Transcript No Slide Title

Konstantinos Perakis, Thanasis Bouras, Dimitris Ntalaperas,
Panagiotis Hasapis, Christos Georgousopoulos, Ratnesh Sahay,
Oya Deniz Beyan, Cristi Potlog, Daniela Usurelu
Linked2Safety Project (FP7-ICT-2011-7 – 5.3)
A NEXT-GENERATION, SECURE LINKED DATA MEDICAL INFORMATION SPACE FOR
SEMANTICALLY-INTERCONNECTING ELECTRONIC HEALTH RECORDS
AND CLINICAL TRIALS SYSTEMS
ADVANCING PATIENTS SAFETY IN CLINICAL RESEARCH
Kick-Off Meeting
Athens, 20-21 October 2011
Currently, EU legislation is strict about processing patient data, especially when
it comes to genetic information:
• It does not matter whether the data to which the program is applied were
previously pseudonymous
• It would be possible for a third party to achieve such a link unofficially, through the
process of data-matching
• The processing should be carried out on-site and should be subject to significant
security measures
• Our approach, as part of a larger ICT project (named Linked2Safety) reflects all of
the above
• There are two core ideas that we implement to address legal issues:
• Usage of data-cubes processing
• Closed-world room data-cubes generation
FP7, ICT-2011 – 5.3
Page 2
Clinical EHR aligned data in a common format
(always in Closed-world Room)
Data-cube
Clinical record A
<Patient>
<Age>30</Age>
<DOB> 1/1/1900</DOB>
…
</Patient>
<Patient>
<Age>30</Age>
<DOB> 1/1/1970</DOB>
…
</Patient>
0 0 0 0 1…
4 8 0 0 5…
0 0 0 2 0…
……
Clinical record B
Data-cube in RDF Format
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>.
@prefix sdmx-metadata: <http://purl.org/linked-data/sdmx/2009/metadata#>.
<http://linked2safety-project.eu/dataset/data-cube/diabetes/2012-07-20/o1> qb:dataSet <http://linked2safety-project.eu/dataset/data-cube/diabetes/2012-07-20>;
l2s-dimension:Diabetes <http://linked2safety-project.eu/dataset/data-cube/diabetes/diabetes/0>;
l2s-dimension:Weight <http://linked2safety-project.eu/dataset/data-cube/diabetes/weight/1>;
sdmx-measure:Cases “0"^^xsd:long;
a qb:Observation.
<http://linked2safety-project.eu/dataset/data-cube/diabetes/2012-07-20/o2> qb:dataSet <http://linked2safety-project.eu/dataset/data-cube/diabetes/2012-07-20>;
l2s-dimension:Diabetes <http://linked2safety-project.eu/dataset/data-cube/diabetes/diabetes/1>;
l2s-dimension:Weight <http://linked2safety-project.eu/dataset/data-cube/diabetes/weight/1>;
sdmx-measure:Cases “8"^^xsd:long;
a qb:Observation.
FP7, ICT-2011 – 5.3
Page 3
FP7, ICT-2011 – 5.3
Page 4
Based on openEHR
Collected from the
consortium
data providers
FP7, ICT-2011 – 5.3
Page 5
Part of
Semantic EHR
Schema of
input file
FP7, ICT-2011 – 5.3
Page 6
FP7, ICT-2011 – 5.3
Page 7
• Add Noide: Perturbation is implemented allowing for both negative and positive perturbation. Thus if the perturbation range is 3, then a random integer
will be generated under a normal distribution within the range of [3;3]
and added to the original value.
•Cut-off: Each cell is tested if it exceeds a pre-set threshold value referred to
as the cut-off threshold. If it passes the cut-off threshold then
it is reported as is, if not then it is replaced.
foreach line
computeunique_key
foreach cell in line_cells
cell_field++
value[cell_field] = valueOf(cell)
value[cell_field] = convertInRange(value, ranges[cell_field])
Cube[unique_key][indexOf(value[cell_field])]++
foreachunique_key
for i=1 to num_of_fields
perturbe(Cube[unique_key][i])
if Cube[unique_key][i] <= threshold
discard (Cube[unique_key][i])
FP7, ICT-2011 – 5.3
Page 8
• This mechanism is responsible for converting the aggregated clinical data which are in the form of
a data cube, into an RDF version of itself adhering to the RDF Data Cube Vocabulary .
