Transcript Day 2 - P2 ALERT overview-J van der Lei

The ALERT Project
Early Detection of Adverse Drug Events
by Integrative Mining of Clinical Records
and Biomedical Knowledge
Johan van der Lei
Erasmus MC – University Medical Center Rotterdam
Consortium Members
Participating institutions:
• Aarhus University Hospital, Århus Sygehus, Denmark
• Agenzia regionale di Sanità, Italy
• AstraZeneca AB, Sweden
• Erasmus University Medical Center, Netherlands
• Fundació IMIM, Spain
• Health Search - Italian College of General Practitioners, Italy
• Imperial College London, UK
• IRCCS Centro Neurolesi “Bonino-Pulejo”, Italy
• London School of Hygiene & Tropical Medicine, UK
• PHARMO Coöperation UA, Netherlands
• Pedianet - Societa’ Servizi Telematici SRL, Italy
• Tel-Aviv University, Israel
• Università di Milano-Bicocca, Italy
• Université Victor-Segalen Bordeaux II, France
• University of Aveiro – IEETA, Portugal
• University of Nottingham, UK
• University of Santiago de Compostela, Spain
• University Pompeu Fabra, Spain
Premises
• We need earlier detection of ADRs
• Clinical records as source
• International, diversity as asset
• Sheer volume (Alert: > 30.000.000 pts)
• Methods of signal detection
• “Real” challenge: detect false-positives
• Causal hypothesis
Belief
• Fragmented universe
• Expertise is judged “locally”
• Each local environment has “own” rules
• If only ….
“We are not students of some subject
matter, but students of problems. And
problems may cut right across the borders
of any subject matter or discipline.”
K.R. Popper (1963). Conjectures and Refutations: The Growth of Scientific
Knowledge.
Multi versus Inter
• Multidisciplinary
– More than one discipline
– Separate contributions
• Interdisciplinary
– Integration and synthesis
– Exchange of methodology
National Academy of Sciences, National Academy of Engineering,
Institute of Medicine (2005). Facilitating Interdisciplinary Research.
Consortium Members
The ALERT Consortium is composed of: 15 beneficiaries + 3 subcontractors
AZ
AUH-AS
UNOTT
ICL
LSHTM
USC
UB2
EMC
PHARMO
UNIMIB
UAVR
SIMG
UPF
FIMIM
PEDIANET
ARS
NEUROLESI
EHRs Databases
TAU (Tel–
Aviv)
Consortium Profile
UB2
NEUROLESI
Spontaneous Reporting Systems
UNIMIB
UPF
PEDIANET
USC
UNOTT
EHRs Databases
ARS
EMC
AZ
BMI Knowledge
PHARMO
TAU
AUH-AS
UAVR
SIMG
Extraction and Interpretation
of Clinical Data
LSHTM
ICL
Project Management
FIMIM
“The time is upon us to recognize that the new
frontier is the interface…. Innovators will need to
jettison the security of familiar tools, ideas, and
specialties as they forge new partnerships.”
F.C. Kafatos, T. Eisner. Unification in the century of biology. Science, 2004;303:1257
Objectives
• Can we detect events
• Can we relate these events to drugs
• Can we develop hypothesis that explain
adverse events
• Can we detect adverse events earlier
• Can we avoid false positives
Strategy
• Focus on science
• Focus on concrete questions
– Accept the lessons of Chaos Theory
• Questions will iterate
– The journey is the reward
• Respect local autonomy
• Foster respectful collaboration
• Respect and address ethical concerns
Strategy – we will not:
• Create companies or institutions
• Share data on the level of individuals
• Will not include `official` bodies