter and large data sets. The results are compared with exact calculations.
|
| 4 |
Tuning of Diagnosis Support Rules through Visualizing Data Transformations |
Leon Bobrowski,Magda Topczewska |
|
Abstract
Medical diagnosis support is often based on the case based reasoning (CBR) scheme. In accordance with this scheme, the record of a new patient is compared with similar records of previous patients with confirmed diagnosis. Such scheme has been implemented among others in the Hepar system, which comprises a hepathological database and a variety of procedures that aim at data analysis and the support of diagnosis. The diagnosis support rules of this system are based on the visualizing data transformations combined with the nearest neighbors technique. The applied transformations of data sets allow not only for data visualization but also for modifications of the distance or similarity measures used in the nearest neighbors technique. In this way, similarity measures can be induced from data sets.
|
| 5 |
Inductive Learning of Simple Diagnostic Scores |
Martin Atzmueller,Joachim Baumeister,Frank Puppe |
|
Abstract
Knowledge acquisition and maintenance in medical domains with a large application domain ontology is a difficult task. To reduce knowledge elicitation costs, semi-automatic learning methods can be used to support the expert..We propose . as a promising approach and present a method for inductive learning of diagnostic scores. It can be be refined incrementally by applying different types of background knowledge. We give an evaluation of the presented approach with a real-world case base.
|
| 6 |
A Virtual Approach to Integrating Biomedical Databases and Terminologies |
V. Maojo,M. García-Remesal,H. Billhardt,J. Crespo,F. Martín-Sánchez,A. Sousa-Pereira |
|
Abstract
INFOGENMED is an informatics and telematics project, funded by the IST directorate of the European Commission. In this paper, we present our current achievements and plans to develop a series of tools to provide on-line integration of remote medical and genetic databases through a common, Web-based browser. Users at research and professional settings will soon need guided access to a wide range of medical (e.g, clinical databases, medical records) and biological (e.g., genomic and proteomic databases) sources. Most of this information is currently located at different heterogeneous databases and data warehouses, including diverse schemas, vocabularies, query languages and restricted access. We have chosen a virtual repository approach for the project. We briefly describe an unification approach to integrate the contents of the databases. By using this kind of projects, users can access different remote sources and retrieve the information they are looking for. Once this information is available, different data analysis methods (such as data mining techniques) can be used in order to extract patterns and knowledge.
|
| 7 |
Data Mining with Meva in MEDLINE |
Holger Tenner,Gerda Roswitha Thurmayr,Rudolf Thurmayr |
|
Abstract
A simple search with PubMed in MEDLINE, the world’s largest medical database, results quite often in a listing of many articles with little relevance for the user. Therefore a medico-scientific data mining web service called Meva (MEDLINE Evaluator) was developed, capable of analyzing the bibliographic fields returned by an inquiry to PubMed. Meva converts these data into a well-structured expressive result, showing a graphical condensed representation of counts and relations of the fields using histograms, correlation tables, detailed sorted lists or MeSH trees. The user can specify filters or minimal frequencies to restrict the analysis in the data mining process. MeSH codes for MeSH terms may be listed. Furthermore he can limit the output on first authors. Results can be delivered as HTML or in a delimited format to import into any database.
|
| 8 |
Isobologram Analysis in MATLAB for Combined Effects of Two Agents in Dose-Response Experiments |
Stefan Wagenpfeil,Uwe Treiber,Antonie Lehmer |
|
Abstract
Isobologram analysis is a way of exploring and visualizing combined drug effects. The aim of this work is to determine as to whether two agents can be considered synergistic or antagonistic. Resulting from a clinical consulting case in urology we developed a MATLAB-based software tool for automated isobologram analysis. In this way we supplement the clinical software-equipment in our laboratory and encourage the evaluation of combined dose-response experiments. Analysis of an example data set demonstrates the approach and the way of interpreting obtained results.
|
| 9 |
Towards an Improved On-line Algorithm to Estimate the Fetal Heart Rate from Ultrasound Data |
Martin Daumer,Christian Harböck,Felix Ko,Christian Lederer,Thomas Schindler,Michael Scholz |
|
Abstract
We describe a new algorithm which estimates the fetal heart rate from ultrasound data. First comparisons show its potential to give a more reliable estimate of the true fetal heart rate than the algorithms embedded in standard CTG (cardio-toco-graphy) monitoring devices.
|
| 10 |
Health Monitoring by an Image Interpretation System – A System for Airborne Fungi Identification |
P. Perner,T. Günther,H. Perner,G. Fiss,R. Ernst |
|
Abstract
Human beings are exposed every day to bioaerosols in the various fields of their personal and/or professional daily life. The European Commission has rules protecting employees in the workplace from biological hazards. Airborne fungi can be detected and identified by an image acquisition and interpretation system. In this paper we present recent results on the development of an image interpretation system for airborne fungi identification. We explain the application domain and describe the development issues. The development strategy and the architecture of the system are described. Finally we give recent results and an outlook to future work.
