Skip to main content

Über dieses Buch

Biomedical engineering and medical informatics are challenging and rapidly growing areas. Applications of information technology in these areas are of paramount imp- tance. The aim of the first ITBAM conference was to bring together scientists, - searchers and practitioners from different disciplines (mathematics, bioinformatics, biology, medicine, biomedical engineering and computer science) having such c- mon interests. We hope that ITBAM conferences will provide opportunities for fru- ful discussions between all attendees and provide a platform where participants can exchange their most recent results, identify future directions and challenges, initiate possible collaborative research and system development, and develop common l- guages for solving problems in the realm of biomedical engineering, bioinformatics and medical informatics. The importance of computer-aided diagnosis and therapy has drawn more and more attention worldwide and laid the foundation for modern medicine with excellent potential for promising applications such as telemedicine, Web-based healthcare and analysis of genetic information. For this conference, after a peer-review process, we finally selected 13 long papers and 8 short papers that are now published in this volume. They are divided in to the following groups: workflow management and database; decision support and data management in biomedicine; medical data modelling and information retrieval; data mining in bioinformatics; knowledge representation and data management in bio- formatics; biological data and signal processing. The papers show how broad the spectrum of topics in applications of information technology to biomedical engine- ing and medical informatics is.



Workflow Management and Database

e-BioFlow: Improving Practical Use of Workflow Systems in Bioinformatics

Workflow management systems (WfMSs) are useful tools for bioinformaticians. As experiences with using WfMSs accumulate, shortcomings of current systems become apparent. In this paper, we focus on practical issues that hinder WfMS users and that arise in the design and execution of workflows, and in access of web services. We present e-BioFlow, a workflow engine that demonstrates in which way a number of these problems can be solved. e-BioFlow offers an improved user interface, can deal with large data volumes, stores all provenance, and has a powerful provenance browser. e-BioFlow also offers the possibility to design and run workflows step by step, allowing its users an explorative research style.

Ingo Wassink, Matthijs Ooms, Pieter Neerincx, Gerrit van der Veer, Han Rauwerda, Jack A. M. Leunissen, Timo M. Breit, Anton Nijholt, Paul van der Vet

MEDCollector: Multisource Epidemic Data Collector

This paper analyzes the requirements and presents a novel approach to the development of a system for epidemiological data collection and integration based on the principles of interoperability and modularity. Accurate and timely epidemic models require the integration of large, fresh datasets. Thus, from an e-science perspective, collected data should be shared seamlessly across multiple applications. This is addressed by our approach, MEDCollector, trough workflow design enables the extraction of data from multiple Web sources. The mapping of extracted entities to ontologies will guarantee the consistency within gathered datasets, and therefore enhance epidemic modeling tools.

João Zamite, Fabrício A. B. Silva, Francisco Couto, Mário J. Silva

Epidemic Marketplace: An Information Management System for Epidemiological Data

The Epidemic Marketplace is part of a computational framework for organizing data for epidemic modeling and forecasting. It is a distributed data management platform where epidemiological data can be stored, managed and made available to the scientific community. It includes tools for the automatic interaction with other applications through web services, for the collection of epidemiological data from internet social networks and for discussion of related topics. This paper defines its requirements, architecture and implementation plan based on open-source software. This platform will assist epidemiologists and public health scientists in finding, sharing and exchanging data.

Luis F. Lopes, Fabrício A. B. Silva, Francisco Couto, João Zamite, Hugo Ferreira, Carla Sousa, Mário J. Silva

Decision Support and Data Management in Biomedicine

DCM Data Management Framework: A Data Warehousing Approach

In health care systems the contribution of Information Technology (IT) has proven to have a dynamic role in supporting the quality of care provided to the general population. Dementia Care Mapping (DCM), an observational tool to assess the quality of care for people with dementia, still depends on spreadsheet based tools for data storage and analysis. This system does not comply with the emerging needs of DCM data to store, share, track, and compare overtime in order to monitor progress and trends in care quality. In this paper we provide an overview of the DCM system, identify the need for data management and we propose a DCM data management framework based on a data warehousing approach to facilitate the data collection, storage, sharing and analysis in an organised and consistent manner. We show the sequence of steps (designing relational and dimensional databases) required to transform DCM data into required information.

