Transcript health-grid-rector - School of Computer Science

Joined up Health and Bio Informatics:
Alan Rector
Bio and Health Informatics Forum/
Medical Informatics Group
Department of Computer Science
University of Manchester
[email protected]
www.cs.man.ac.uk/mig img.man.ac.uk
www.clinical-escience.org
mygrid.man.ac.uk
O p e n G A LE N
1
The Problem
• The next steps in exploiting our exploding
knowledge of basic biology depends on
understanding its relation with health and
disease.
• Health care is
– Deluged with information
• about generalities, policies, and theory
– Information and Knowledge Poor
• about specifics of patient care and outcomes
O p e n G A LE N
2
A Convergence of Need
• Post genomic
research
• Safe, high quality,
evidence based health
care
Need more and better clinical information
• Which scales
– In Size
– In Complexity
Knowledge is Fractal
O p e n G A LE N
3
A convergence of Technologies
• Post genomic
research
• Safe, high quality,
evidence based health
care
• Web/Grid/Semantic Web
• Ontologies & Information fusion
• Language technology
• Data mining and case based reasoning
• Healthcare records & standards
• Mobile devices
Open Collaborative Research
O p e n G A LE N
4
A Unique Time
• E-Science
• The Grid
• The Semantic Web / Grid
• BioInformatics Genomics/Proteomics…
• Massive investment in population medicine
• Massive investment in NHS computing
• Maturing Electronic Health Records
• …
Ride the Whirlwind!
O p e n G A LE N
5
Protocol/Collection-based research
Research
idea
Results
in vivo
Plausibility
in Silico/Collecto
Data Analysis
Tools
Shared
Collections
Models &
Standards
Data
Collection
Tools
Protocol
Approval Tools
Automatic Patient
Screening
O p e n G A LE N
Protocol
Authoring Tools
6
“Stones in the Road”
• Confidentiality, Privacy and Consent
– How to keep public confidence while enabling
research
• Information capture
– Speed and ease of use require language technology
• doctors dictate!
• Information integration
– Need common ontologies which bridge bio and
health information
O p e n G A LE N
7
One Response: CLEF
Joining up Health Care & Bioscience in Cancer
• Clinical e-Science Framework
– Clinical care
– Clinical research
– Clinical bioscience
• Genotype meets Phenotype
• New technologies for healthcare
– A focus to adapt new technologies to
healthcare
• New ways to do clinical research
– Faster, safer, easier, better
• Trial design, execution, archiving, reporting
O p e n G A LE N
8
CLEF
Towards and “end-to-end” solution
in an ethical framework
• Patient care
• Formulation of clinical studies
• Information capture
• Information representation
• Information analysis and integration
• Knowledge & hypothesis generation
• Clinical support
O p e n G A LE N
9
CLEF: A meeting of open technologies
• Organisational issues & Information governance
– Consent, Models of access, balance of research and privacy
• Information capture & quality
– Language technology + Ontologies (OpenGALEN & OWL) +
E Health Record (OpenEHR)
• Information use for Care
– E Health Record + Decision support + Ontologies + Language
generation
• Information Re-use for Research
– Pseudonymised E Health Record + Ontologies +
Metadata/repositories
O p e n G A LE N
10
CLEF: Language Technology
• Extraction of simple information from
clinical records
– Measures of reliability
• Pseudonomysation aids
• Language generation
– Validation
• “What you see is what you meant”
– Presentation
O p e n G A LE N
11
CLEF Logic-based Ontologies:
Conceptual Lego
“SNPolymorphism of CFTRGene causing Defect in MembraneTransport of ChlorideIon
causing Increase in Viscosity of Mucus in CysticFibrosis…”
“Hand which is
anatomically
normal”
OpenGALEN & OWL
O p e n G A LE N
12
Species
Bridging Scales with
Ontologies
Genes
Protein
Function
CFTRGene in humans
Disease
Protein coded by
(CFTRgene & in humans)
Membrane transport mediated by
(Protein coded by
(CFTRgene in humans))
Disease caused by
(abnormality in
(Membrane transport mediated by
(Protein coded by (CTFR gene & in humans))))
O p e n G A LE N
13
Avoiding combinatorial explosions
• The “Exploding Bicycle”
From “phrase book” to “dictionary +
grammar”
– 1980 - ICD-9 (E826) 8
– 1990 - READ-2 (T30..) 81
– 1995 - READ-3 87
– 1996 - ICD-10 (V10-19 Australian) 587
• V31.22 Occupant of three-wheeled motor vehicle injured in
collision with pedal cycle, person on outside of vehicle,
nontraffic accident, while working for income
– and meanwhile elsewhere in ICD-10
• W65.40 Drowning and submersion while in bath-tub, street
and highway, while engaged in sports activity
O p e n G A LE N
• X35.44 Victim of volcanic eruption, street and highway,
while resting, sleeping, eating or engaging in other vital
activities
14
Making it simple: Tools
• Logic based ontology (OWL) is the
assembler
– Write real ontologies in “high level languages”
• “Intermediate representations”
– Present real ontologies to be relevant to needs
• “Views”
• Scalable simplicity for end-users requires
sophisticated architecture
– “Swans paddle furiously under water”
• Decoupled distributed environment
– “Owned” by the domain experts
O p e n G A LE N
15
Summary
• Convergence of need in healthcare & post
genomic research
– Matched by convergence of technologies
• E-Science – an opportunity for collaboration
– Faster, less costly, more effective translation from
bioscience to health care
• Barriers to be overcome
– Information capture
– Privacy, confidentiality, & consent
– Information integration – sharing of meaning
• Common “Ontologies” are a key resource
O p e n G A LE N
16
CLEF Consortium
www.clinical-escience.org
• Bio Health Informatics Forum, Department of
Computer Science, University of Manchester
• Centre for Health Informatics and
Multiprofessional Education, University College
London
• Natural Langauge Group, Department of
Computer Science, University of Sheffield
• Judge Institute for Management Studies,
University of Cambridge
• Information Technology Research Institute,
University of Brighton
• Royal Marsden Hospital Trust
• North and North Central London
Cancer Networks
17
O p e n G A LE N