|
| 11 |
Quantification and Characterization of Pulmonary Emphysema in Multislice-CT |
Oliver Weinheimer,Tobias Achenbach,Christian Buschsiewke,Claus Peter Heussel,Thomas Uthmann,Hans-Ulr |
|
Abstract
The new technology of the Multislice-CT provides volume data sets with approximately isotropic resolution, which permits a non invasive measurement of diffuse lung diseases like emphysema in the 3D space. The aim of our project is the development of a full automatic 3D CAD (Computer Aided Diagnosis) software tool for detection, quantification and characterization of emphysema in a thoracic CT data set. It should supply independently an analysis of an image data set to support the physician in clinical daily routine. In this paper we describe the developed 3D algorithms for the segmentation of the tracheo-bronchial tree, the lungs and the emphysema regions. We present different emphysema describing indices.
|
| 12 |
Interactive Visualization of Diagnostic Data from Cardiac Images Using 3D Glyphs |
Soo-Mi Choi,Don-Su Lee,Seong-Joon Yoo,Myoung-Hee Kim |
|
Abstract
This paper describes accurate methods for measuring diagnostic data in cardiology and presents new ideas on interactive data visualization with 3D glyphs to get better insight about the measured data. First, we reconstruct the 3D shape and motion of the left ventricle from cardiac images using our time-varying deformable model. Then we accurately compute ventricular volume, mass, wall thickness and wall motion in 3D or 4D spaces. The computed data are interactively visualized in a qualitative and quantitative manner and can be combined into a single glyph. Thus, glyph-based interactive visualization can encode more information and can give access to several aspects of diagnostic data at once. This perceptually easy interface is useful for many diagnostic and patient monitoring applications.
|
| 13 |
Predicting Influenza Waves with Health Insurance Data |
Rainer Schmidt,Lothar Gierl |
|
Abstract
In the recent years, many of the most developed countries have started to develop influenza surveillance systems, because influenza is the last of the classic plagues of the past, which still has to be brought under control and because influenza causes a lot of costs. Efforts have been undertaken on the basis of data from health centres. An alternative is to develop surveillance nets. General practitioners voluntary send reports about the influenza situation in their practise. We have developed a method to predict influenza waves on the basis of health insurance data. In this paper, we introduce different data sources and ideas how to predict influenza waves. We summarise our method, and the main part of the paper deals with first experimental results.
|
| 14 |
Fuzzy Inference Systems for Multistage Diagnosis of Acute Renal Failure in Children |
Marek Kurzynski |
|
Abstract
This paper presents fuzzy inference systems developed for the multistage pattern recognition. Two different methods of generating fuzzy if-then rules from empirical data are presented and their application to the computer-aided diagnosis of acute renal failure are discussed and compared with algorithms based on statistical model.
|
| 15 |
Data Imbalance in Surveillance of Nosocomial Infections |
Gilles Cohen,Mélanie Hilario,Hugo Sax,Stéphane Hugonnet |
|
Abstract
An important problem that arises in hospitals is the monitoring and detection of nosocomial or hospital acquired infections (NIs). This paper describes a retrospective analysis of a prevalence survey of NIs done in the Geneva University Hospital. Our goal is to identify patients with one or more NIs on the basis of clinical and other data collected during the survey. In this classification task, the main difficulty resides in the significant imbalance between positive or infected (11%) and negative (89%) cases. To remedy class imbalance, we propose a novel approach in which both oversampling of rare positives and undersampling of the non infected majority rely on synthetic cases generated via class-specific subclustering. Experiments have shown this approach to be remarkably more effective than classical random resampling methods.
|
| 16 |
An Outline of an Expert System for Diagnosis and Treatment of Bronchogenic Carcinoma |
I. Rodríguez-Daza,L. M. Laita,E. Roanes-Lozano,A. M. Crespo-Alonso,V. Maojo,L. de Ledesma,L. Laita |
|
Abstract
We present in this paper a “rule based knowledge system” for diagnosis and treatment of bronchogenic carcinoma. The rule based knowledge system consists of a “knowledge base”, an “inference engine” and a “graphical user interface”. For the sake of space, these three items will be described but not completely detailed here. The system is wholly described in the monograph [14] (in Spanish). The knowledge base contains the experts’ knowledge in form of logical expressions. The inference engine is a program that both verifies consistency of the knowledge base and extracts automatically consequences from the information used in building the knowledge base. The latter is implemented in the computer algebra language CoCoA and is based on a theory original of the team to which the authors belong. As the paper is intended for different audiences, this theory will be informally presented. A friendly graphical user interface facilitates the introduction of medical data.
|
| 17 |
Back Matter |
|
|
Abstract
|
发表于 2025-3-21 19:08:32
