Date(s) - 15/01/2013
1:30 pm - 5:00 pm
Institute of Psychiatry
Mental Health Biomedical Research Centre and Dementia Unit Bioinformatics Group
TITLE: Mining electronic health records: towards better research applications and clinical care
DATE: Tuesday 15th January 2013, 2:00pm – 5:00pm
LOCATION: Wolfson Lecture Theatre, Institute of Psychiatry,
Denmark Hill Campus, Kings College London
16 De Crespigny Park , London SE5 8AF
1.30pm – Registration
2.00pm – Tackling text: mining unstructured data in the South London and Maudsley NHS Foundation Trust Clinical Records Interactive Search (CRIS) system (slides)
Dr Angus Roberts, University of Sheffield
2.30pm – BioMart: Driving a paradigm change in biomedical data management (slides)
Dr Arek Kasprzyk, BioMart lead (ex EBI/OICR)
3.00pm – Standardising the representation of clinical information: for patient care and for research (slides)
Professor Dipak Kalra, University College London
3.30-3.45pm – Tea Break (15mins)
3.45-4.00pm – Addressing the Big Data challenges in Translational Medicine
Dr Jonathan Sheldon, Global Senior Director of Translational Medicine at Oracle
4.00pm – Mining electronic health records: towards better research applications and clinical care (title tbc)
Professor Søren Brunak, Technical University of Denmark
5.00pm – Refreshments, then visit to the Phoenix pub (located next to Denmark Hill rail station)
Location map: http://www.kcl.ac.uk/campuslife/campuses/denmarkhill/index.aspx
Please register by sending an email to firstname.lastname@example.org with subject “register”.
2.30pm – Dr Angus Roberts, University of Sheffield
Title: Tackling text: mining unstructured data in South London and The Maudsley NHS Trust Clinical Records Interactive Search (CRIS) system
Biography: After working for ten years as a biomedical scientist in a large district general hospital, Angus Roberts retrained as a computer scientist, and returned to the NHS to develop audit and clinical information systems. This led him to research on the representation of clinical information using medical terminologies and ontologies, and then to an MRC bioinformatics studentship on the natural language processing of medical records. He is currently a research fellow at the University of Sheffield, where he leads life science related projects for GATE, the world-leading architecture for language engineering. Current projects include a large-scale search and access system for medical information; mining the literature to assist with rapid vaccine development; and information extraction from the South London and The Maudsley NHS Trust Clinical Records Interactive Search (CRIS) system.
2.30pm – Dr Arek Kasprzyk, BioMart lead (ex EBI/OICR)
Title: BioMart: driving a paradigm change in biomedical data management
Biography: Arek designed and implemented BioMart (www.biomart.org), an innovative open source software for biomedical research, which provided the first large scale federated data management solution at the European Bioinformatics Institute in Hinxton, United Kingdom. While BioMart’s original goal was to manage data from the Human Genome Project hosted by the Sanger Institute, it has since grown to become a multi-institute collaboration involving a large number of different database projects and 28 different scientific organizations on five continents: Asia, Australia, Europe, North America and South America.
As a result of this success, he was personally recruited by the Ontario Institute for Cancer Research (OICR) in Toronto, Canada to lead the International Cancer Genome Consortium Data Coordination Center, and create the architecture to manage their data, which will eventually be equivalent to 50,000 Human Genome Projects. Under his leadership and guidance, the developers and scientists re-engineered the BioMart software and achieved this ambitious goal 2 years ahead of schedule. This accomplishment resulted in the publication of the November 2011 issue of Database: The Journal of Biological Databases and Curation solely dedicated to BioMart (http://oxfordjournals-marketing.oup.com/q/1MozDkVONg1Q1p/wv). Shortly after, BioMart was featured in the January 2012 issue of Nature Methods featuring novel adaptive technologies (http://www.nature.com/nmeth/journal/v9/n1/full/nmeth.1815.html).
3.00pm – Professor Dipak Kalra, UCL
Title: Standardising the representation of clinical information: for patient care and for research
Biography: Professor Dipak Kalra plays a leading international role in research and development of electronic health record architectures and systems. His interests include the requirements and models needed to ensure the robust long-term preservation of clinical meaning and protection of privacy. He leads CEN and ISO Task Forces producing international standards on Electronic Health Records communications, personal health records, EHR architecture requirements, and he has contributed to several standards relating to EHR security and confidentiality. He is a member of HL7 and IHE UK. He is involved in European research projects on EHR system quality labelling, semantic interoperability and clinical knowledge discovery.
He and his team are partners in a new EU funded Framework 7 project focussing on enabling the re-use of electronic health record information for clinical research, alongside ten global pharmaceutical companies. He is also a partner in European projects on EHR system quality and on semantic interoperability, and in two Wellcome Trust / MRC projects on the modelling, interpretation and protection of research data warehouses in HIV and cardiovascular epidemiology. Dipak and his research team have developed and deployed electronic health record systems that support shared care for chronic conditions, in cardiology (north London) and in mental health (Berkshire).
Dipak is a consultant to the NHS (England) on clinical information modelling, clinical data structures and archetypes, and terminology binding, and an advisor to the European Commission on semantic interoperability.
Dipak is a Director of the openEHR Foundation, Vice President for research of the EuroRec Institute, and advisor to the European Commission on semantic interoperability. He is a former London GP. He was previously a GP for eight years in a deprived part of east London and co-led the development of an NHS accredited GP system used within east London.
3.30-3.45pm – Tea Break (15mins)
3.45-4.00pm – Jonathan Sheldon, Ph.D., Global Senior Director of Translational Medicine at Oracle
Title: Addressing the Big Data challenges in Translational Medicine
Biography: Previously, Dr. Sheldon was Chief Scientific Officer at InforSense, (acquired by IDBS) where he was responsible for the company’s strategic direction in the life science and healthcare markets, as well as managing the technical services group responsible for customer implementations. Prior to InforSense, he was Chief Technology Officer for Confirmant Ltd, where he was responsible for developing the company’s proteomics products and services. He also established the first bioinformatics group and was Head of Bioinformatics for five years at Roche Welwyn, UK. Dr. Sheldon holds a Ph.D. in Molecular Biology/Biochemistry from the University of Cambridge.
4.00-5.00pm – Prof Søren Brunak, Director, Center for Biological Sequence Analysis, Department of Systems Biology, Technical University of Denmark
Title: Mining electronic health records: towards better research applications and clinical care (title tbc)
Biography: Søren Brunak, Ph.D., is professor of Bioinformatics at the Technical University of Denmark and professor of Disease Systems Biology at the University of Copenhagen. Prof. Brunak is the founding Director of the Center for Biological Sequence Analysis, which was formed in 1993 as a multi-disciplinary research group of molecular biologists, biochemists, medical doctors, physicists, and computer scientists. Søren Brunak has been highly active within data integration, where machine learning techniques often have been used to integrate predicted or experimentally established functional genome and proteome annotation. With 120 employees it is one of the large bioinformatics and systems biology centers in Europe. His current research does combine molecular level systems biology and healthcare sector data such as electronic patient records and biobank questionnaires. Recent work has included extracting disease phenotypes and adverse drug reactions from electronic patient records and he recently published a paper in Nature Review Genetics ‘Mining electronic health records: towards better research applications and clinical care’ (http://www.ncbi.nlm.nih.gov/pubmed/22549152). The aim is to group and stratify patients not only from their genotype, but also phenotypically based on the clinical descriptions in the medical records. Søren Brunak is a member of EMBO
Bookings are closed for this event.