The vision of a HealthGrid
Sofie NØRAGER
European Commission
DG INFSO, eHealth unit
Outline of the presentation

Introduction to the HealthGrid

Some examples of Grid Imaging projects
eH E A L T H - R&D ACTIVITIES
from
PAST 10 years (1991-2002)
“INFORMATION Technology
“M to m”
for HealthCare”
to
FUTURE 10 years (2003-2014)
“KNOWLEDGE Technology for Health”
“m to M”
1989-1990 1991-1994 1995-1998 1999-2002
2003-2006
2007-2010
2011-2014
1. E-Molecule: Bioinformatics
FP2
FP3
FP4
Computers
for
Doctors
Networks
for
HealthCare
Professionals
User
Needs
Approach
FP5
Societal DG RTD
Demands
@
Budget
Budget
Budget
Budget
20M €
100M €
140M €
200M €
Projects
Projects
Projects
Projects
30
63
158
125
Results
Results
Results
Results
batch of
Products
EU Health
Feasibility
AIM
Community
Study
1st
Telematics
Industry
2. E-cellule/tissue:
neuroinformatics
3. E-Individual: Medical
Informatics
Electromagnetic Fields
Others
RESEARCH
TELECOM
POLICIES
Regional - National Plans
DG SANCO supports: Public Health Policy
DG INFSO supports: eHealth 2002 + 2005,
eHealth Ministerial Conference 2005,
TEN/TELECOM, etc
DG REGIO, RELEX, EMP, ENT…
supports
Others
eEUROPE
- eHEAlth
Synergy between Medical Informatics, Bioinformatics, and
Neuroinformatics:
Knowledge Empowering Individual Health Care & Well-Being
1.Medical Informatics (MI)
2.Bioinformatics/Genomics (BI)
citizen, patient and population
informatics
Medical
Sciences
IT
•Electronic Health Record (EHR)
•Health Informatics/Telematics
Standards
•Clinical Decision Support
•Intelligent Agent Systems for
Health
•Telemedicine
•Safety and Security
•etc.
B
example: Informatics
in support of the next
generation of brain
research: Molecular
Neuroscience
Behavioral
Sciences
Social Sciences
molecular informatics
A
D
•Structural Genomics
•Functional Genomics
•Proteomics
•Biochip Technologies
•Advanced Data Clustering and
Analysis Techniques
•Computational Biology
•Ethics
•etc.
C
•Biosignal Analysis and Pattern
Recognition Systems
•Neuro Algorithms
•Neurocell Technology
•Human Computer Interfaces
•Machine Learning
•Knowledge Discovery
•etc.
3.Neuroinformatics (NI)
cell to organ informatics
Biological
Sciences
example: Advancing
into the molecular
causes of diseases:
Molecular Medicine
example: Exploiting
human genetics
variation for
individualized
health care:
Individualized
Health Care
example: Gene expression
imaging in the brain or
integration of genomic and
neuroscience databases:
Neurogenomics
example: Modeling of structure and
function of molecules, cells, systems in
disease: Health Knowledge Science
DG INFSO.B.1/JCH/CVD/ 14.XII.2001/ “rings”
v19/10/2001
“European” Research Area
» now is the time to bring our endeavours together and to
build a research and innovation equivalent of the "common
market" for goods and services. That structure is called the
European Research Area and is regrouping all Community
supports for the better coordination of research activities and
the convergence of research and innovation policies, at
national and EU levels. «
Health + Grid = HealthGrid
Health:
All levels of data & information, from molecule to
population needed to ensure better prevention,
diagnosis and treatment.
Grid:
An environment, created through the sharing of
resources, in which heterogeneous and dispersed data
as well as applications can be accessed by different
partners according to their authorisation, without loss
of information.
Draft Ideas, September 2002
HealthGRID
Public Health
Public Health
Patient
Tissue, organ
Cell
Molecule
Association
Modelling
Computation
Patient
Patient
Tissue, organ
Cell
Molecule
related data
Databases
INDIVIDUALISED HEALTHCARE
MOLECULAR MEDECINE
Computational
recommandation
In 5 Years !
Infrastructures, Technology
Epidemiology
Grid
Imaging
Grid
HealthGrid
Pharma
Grid
Conferences & web site
www.healthgrid.org
Hospital
Grid
BioGrid
BrainGrid
Environment, Astronomy,Physics
In 10 Years ?
Infrastructures, Technology
Imaging
Grid
Epidemiology
Grid
HealthGrid
Pharma
Grid
Conferences & web side
Hospital
Grid
www.healthgrid.org
BrainGrid
BioGrid
Environment, Astronomy,Physics
Starting Point
Grid-Enabled Medical
Simulation Services
European federated
mammogram database on
a GRID infrastructure
Trial for the introduction of
the Grid approach in the
biotechnology industry
Biology & Medical Apps:
Medical imaging
BioGrid Task: operate a
Grid for biomolecular
simulations
Computational Grid for
“Virtual Arteries”
Surgical support tool
1st Conference
HealthGrid 2003, Lyon January 2003

Knowledge and information discovery across
distributed/federated databases

Computational grids

Integration

Virtual organisations

Privacy & security

Healthcare reluctance to introduce new IT
www.healthgrid.org

Under development - depends on your input

Information about Grid technology - also for starters

Link to projects (EU, US, ASIA etc.)

