Lecture Notes in Computer Science 7451 CommencedPublicationin1973 FoundingandFormerSeriesEditors: GerhardGoos,JurisHartmanis,andJanvanLeeuwen EditorialBoard DavidHutchison LancasterUniversity,UK TakeoKanade CarnegieMellonUniversity,Pittsburgh,PA,USA JosefKittler UniversityofSurrey,Guildford,UK JonM.Kleinberg CornellUniversity,Ithaca,NY,USA AlfredKobsa UniversityofCalifornia,Irvine,CA,USA FriedemannMattern ETHZurich,Switzerland JohnC.Mitchell StanfordUniversity,CA,USA MoniNaor WeizmannInstituteofScience,Rehovot,Israel OscarNierstrasz UniversityofBern,Switzerland C.PanduRangan IndianInstituteofTechnology,Madras,India BernhardSteffen TUDortmundUniversity,Germany MadhuSudan MicrosoftResearch,Cambridge,MA,USA DemetriTerzopoulos UniversityofCalifornia,LosAngeles,CA,USA DougTygar UniversityofCalifornia,Berkeley,CA,USA GerhardWeikum MaxPlanckInstituteforInformatics,Saarbruecken,Germany Christian Böhm Sami Khuri Lenka Lhotská M. Elena Renda (Eds.) Information Technology in Bio- and Medical Informatics Third International Conference, ITBAM 2012 Vienna, Austria, September 4-5, 2012 Proceedings 1 3 VolumeEditors ChristianBöhm Ludwig-Maximilians-University,DepartmentofComputerScience Oettingenstraße67,80538München,Germany E-mail:[email protected]fi.lmu.de SamiKhuri SanJoséStateUniversity,DepartmentofComputerScience OneWashingtonSquare,SanJosé,CA95192-0249,USA E-mail:[email protected] LenkaLhotská CzechTechnicalUniversity,FacultyofElectricalEngineering DepartmentofCybernetics Technicka2,16627Prague6,CzechRepublic E-mail:[email protected] M.ElenaRenda IstitutodiInformaticaeTelematicadelCNR ViaG.Moruzzi1,56124Pisa,Italy E-mail:[email protected] ISSN0302-9743 e-ISSN1611-3349 ISBN978-3-642-32394-2 e-ISBN978-3-642-32395-9 DOI10.1007/978-3-642-32395-9 SpringerHeidelbergDordrechtLondonNewYork LibraryofCongressControlNumber:2012943467 CRSubjectClassification(1998):H.3,H.2.8,H.4-5,J.3,J.1 LNCSSublibrary:SL3–InformationSystemsandApplication,incl.Internet/Web andHCI ©Springer-VerlagBerlinHeidelberg2012 Thisworkissubjecttocopyright.Allrightsarereserved,whetherthewholeorpartofthematerialis concerned,specificallytherightsoftranslation,reprinting,re-useofillustrations,recitation,broadcasting, reproductiononmicrofilmsorinanyotherway,andstorageindatabanks.Duplicationofthispublication orpartsthereofispermittedonlyundertheprovisionsoftheGermanCopyrightLawofSeptember9,1965, initscurrentversion,andpermissionforusemustalwaysbeobtainedfromSpringer.Violationsareliable toprosecutionundertheGermanCopyrightLaw. Theuseofgeneraldescriptivenames,registerednames,trademarks,etc.inthispublicationdoesnotimply, evenintheabsenceofaspecificstatement,thatsuchnamesareexemptfromtherelevantprotectivelaws andregulationsandthereforefreeforgeneraluse. Typesetting:Camera-readybyauthor,dataconversionbyScientificPublishingServices,Chennai,India Printedonacid-freepaper SpringerispartofSpringerScience+BusinessMedia(www.springer.com) Preface Biomedicalengineeringandmedicalinformaticsrepresentchallengingandrapidly growing areas. Applications of information technology in these areas are of paramount importance. Building on the success of ITBAM 2010 and ITBAM 2011, the aim of the third ITBAM conference was to continue bringing to- getherscientists,researchers,andpractitionersfromdifferentdisciplines,namely, from mathematics, computer science, bioinformatics, biomedical engineering, medicine,biology,anddifferentfieldsoflifesciences,sothattheycanpresentand discusstheirresearchresultsinbioinformaticsandmedicalinformatics.Wehope that ITBAM will always serve as a platform for fruitful discussions between all attendees, where participants can exchange their recent results, identify future directions and challenges, initiate possible collaborative research, and develop common languages for solving problems in the realm of biomedical engineering, bioinformatics, and medical informatics. The importance of computer-aided diagnosis and therapy continues to draw attention worldwide and has laid the foundations for modern medicine with excellent potential for promising applications in a variety of fields, such as, telemedicine, Web-based healthcare, analysis of genetic information and per- sonalized medicine. Following a thorough peer-review process, we selected 12 longpapersandthreeshortpapersforthethirdannualITBAMconference.The OrganizingCommittee would like to thank the reviewers for their excellent job. The articles