• The RDF Data Cube Vocabulary introduces a reusable set of concepts and components based on
SDMX (Statistical Data and Metadata Exchange)
• The SDMX standard includes a set of Content Oriented Guidelines (COG) which define a set of
common statistical concepts and associated code lists that are intended to be reusable across data
sets.
• An extension Data cube structure definition was always created (based on SEHR) to extend the
concepts supported by SMDX.
• The core class element of an RDF Data Cube Vocabulary is the “Dataset”. This class describes the
structure of a data cube as a collection of the class “Observation”. The latter class holds the
description of an occurrence number, the dimensions coordination for that number along with the
semantics of those dimensions.
FP7, ICT-2011 – 5.3
Page 9
• All of the components described within this paper were designed and developed in
the context of the Linked2Safety project and were validated in real life scenarios
at the premises of the consortium clinical data providers
• The clinical piloting candidates indicated the data variables utilized in clinical
practice, from which the two schema models (SEHR and CEHR) were built.
• With regards to the adverse events identification, a key point is the ability to relate
different types of adverse events to different molecular fragments and thus the
ability to detect the possibility of an adverse event occurring when specific
conditions are in place.
FP7, ICT-2011 – 5.3
Page 10
• The conduction of a fully scaled two-phase piloting procedure
is envisaged to be conducted for validating and evaluating
the Linked2Safety platform prior to its final release.
• Incorporation of MedDRA taxonomy into Semantic EHR
FP7, ICT-2011 – 5.3
Page 11
Any Questions ??
FP7, ICT-2011 – 5.3
Page 12
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
L. Kun, R. Beuscart, G. Coatrieux, C. Quantin, "Improving outcomes with interoperable EHRs and secure global health information
infrastructure", 29th IEEE EMBS Int. Conf, pp. 6158 - 6159, August 2007
O. Kilic, A. Dogac, M. Eichelberg, “Providing Interoperability of eHealth Communities Through Peer-to-Peer Networks”, IEEE Transactions on
Information Technology in Biomedicine, Volume: 14 , pp. 846 – 853, May 2010
WHO, "Building Foundations eHealth in Europe", Available online at: http://www.who.int/goe/BFeuroFull.pdf, 2010
B. Stewart, S. Fernandes, E. Rodriguez-Huertas, M. Landzberg, "A preliminary look at duplicate testing associated with lack of electronic
health record interoperability for transferred patients", JAMIA 2010; 17:341-344 doi:10.1136/jamia.2009.001750
O. Kilic, A. Dogac, M. Eichelberg, “Achieving Clinical Statement Interoperability Using R-MIM and Archetype-Based Semantic
Transformations”, IEEE Trans. Inf. Tech. Biomedicine, Volume: 13, pp. 467 - 477, July 2009
J. T. Fernandez-Breis, P. J. Vivancos-Vicente, M. Menarguez-Tortosa, D. Moner, J. A. Maldonado, R. Valencia-Garcia, T. G. Miranda-Mena,
"Using semantic technologies to promote interoperability between electronic healthcare records' information models ", 28th IEEE EMBS Int.
Conf, pp. 2614-2617, Sept. 2006
L. Al-Safadi, "Semantic-Based Exchanger for Electronic Medical Record", 3rd Int. Conf. on Convergence and Hybrid Information Technology,
2008
A. Antoniades et al., "Linked2Safety: A secure linked data medical information space for semantically-interconnecting EHRs advancing
patients' safety in medical research", 12th Int. IEEE Conf. on Bioinformatics & Bioengineering (BIBE), IEEE, 2012
N. Forgó, M. Góralczyk, and C. Graf von Rex. "Security issues in research projects with patient's medical data", 12th Int. IEEE Conf. on
Bioinformatics & Bioengineering (BIBE), IEEE, 2012
Sahay, R., Fox, R., Zimmermann, A., Polleres, A., and Hauswirth, M. (2011). A Methodological Approach for Ontologising and Aligning
Health Level Seven (HL7) Applications. In ARES 2011 - Proceedings of the Availability, Reliability and Security for Business, Enterprise and
Health Information Systems, Vienna, Austria, August 22-26, pages 102–117. Springer LNCS Series
FP7, ICT-2011 – 5.3
Page 13