Shehla Khalid, Claire Surr, Daniel Neagu

Automatic Classification of Intrapartal Fetal Heart-Rate Recordings – Can It Compete with Experts?

Fetal heart rate (fHR) is used to evaluate the fetal well-being during the delivery. It provides information of fetal status and allows doctors to detect ongoing hypoxia. Routine clinical evaluation of intrapartal fHR is based on description of macroscopic morphological features of its baseline. In this paper we show, that by using additional features for description of the fHR recordings, we can improve the classification accuracy. Additionally since results of automatic signal evaluation are easily reproducible we can objectify the whole process, thus enabling us to focus on the underlying reasons for high expert inter-observer and intra-observer variability.

Václav Chudáček, Jiří Spilka, Michal Huptych, George Georgoulas, Petr Janků, Michal Koucký, Chrysostomos Stylios, Lenka Lhotská

Clinical Informatics to Diagnose Cardiac Diseases Based on Data Mining

The Emergency Department (ED) has been frustrated by the problems of overcrowding, long waiting times, and high costs over decades. With the development of computer techniques, various kinds of information systems have appeared and made people work more effectively. The Emergency Department Information System (EDIS) has been heralded as a “must” for the modern ED, which can enhance patients care, decrease the waiting time and cost, and alleviate the problem of overcrowding. This paper targets at building an engine of use in an EDIS. Based on the frameworks of patients flow in ED, real-world data were collected from the electronic medical records at the Emergency Department: more than 210000 records of 842 registered chest pain patients in total. By utilizing the data mining techniques, an engine of an expert system was proposed to help physicians with faster and more accurate decision making of diagnosis and lab test selections.

Sung Ho Ha, Zhen Yu Zhang

Decision Support in Biomedicine (Short Papers)

The Case-Based Software System for Physician’s Decision Support

Human body is an example of an object for which it is really impossible to build the exact behavior model. Case-Based Reasoning is a practical decision making technique used to emulate human thinking process. The article describes an approach to building intellectual systems based on Case-Based Reasoning and Data Mining techniques. A software system for physician’s decision support in diagnostics and treatment selection is used as an example. This approach is based on identifying classes within the case base. The similarity measure is introduced. This measure is especially useful when the current case is incompletely described and gets to class intersection.

Leonid Karpov, Valery Yudin

SASAgent: An Agent Based Architecture for Search, Retrieval and Composition of e-Science Models and Tools

Scientific Computing is a multidisciplinary field that goes beyond the use of computer as machine where researchers write simple texts, presentations or store analysis and results of their experiments. Considering the increase use of computer resources applied to experiments and simulations, it is notable that the research groups are at a new level of scientific computing, well represented by e-Science domain. This work aims to propose an architecture, based on intelligent agents, to search, retrieve and compose simulation models, generated within research projects related to scientific domains. The SASAgent architecture is described and a case study is presented. Preliminary results suggest that the proposed architecture is promising to achieve requirements found in e-Science projects.

Luiz Felipe Mendes, Regina Braga, Fernanda Campos

Clustering of Protein Substructures for Discovery of a Novel Class of Sequence-Structure Fragments

In this paper, we propose a novel method for clustering of protein substructures that we developed to study the relationships between protein sequences and their corresponding structures. We show the results of the comparison to other commonly used methods for clustering of protein structures. Finally, we outline a procedure for finding sequence profiles that tend to occur in more than one structural conformation but the number of their structural conformations is limited. This procedure is based on our method for protein substructure clustering.

Ivana Rudolfova, Jaroslav Zendulka, Matej Lexa

A Comorbidity Network Approach to Predict Disease Risk

A prediction model that exploits the past medical patient history to determine the risk of individuals to develop future diseases is proposed. The model is generated by using the set of frequent diseases that contemporarily appear in the same patient. The illnesses a patient could likely be affected in the future are obtained by considering the items induced by high confidence rules generated by the frequent diseases. Furthermore, a phenotypic comorbidity network is built and its structural properties are studied in order to better understand the connections between illnesses. Experimental results show that the proposed approach is a promising way for assessing disease risk.