can be found in the proceedings and are divided into the follow- ingsections:MedicalDataMiningandInformationRetrieval;MetadataModels, Prediction,andMobileApplications;SystemsBiologyandDataMininginBioin- formatics.The papers show how broadthe spectrum of topics in applications of information technology to biomedical engineering and medical informatics is. The editors would like to thank all the participants for their high-quality contributions and Springer for publishing the proceedings of this conference. Once again, our special thanks go to Gabriela Wagner for her hard work on various aspects of this event. June 2012 Christian Bo¨hm Sami Khuri Lenka Lhotska M. Elena Renda Organization General Chair Christian Bo¨hm University of Munich, Germany Conference Program Chairs Sami Khuri San Jos´e State University, USA Lenka Lhotska Czech Technical University Prague, Czech Republic M. Elena Renda IIT - CNR, Pisa, Italy Program Committee Werner Aigner FAW Fuat Akal Functional Genomics Center Zurich, Switzerland Tatsuya Akutsu Kyoto University, Japan Andreas Albrecht Queen’s University Belfast, UK Lijo Anto Manjaly Antony CentreforBioinformatics,UniversityofKerala, India Rub´en Arman˜anzas Arnedillo University of the Basque Country, Spain Peter Baumann Jacobs University Bremen, Germany Balaram Bhattacharyya Visva-Bharati University, India Christian Blaschke Bioalma Madrid, Spain Andreas M. Boehm Rudolf Virchow Center for Experimental Biomedicine, Germany Veselka Boeva Technical University of Plovdiv, Bulgaria Gianluca Bontempi Universit´e Libre de Bruxelles, Belgium Roberta Bosotti Nerviano Medical Science s.r.l., Italy Rita Casadio University of Bologna, Italy So`nia Casillas Universitat Auto`noma de Barcelona,Spain Kun-Mao Chao National Taiwan University Vaclav Chudacek Czech Technical University in Prague, Czech Republic Coral del Val Mun˜oz University of Granada, Spain Hans-Dieter Ehrich Technical University of Braunschweig, Germany Mourad Elloumi University of Tunis, Tunisia Maria Federico University of Modena and Reggio Emilia, Italy Pedro Fernandes Inst.Gulbenkian de Ciˆencia, Portugal VIII Organization Christoph M. Friedrich University of Applied Sciences Dortmund, Germany Xiangchao Gan University of Oxford, UK Alejandro Giorgetti University of Verona, Italy Alireza Hadj Khodabakhshi Simon Fraser University, Canada Volker Heun Ludwig-Maximilians-Universita¨tMu¨nchen, Germany Chun-Hsi Huang University of Connecticut, USA Lars Kaderali University of Technology Dresden, Germany Alastair Kerr University of Edinburgh, UK Michal Kra´tky´ Technical University of Ostrava, Czech Republic Vaclav Kremen Czech Technical University in Prague, Czech Republic Josef Ku¨ng University of Linz, Austria Gorka Lasso CICbioGUNE, Derio, Spain Roger Marshall Plymouth State University, USA Elio Masciari ICAR-CNR, Universit`a della Calabria, Italy Henning Mersch RWTH Aachen University, Germany Aleksandar Milosavljevic Baylor College of Medicine, USA Jean-Christophe Nebel Kingston University, London, UK Vit Novacek NationalUniversity ofIreland,Galway,Ireland Nadia Pisanti University of Pisa, Italy Cinzia Pizzi Universit`a degli Studi di Padova, Italy Clara Pizzuti Institute for HighPerformanceComputing and Networking (ICAR)-National Research Council(CNR), Italy Meikel Poess Oracle Corporation, Redwood Shores, CA, USA Nicole Radde Universita¨t Stuttgart, Germany Stefano Rovetta University of Genova, Italy Cristina Rubio-Escudero University of Seville, Spain Nick Sahinidis Carnegie Mellon University, USA Roberto Santana UniversityoftheBasqueCountry(UPV/EHU), Spain Kristan Schneider University of Vienna, Austria Kathleen Steinhofel King’s College London, UK A Min Tjoa Vienna University of Technology, Austria Paul van der Vet University of Twente, The Netherlands Roland R. Wagner University of Linz, Austria Viacheslav Wolfengagen Institute JurInfoR-MSU, Russia Borys Wrobel Polish Academy of Sciences, Poland Filip Zavoral Charles University in Prague, Czech Republic Songmao Zhang Chinese Academy of Sciences, China Qiang Zhu The University of Michigan, USA Frank Gerrit Zoellner University of Heidelberg, Germany Table of Contents Session 1 Intelligent Data Acquisition and Scoring System for Intensive Medicine........................................................ 