Upload
andre-dekker
View
386
Download
2
Embed Size (px)
Citation preview
Andre Dekker, PhDMedical PhysicistMAASTRO Clinic
MaastrichtThe Netherlands
Informatics and Clinical Decision Support in Precision Medicine
2
© MAASTRO 2015
Disclosures
Research collaborations incl. funding / honoraria etc.– Varian (VATE, chinaCAT, euroCAT), Siemens (euroCAT), Sohard (SeDI,
CloudAtlas), Mirada Medical (CloudAtlas), Philips (EURECA, TraIT, SWIFT-RT), Xerox (EURECA), De Praktijkindex (DLRA)
Public research funding– Radiomics (USA-NIH/U01CA143062), euroCAT(EU-Interreg), duCAT (NL-
STW), EURECA (EU-FP7), SeDI & CloudAtlas (EU-EUREKA), TraIT (NL-CTMM), DLRA (NL-NVRO)
Spin-offs and commercial ventures– MAASTRO Innovations B.V. (CSO)– Various patents on medical machine learning
3
© MAASTRO 2015
Review the feasibility of engaging stakeholders on an international scale
from academia, government, and industry
to develop an open source interoperable informatics research infrastructure
for the evaluation of clinical support systems and the technical requirements to meet this goal.
4
© MAASTRO 2015
Data > Decision Support
1. Modeling“Learn a model from data”
2. Validation“Estimate model performance”
3. Decision Support“Impact of the model on clinical practice”
5
© MAASTRO 2015
Dehing-Oberije (MAASTRO), IJROBP 2009;74:355
A model learnt from data – Early Example
Training cohort– 322 patients (MAASTRO)
Clinical variablesSupport Vector MachinesNomogram
Validated in external hospitals from Belgium
AUC 0.75 for 2 year survival
Cary Oberije et al.
6
© MAASTRO 2015
Radiomics (www.radiomics.org)
Source: Nature Communic. 5:4006 (2014)
7
© MAASTRO 2015
Clinical Decision Support / Rapid Learning Health Care / Precision Medicine / Predict outcome in an individual
In [..] rapid-learning [..] data routinely generated through patient care and clinical research feed into an ever-growing [..] set of coordinated databases. J Clin Oncol 2010;28:4268
[..] rapid learning [..] where we can learn from each patient to guide practice, is [..] crucial to guide rational health policy and to contain costs [..].Lancet Oncol 2011;12:933
Examples: Radiotherapy CAT (www.eurocat.info) ASCO’s CancerLinQ
Source: J Clin Oncol 2010;28:4268
8
© MAASTRO 2015
Scaling up to all cancer patients
Oncology2005-2015140M patients100k hospitals1-10GB per patient140-1400PB80% unstructured
Source: Cancer Research UK
Source: Institute for Health Technology Transformation
9
© MAASTRO 2015
Informatics Need
• You need to learn from other patients to predict the outcome of a new patient
• These data are spread out over 100k hospitals
• So we need to share…, challenges:• Administrative (I don’t have the
time)• Political (I don’t want to )• Ethical (I am not allowed)• Technical (I can’t)
Oncology2005-2015140M patients100k hospitals1-10GB per patient140-1400PB80% unstructured
[..] the problem is not really technical […]. Rather, the problems are ethical, political, and administrative. Lancet Oncol 2011;12:933
10
© MAASTRO 2015
The ‘standard’ approach
• Sharing standardized, highly curated data from clinical research programs
11
© MAASTRO 2015
TraIT – Translational Research IT Platform
Oct 2015: 1750 users – 250 centers – 215 studies – 32 partnersUniversity Medical Centers, several other public institutions, charities, and companies2011-now: ~15-20M€
12
© MAASTRO 2015
The ‘standard’ approach
• Sharing standardized, highly curated data from clinical research programs
• Very useful, but only 3% of patients (if that)• Worries about privacy, loss of control, limited amount of
features, limited reusability, a lot of work
13
© MAASTRO 2015
A different approach
If sharing is the problem: Don’t share the data
If you can’t bring the data to the learning applicationYou have to bring the learning application to the data
Consequences• The learning application has to be distributed • The data has to be readable by an application (i.e. not a human)
• Solution: Sharing standardized highly curated research data• Solution: Not-sharing non-standardized non-curated clinical data
14
© MAASTRO 2015
Source: Varian Medical Systems
15
© MAASTRO 2015
In-hospital infra & de-identification
Deidentification:• Removal of obvious patient identifiers (name, MRN, social security number, email etc.)• Assign a persistent token pseudonym• Change (data banding) of obvious but required patient identifiers (everyone born and died on the
15th of the month, part of the postal code)• No individual patient data leaves the hospital
16
© MAASTRO 2015
euroCAT, duCAT, chinaCAT, ozCAT, VATE, ukCAT, dkCAT, worldCAT, BIONIC Network
Industry Partners
Active or funded CAT partners (19)
Prospective centers
2
5
Map from cgadvertising.com
5
Clinical / Academic Partners
17
© MAASTRO 2015
Summary
Review the feasibility of engaging stakeholders on an international scale from academia, government and industry It is very feasible to do this on an international scaleto develop an open source interoperable informatics research infrastructure We choose both a centralized approach AND a Semantic Web / Linked Data approach with 80% open sourcefor the evaluation of clinical support systems For us these are systems which predict outcomes using clinical dataand the technical requirements to meet this goal.Future: Don’t share the data, keep them where they are now
18
© MAASTRO 2015
Acknowledgements
• Varian, Palo Alto, CA, USA• Siemens, Malvern, PA, USA• RTOG, Philadelphia, PA, USA• MAASTRO, Maastricht, Netherlands• Policlinico Gemelli, Roma, Italy• UH Ghent, Belgium• Catherina Zkh Eindhoven, Netherlands• UZ Leuven, Belgium• Radboud, Nijmegen, Netherlands• University of Sydney, Australia
• Liverpool and Macarthur CC, Australia• CHU Liege, Belgium• Uniklinikum Aachen, Germany• LOC Genk/Hasselt, Belgium• Princess Margaret Hospital, Canada• The Christie, Manchester, UK• UH Leuven, Belgium• State Hospital, Rovigo, Italy• Illawarra Shoalhaven CC, Australia • Fudan Cancer Center, Shanghai, China
More info on: www.predictcancer.org www.cancerdata.orgwww.eurocat.info www.mistir.info
Andre Dekker, PhDMedical PhysicistMAASTRO Clinic
MaastrichtThe Netherlands
Thank you for your attention
More info on: www.eurocat.info
www.predictcancer.orgwww.cancerdata.org
www.mistir.infowww.maastro.nl