Francesco Folino, Clara Pizzuti, Maria Ventura

Mining and Post-processing of Association Rules in the Atherosclerosis Risk Domain

The paper presents a novel approach to post-processing of association rules based on the idea of meta-learning. A subsequent association rule mining step is applied to the results of ”standard” association rule mining. We thus obtain ”rules about rules” that help to better understand the association rules generated in the first step.

A case study of applying this approach to data about atherosclerosis risk is described in the paper.

Petr Berka, Jan Rauch

Medical Data Modeling and Information Retrieval

Optimized Column-Oriented Model: A Storage and Search Efficient Representation of Medical Data

Medical data have a number of unique characteristics like data sparseness, high dimensionality and rapidly changing set of attributes. Entity Attribute Value (EAV) is the widely used solution to handle the above challenges of medical data, but EAV is neither storage efficient nor search efficient. In this paper, we have proposed a storage & search efficient data model: Optimized Column-Oriented Model (OCOM) for physical representation of high dimensional and sparse data as an alternative of widely used EAV. We have implemented both EAV and OCOM models in a medical data warehousing environment and performed different relational and warehouse queries on both the models. The experimental results show that OCOM is dramatically search efficient and occupy less storage space compared to EAV.

Razan Paul, Abu Sayed Md. Latiful Hoque

A Semantic Query Interface for the OGO Platform

In the last years, a number of semantic biomedical systems have been developed to store biomedical knowledge in an accessible manner. However, their practical usage is limited, since they require expertise in semantic languages by the user, or, in the other hand, their query interfaces do not fully exploit the semantics of the knowledge represented. Such drawbacks were present in the OGO system, a resource that semantically integrates knowledge about orthologs and human genetic diseases, developed by our research group. In this paper, we present an extension of the OGO system for improving the process of designing advanced semantic queries. The query module requires the users to know and to manage only the OGO ontology, which represents the domain knowledge, simplifying the process of query building.

José Antonio Miñarro-Giménez, Mikel Egaña Aranguren, Francisco García-Sánchez, Jesualdo Tomás Fernández-Breis

BioMedical Information Retrieval: The BioTracer Approach

With the large amount of biomedical information available today, providing a good search tool is vital. Such a tool should not only be able to retrieve the sought information, but also to filter out irrelevant documents, while giving the relevant ones the highest ranking. Focusing on biomedical information, the main goal of this work has been to investigate how to improve the ability for a system to find and rank relevant documents. To achieve this, we apply a series of information retrieval techniques to search in biomedical information and combine them in an optimal manner. These techniques include extending and using well-established information retrieval (IR) similarity models like the Vector Space Model (VSM) and BM25 and their underlying scoring schemes, and allowing users to affect the ranking according to their view of relevance. The techniques have been implemented and tested in a proof-of-concept prototype called BioTracer, extending a Java-based open source search engine library. The results from our experiments using the TREC 2004 Genomic Track collection seem promising. Our investigation have also revealed that involving the user in the search will indeed have positive effects on the ranking of search results, and that the approaches used in BioTracer can be used to meet the user’s information needs.

Heri Ramampiaro

Data Mining in Bioinformatics

A Self-organizing State Space Approach to Inferring Time-Varying Causalities between Regulatory Proteins

A number of methods based on time-dependent state space models have been proposed for inferring time-varying gene regulatory networks. These methods are capable of detecting a relatively small number of topological changes in gene regulatory networks. However, they are insufficient since there is a greater number of changes in the gene regulatory mechanisms; the function of a regulatory protein frequently changes due to post-translational modification, such as protein phosphorylation and ATP-binding. We propose a self-organizing state space approach to inferring consecutive changes in causalities between regulatory proteins from gene expression data. Hidden regulatory proteins are identified using a test-based method from genome-wide protein-DNA binding data. Application of this approach to cell cycle data demonstrated its effectiveness.

Osamu Hirose, Kentaro Shimizu

Knowledge Representation and Data Management in Bioinformatics

Retrieving Samples from Biobanks

Biobanks are extremely important resources for medical research: they collect biological material (samples) and data describing this material. Biobanks provide medical researchers with material and data they need for their studies. Data availability varies greatly among samples and makes the retrieval of data and identification of relevant samples a strenuous task. We show the challenges and limitations when using pure SQL statements for querying a relational database. To tackle the problem of locating interesting material we present a novel approach which automatically generates approximate queries with ranking capabilities. Medical researchers use a Query By Example interface to specify desired attributes and restrictions and assign weights to them to influence the ranking function.