1 Filipe Portela, Manuel Filipe Santos, Jos´e Machado, A´lvaro Silva, Fernando Rua, and Ant´onio Abelha Data Mining in the Study of the Chronic Obstructive Pulmonary Disease ......................................................... 16 Maribel Yasmina Santos, Jorge Cruz, and Artur Teles de Arau´jo Practical Problems and Solutions in Hospital Information System Data Mining ......................................................... 31 Miroslav Bursa, Lenka Lhotska, Vaclav Chudacek, Jiri Spilka, Petr Janku, and Martin Huser Session 2 Using Generic Meta-Data-Models for Clustering Medical Data ......... 40 Dominic Girardi, Michael Giretzlehner, and Josef Ku¨ng A Mobile Based Authorization Mechanism for Patient Managed Role Based Access Control............................................. 54 Ca´tia Santos-Pereira, Alexandre B. Augusto, Manuel E. Correia, Ana Ferreira, and Ricardo Cruz-Correia Care@HOME: A Mobile Monitoring System for Patient Treatment and Blood Pressure Tracking .......................................... 69 Mersini Paschou, Efrosini Sourla, George Basagiannis, Evangelos Sakkopoulos, and Athanasios Tsakalidis Session 3 An Integrative Clustering Approach Combining Particle Swarm Optimization and Formal Concept Analysis ......................... 84 Anna Hristoskova, Veselka Boeva, and Elena Tsiporkova Link Prediction Approaches for Disease Networks .................... 99 Francesco Folino and Clara Pizzuti X Table of Contents Toward a Semantic Framework for the Querying, Mining and Visualization of Cancer Microenvironment Data ..................... 109 Michelangelo Ceci, Fabio Fumarola, Pietro Hiram Guzzi, Federica Mandreoli, Riccardo Martoglia, Elio Masciari, Massimo Mecella, and Wilma Penzo Session 4 Argumentation to Represent and Reason over Biological Systems ...... 124 Adam Wyner, Luke Riley, Robert Hoehndorf, and Samuel Croset The Use of Design Specificity in Standardized Mean Difference for Analysis of High throughput RNA Interference Screens ............... 139 Karol Kozak Toward a Translational Medicine Approach for Hypertrophic Cardiomyopathy ................................................. 151 Catia M. Machado, Francisco M. Couto, Alexandra R. Fernandes, Susana Santos, and Ana T. Freitas Poster Session Computational Sensemaking on Examples of Knowledge Discovery from Neuroscience Data: Towards Enhancing Stroke Rehabilitation..... 166 Andreas Holzinger, Reinhold Scherer, Martin Seeber, Johanna Wagner, and Gernot Mu¨ller-Putz The Database of the CardiovascularSystem Related Signals........... 169 Jan Havl´ık, Lucie Kuˇcerova´, Imrich Kohu´t, Jan Dvoˇra´k, and Vratislav Fabi´an Patient Monitoring Using Bioimpedance Signal ...................... 171 Jan Havl´ık, Ondˇrej Fousek, and Miroslav Loˇzek Author Index.................................................. 173 Intelligent Data Acquisition and Scoring System for Intensive Medicine Filipe Portela1, Manuel Filipe Santos1, José Machado2, Álvaro Silva3, Fernando Rua3, and António Abelha2 1 Centro Algoritmi, University of Minho, Guimarães, Portugal {cfp,mfs}@dsi.uminho.pt 2 CCTC, University of Minho, Braga, Portugal {jmac,abelha}@di.uminho.pt 3 Serviço de Cuidados Intensivos, Centro Hospitalar do Porto, Hospital Santo António, Portugal [email protected] [email protected] Abstract. In a critical area as is Intensive Medicine, the existence of systems to support the clinical decision is mandatory. These systems should ensure a set of data to evaluate medical scores like is SAPS, SOFA and GLASGOW. The value of these scores gives the doctors the ability to understand the real condition of the patient and provides a mean to improve their decisions in order to choose the best therapy for the patient. Unfortunately, almost all of the required data to obtain these scores are recorded on paper and rarely are stored electronically. Doctors recognize this as an important limitation in the Intensive Care Units. This paper presents an intelligent system to obtain the data, calculate the scores and disseminate the results in an online, automatic, continuous and pervasive way. The major features of the system are detailed and discussed. A preliminary assessment of the system is also provided. Keywords: Intensive Medicine Scores, Real Time, Pervasive System, Scoring System, SAPS, SOFA, GLASGOW. 