Transcript Document
Termkonferens 2003 Network of Excellence: Semantic Interoperability and Data Mining in Biomedicine [SemanticMining] Hans Åhlfeldt - Linköpings universitet – Co-ordinator Gunnar Klein - Karolinska institutet Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining EUs sjätte ramprogram FP6 • Integrated Project - IP – storskaliga forsknings- och utvecklingsprojekt – industrinära, applikationsnära, produktutveckling • Network of Excellence - NoE – nätverk, motverka fragmentisering, främja samverkan – europeisk forskning världsledande – long term - “self-sustainable network” • ”Traditionella” projekt och utbytesprogram – FP1 - FP5 – forsknings- och utvecklingsprojekt – utbytesprogram för forskare och studenter Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining FP6 - tematiska områden • • • • • • • biomedicin informationsteknologi … ... hållbar tillväxt rymdforskning livsmedel, jordbruk … ... Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining IST - Information Society Technologies • eHealth • Semantic-based Knowledge Systems Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining SemanticMining • Semantic Interoperability and Data Mining in Biomedicine • 25 partners från 11 länder • 100 forskare, 34 doktorander Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Application Areas... ...Research Areas Knowledge engineering Ontology engineering Coding, indexing and information retrieval Data mining, knowledge extraction and representation Natural Language Processing The Semantic Web Health Statistics …to support application areas Health Care Information and decision support Infrastructure for health care information systems Bioinformatics Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining NoE SemanticMining • Network is not about harmonising software devices or delivering common services • Network is about harmonising knowledge representation strategies and ontologies – Ontology and knowledge queries pervade all levels of semantic web architecture (not just middleware) – Can’t take result of one query, and use it as argument in next query to a different service, if KR strategies and ontologies are inconsistent, or not compatible Termkonferens 5-6 nov 2003 Information Models NLP Ontologies Applications Domain Ontologies Decision Support Models Network of Excellence SemanticMining Ongoing projects Ongoing, nationally or EU-funded research projects – – – – – – – – – – Swedish/Nordic evaluation of SNOMED CT Machine translation based on parallel corpus The German Specialist Lexicon MEDTAG - text tagging and retrieval, Swiss-Prot MedO - domain ontology for medicine CLEF, OntoWeb, OpenGALEN EBI - Gene Ontology, ORIEL, BioBabel Electronic Health Record ECHI - European Community Health Indicators HDP - Hospital Data project (comparing hospital activity across EU) Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Research areas • • • • • • • Ontology engineering Multilingual medical dictionary SNOMED CT Health care statistics Data mining and information retrieval Concept systems for laboratory medicine The electronic health record Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Integration activities • Sharing of knowledge and research tools – workshops – common web site • Mobility program – researchers, PhD students • Summer school 2004 • Educational material • Contribution to standards Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Contribution to Standards • CEN / ISO – – – – • Gunnar Klein (TC 251 Chairman ) Anders Thurin (Vocabulary for Terminological Systems Project leader ) Magnus Fågelberg (European Terminology Group Convenor ) Dipak Kalra (TC 251) IUPAC – Urban Forsum (C-NPU, IFCC-IUPAC Chair) • HL7 – Dipak Kalra - Electronic Health Records – Jeremy Rogers, Alan Rector – vocabulary, terminology • W3C / Semantic Web / OWL – Robert Stevens, Jeremy Rogers • SWISS-PROT, Gene Ontology de facto standards – EBI, Midori Harris • OMG Life Sciences Research Domain Task Force – EBI Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining REFTERM - SNOMED CT • Several separate nationally funded evaluations • Interest from Nordic National Boards of Health to co-operate across Europe in evaluating SNOMED • NoE will support and coordinate ... • Methods for machine translation based on parallel corpora • Development of multi-lingual medical dictionary • Translation and evaluation of SNOMED CT Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Förädling av medicintexter till detaljerade termbanker NLPLAB, Institutionen för datavetenskap, LiU Lars Ahrenberg, Magnus Merkel, Michael Petterstedt i samarbete med Medicinsk informatik, LiU Mikael Nyström, Hans Åhlfeldt i samarbete med Karolinska institutet, KI Gunnar Klein, Gunnar Nilsson, Rong Chen Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Ordlänkning (word alignment) • Parallellställa textsegment på ord- och frasnivå – Input: parallella dokument (dvs. original och motsvarande översättning) – Output: 1) tvåspråkig termbank på ord- och termnivå, 2) detaljerad lingvistisk information om översättningskorrespondenser. Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Parallell corpus - källterminologier på svenska och engelska • • • • ICD10, KSH97, KSH97P ICF NCSP MeSH Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Källterminologier Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Exempel Bryta ned till kortare, mer specifika termer – sv: psykiska språkfunktioner eng: mental functions of language – sv: eng: – sv: eng: psykiska mental språkfunktioner functions of language – sv: Andra specificerade anemier orsakade av enzymrubbningar eng: Other anaemias due to enzyme disorders – sv: eng: – sv: eng: – sv: eng: – sv: eng: – sv: eng: Termkonferens 5-6 nov 2003 andra other specificerade NULL anemier anaemias orsakade av due to enzymrubbningar enzyme disorders Network of Excellence SemanticMining I*Link – interaktiv träning Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining I*Trix - Automatisk länkning Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Partners in SemanticMining Academia Dept Biomedical Engineering/Medical Informatics, Linköping University, Sweden Dept of Computer Science, Linköping University, Sweden Karolinska Institutet, Stockholm, Sweden Sahlgrenska University Hospital, Göteborg, Sweden Dept of Medical Informatics, Computational Linguistics, Freiburg University, Germany Dept of Computer Science, Freiburg University, Germany Institute of Formal Ontology and medical Information Science (IFOMIS), Leipzig, Germany Institute of Informatics and Applied Mathematics, University of Kiel, Germany Division of Medical Informatics, Geneve University Hospital, Switzerland Dept of Computer Science, University of Manchester, UK Centre for Health Informatics and Multiprofessional Education, University College London, UK The Information Technology Research Institute, University of Brighton, UK Public Health and Medical Informatics Laboratory , Broussais University Hospital, Paris, France Institute of Cognitive Science (CNR – ISTC), Laboratory for Applied Ontology, Roma, Italy Institutes, Health and Welfare Organisations European Bioinformatics Institute (EBI), Hinxton, UK National Institute and Library for Health Information, Budapest, Hungary The Nordic Terminology Network (Public Health and Welfare Organisations in the Nordic Countries) WHO Collaborating Centre for Classification of Diseases in the Nordic countries Committee Nomenclature, Properties and Units in Laboratory Medicine (C-NPU) Enterprises Merrall-Ross International Ltd, Cheshire, UK European Dynamics, Greece Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining NoE SemanticMining • • • • • • • Ontology engineering Multilingual medical dictionary SNOMED CT Health care statistics Data mining and information retrieval Concept systems for laboratory medicine The electronic health record Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining Management • Decision making – The Assembly (all members) – The Board (elected annually by assembly) • Flexible steering – Committees, Work packages, Annual budgeting • Communication – web service, group-ware • Management Office – – – – Co-ordinator’s Office (Hans Åhlfeldt, Hans Gill) International Office Director (Johan Åkerman, Ann-Christine Comstock) Legal Advisor (Göran Hessling) Management Advisory Group (Magnus Holmström) Termkonferens 5-6 nov 2003 Network of Excellence SemanticMining