Claus Dabringer, Johann Eder

Logical Knowledge Representation of Regulatory Relations in Biomedical Pathways

Knowledge on regulatory relations, in for example regulatory pathways in biology, is used widely in experiment design by biomedical researchers and in systems biology. The knowledge has typically either been represented through simple graphs or through very expressive differential equation simulations of smaller sections of a pathway.

As an alternative, in this work we suggest a knowledge representation of the most basic relations in regulatory processes



positively regulates


negatively regulates

in logics based on a semantic analysis. We discuss the usage of these relations in biology and in artificial intelligence for hypothesis development in drug discovery.

Sine Zambach, Jens Ulrik Hansen

Smooth Introduction of Semantic Tagging in Genotyping Procedures

Concepts and tools from research on the Semantic Web have found widespread application in the classification of biomedical literature works and research results. A more substantial advantage could come from the semantic classification of any kind of documents from research, or even from ordinary diagnostic test: this may pave the way to building an impressive, semantically searchable knowledge base. The use of semantic tagging at this operating level is hampered by the lack of proper tools. In this paper we present an approach to introduce semantic tagging in genotyping test procedures. A formal analysis of the process workflow is crucial to pinpoint stages where tagging might be applied. Later, an enriched Enterprise Content Management system allows the archiving of test documents, whose metadata can encompass terms from any kind of ontologies. The flexibility and the usability of the system represent key factors for an actual, widespread introduction of semantic tagging in this field.

Alessio Bechini, Jacopo Viotto, Riccardo Giannini

Biological Data and Signal Processing

Laboratory Kit for Oscillometry Measurement of Blood Pressure

This paper presents a laboratory kit for oscillometry blood pressure measurement. The laboratory kit was designed for research purposes in the field of medical technology. The presented device allows to show not only the calculated results (such as systolic and diastolic blood pressure and the heart rate) as standard devices, but also the raw signals. It means there is a possibility to study the impact of set-up parameters and other factors on the measured values.

Jan Dvořák, Jan Havlík

Initial Analysis of the EEG Signal Processing Methods for Studying Correlations between Muscle and Brain Activity

The paper presents an analysis of EEG signal processing methods for studying correlations between human muscle and brain activity. The main task of this work is to design the methods of EEG signal processing and to verify them on artificial and real signals. The paper introduces methods of EEG processing in time and frequency domain.

Helena Valentová, Jan Havlík

Highlighting the Current Issues with Pride Suggestions for Improving the Performance of Real Time Cardiac Health Monitoring

Electrocardiogram (ECG) signal utilized by Clinicians to extract very useful information about the functional status of the heart. Of particular interest systems designed for monitoring people outdoor and detecting abnormalities on the real time. However, there are far from achieving the ideal of being able to perform adequately real time remote cardiac health monitoring in practical life. That is due to problematical challenges. In this paper we discuss all these issues, furthermore our intimations and propositions to relief such concerns are stated.

Mohamed Ezzeldin A. Bashir, Dong Gyu Lee, Makki Akasha, Gyeong Min Yi, Eun-jong Cha, Jang-whan Bae, Myeong Chan Cho, Keun Ho Ryu


Weitere Informationen

Premium Partner

Neuer Inhalt

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.



Product Lifecycle Management im Konzernumfeld – Herausforderungen, Lösungsansätze und Handlungsempfehlungen

Für produzierende Unternehmen hat sich Product Lifecycle Management in den letzten Jahrzehnten in wachsendem Maße zu einem strategisch wichtigen Ansatz entwickelt. Forciert durch steigende Effektivitäts- und Effizienzanforderungen stellen viele Unternehmen ihre Product Lifecycle Management-Prozesse und -Informationssysteme auf den Prüfstand. Der vorliegende Beitrag beschreibt entlang eines etablierten Analyseframeworks Herausforderungen und Lösungsansätze im Product Lifecycle Management im Konzernumfeld.
Jetzt gratis downloaden!