1 Introduction During the last three decades, several physiological-based prognostic models have emerged [1]. In 1980, the severity scoring systems were introduced in the Intensive Care Units (ICUs) [2]. Intensive-care medicine score systems serve to quantify the severity of diseases and to characterize patient groups on the basis of objective criteria [1]. The scores describe patient severity by adding up points. As main objectives, they: assess the prognosis; establish the amount of treatment required; provide information on the prognosis of patients; indicate the efficacy of therapeutic interventions; and serve for the stratification in clinical studies and workload [2], helping doctors in the decision process. In the ICU a high number of scoring systems are used that can be grouped in: diseases, patient and universally mortality prediction. This work has been developed in the context of INTCare research project [3], an intelligent decision support system that makes use of online learning to predict the C. Böhm et al. (Eds.): ITBAM 2012, LNCS 7451, pp. 1–15, 2012. © Springer-Verlag Berlin Heidelberg 2012 2 F. Portela et al. organ failure and the outcome of the ICU patients. The work developed was only focused on the scores that have variables that are used by Decision Support System, i.e., SAPS, SOFA and Glasgow. In the context of INTCare, a new set of data had to be acquired in order to induce Data Mining (DM) models able to predict the organ failure and the outcome of the patients. These scores rarely were stored in an electronic way. As a normal procedure, the nurses / doctors calculate these scores by consulting the patient’s bed side monitors, interpreting the lab results and reading admission documents in an offline mode. The existence of multiple data sources for each organic system [4] difficult the evaluation of the variables by the human and, consequently, can delay / interfere negatively in the decision making process. For the development of INTCare system this situation was unaffordable. The inexistence of all data in an electronic mode and in real time made impossible the construction of prediction models. Those limitations dictated the development of a completely new scoring system to collect the data and to score the measures in real- time. A lot of research has been done to understand how it would be possible to acquire and prepare the necessary data. An intelligent agent based approach has been followed to perform crucial tasks such as the automatic data acquisition and the online scoring. The main goal of the project was the concentration of the decision support tasks in a single platform. According to Keegan [1] there are several limitations inherent to the ICU prognostic models: i) errors in data collection and data entry, flaws in development and validation of the models; ii) variables used to make predictions may not be easily measured; and some laboratory values may not be routinely obtained. The lack of standardization in obtaining values leads to missing data and to the fault of important prognostic variables, compromising the performance of the models [5]. The empirical experience accumulated in this field of acting allowed the development of a system able to overcome the limitations described above. This system has been deployed in the ICU of the Centro Hospitalar do Porto (CHP), Porto, Portugal. This paper presents an intelligent scoring system to feed DM models as a way to predict the organ failure and the outcome of the ICU patients. Chapter one introduces the problematic and the subject, the second chapter makes an overview of the situation and explains the main concepts. Chapter three present the data manipulation process. Chapters four and five will present the scoring system and the results achieved. The preliminary results of a study on the technological acceptance are presented. Finally, some conclusions will be done about the work and the future work. 2 Background It is common sense that in the ICU a set of clinical measures should be used regularly. Many of the scoring processes are executed manually and require a high level of human intervention. Currently there are systems able to collect all data produced during the day and execute some scoring. An example of this is the system presented by Shabot [6] where “Three measures of severity of illness are automatically calculated for each adult ICU patient on admission and again daily”. When the scores are calculated manually the value considered are not the worst among the measured values but the worst value registered by someone. This configures a major limitation.