Information about conferences

Central contact point - who, what, how

Developed by the HealthGrid Association
HealthGrid 2004
January 29th - 30th 2004, Clermont-Ferrand, France
http://clermont2004.healthgrid.org
The aims of this conference are to reinforce and promote
awareness of the possibilities and advantages linked to the
deployment of GRID technologies in health. In this context
"Health" does not involve only clinical practice but covers
the whole range of information from molecular level (genetic
and proteomic information) through cells and tissues, to the
individual and finally the population level (social healthcare).
Medical Imaging Grid’s

MAMMOGRID (Mammogram database)

eDIAMOND (Mammogram database)

GEMSS (Medical Imaging Reconstruction)

MEDIGRID (Medical Images for 3D modelling)

NDMA (National Digital Mammography Archive)

etc etc.
GEMSS: GRID-enabled Medical
Simulation Services
Project Duration: 30 months, Commencement: 1.9.2002
Grid Software Simulation
/solutions
/Imaging
Software
Bio-numeric Medical
modelling
Expertise
Legal
Aspects
Medical simulation service
+ networked compute resources
User-site
Simulation Service System
(SW installed)
GRID SW (interface)
Pre- & Postprocessing
GRID
SW
Could also be moved
to the services portal
Applications SW
GRID SW
(service use)
Internet
Internet
or
orIntranet
Intranet
http://www.gemss.de
GEMSS - main goals
Main GEMSS Goals:





Secure and lawful Grid provision of medical
simulation services,
Build 6 Grid-enabled medical prototype applications,
Build suitable middleware on top of common
standards,
Install and evaluate a GEMSS test-bed,
Anticipate privacy, security and other legal concerns
related to providing medical services over the
Internet.
GEMSS Technical Goals & Challenges
Web Service Security
Secure Transfer (https)
Secure Transfer (https)
Web Service Security
Bridge to
local PKI ?
Local
Authorisation
Keystore +
Certificates
Keystore +
Certificates
SOAP marshalling
Web Service
Apache
Error
Application QoS
recovery
Logger
WSDL
Language API
Registry
Certification
Invocation
Business Application
Processes Workflow
Nego
tiation
Client
Internet
• Workflow
Enactor
• Negotiation
• Business
Processes
Necessary Assumption:
No special purpose network infrastructure
UI
Elements
Appropriate
User
Interfaces
&
Applications
Workflow
Server
Logger
Compute
Resource
Conversational
Authorisation
VNC
Data
Storage
Negotiated
Service
Provision
• Secure Transfer, Web Services Security, Logging
GEMSS - outlook
Status of Work:

GEMSS has finalised its design phase:
client-server arch. based on web services
(OGSA-compliant).

Outlook: prototype system
– Feb. 2004
final GEMSS system – Aug. 2004

Contribution to Standardisation:
GEMSS is assessing its involvement in GGF, IETF or
W3C. Final Strategy has yet to be decided.
MammoGrid - European federated
mammogram database implemented
on a GRID infrastructure
Main goals:



To provide a demonstrator for use in epidemiological
studies, quality control and validation of computer
aided detection algorithms.
Development of a fully functional Grid for these
purposes, which will be implemented in hospitals.
Development of some CADe techniques - use of the
SMF (Standard Mammogram Form)
http://lotus5.vitamib.com/hnb/mammogrid/mammogrid.nsf/Web/Frame?openform
MammoGrid Federated System Solution
Hospital Italy
Local
Analysis
Local
Query
Healthcare Institute
University Database
Local
Query
Local
Query
Local
Analysis
Local
Analysis
GRID
Local
Local
•Knowledge is stored alongside data
•Active (meta-)objects manage
Analysis Query
various versions of data and
Hospital UK
algorithms
•Small network bandwidth required
Query
Result
Clinician’s Workstations
Massively distributed data
AND distributed analyses
Shared meta-data
Analysis-specific data
MammoGrid
Why a Grid infrastructure ?

Large federated databases



Ontologies and metadata







large data (size of images)
needs enough data for statistics
Heterogeneous image formation parameters and features
Needs “standard” for comparison
Clinical information
Geographically distributed data
Effective data mining of a rapidly growing database
Computing expensive simulations
Allow for complex queries involving executables
MammoGrid Challenges

Data resides in hospitals


Legal restrictions on access to data





Firewall protected
Clinicians, researchers, developers, Govt, …
Secure file transfer - Patient privacy & security
Combining several databases
Medical image analysis clients are not Grid experts!
Services must be system-resident, invisible, generic.
Impact of Grid technology in Health

Define collaborations.
There is a need for both technology developers and users
in order to move from “research to applications”.

Define resources to be shared and access rights address privacy and security issues.

Awareness of other Grid’s - no reinventing the wheel,
interoperability

Creation of a HealthGrid community will ensure
impact on standards, enable showcases etc.
Thank you for your attention !