Linked Data efforts for data standards in biopharma and healthcare

download Linked Data efforts for data standards in biopharma and healthcare

of 12

  • date post

    21-Jan-2017
  • Category

    Technology

  • view

    1.018
  • download

    0

Embed Size (px)

Transcript of Linked Data efforts for data standards in biopharma and healthcare

QUEST

Linked Data efforts for data standards in biopharma and healthcare

Kerstin Forsberg (@kerfors on Twitter, SlideShare etc.)Informatics Analyst and Lifetime LearnerAZ IT | R&D Information

Lnkade Data i Sverige 2016, LDSV2016

See alsohttp://kerfors.blogspot.se/2016/04/linked-data-in-sweden-2016.html

Standardized the StandardsIn traditional standard organizationsCDISC in RDFHL7 FHIR in RDFMeSH in RDFICD-11 in OWLOthers standards e.g. ATC, WHO Drug and MedDRA

2Kerstin Forsberg | LDSV2016, April 26 2016AZIT | R&D Information

Use standardized standards3Web of (Linked) DataAn Intro To The Semantic Web: Why You Need To Know About It Sooner Than Later , by Samantha Wong Image Source: Frederic Martin

Kerstin Forsberg | LDSV2016, April 26 2016AZIT | R&D Information

http://yosemiteproject.org/In new cross-functional communities

3

Standardized the StandardsObservationsPushing back to traditional standard organizations requires knowledge awareness and community buildingMuch of the work done in new cross-functional communities e.g. Yosemite project and PhUSEMany use githubExcel spreadsheets still rules :-(

4Kerstin Forsberg | LDSV2016, April 26 2016AZIT | R&D Information

CDISC2RDF, Oct 2012 a pre-competitive project with AZ, Roche, W3C et al. to show case Semantic Web standards and Linked Data principles.

FDA meeting Nov 2012: Solutions for Study Data Exchange Standards Meeting W3C Semantic Web presentation.

June 2013 the Semantic Technology project, a FDA/PhUSE working group for Emerging Technologies, with 25+ repr. from FDA, CDISC, Pharma:s, CRO:s and software vendors.

Oct 2013 press release: Representing existing standards (SDTM, CDASH,SEND, ADaM) in RDF.

Dec 2014, Public review of CDISC in RDF Guide.

July 2015, Published on http://www.cdisc.org/rdf and https://github.com/phuse-org/rdf.cdisc.org

CDISC (clinical study data standards) in RDFKnowledge awareness and community building 5

CDISC Interchange Europe 2011 and 2012presentations from Roche and AstraZeneca

Kerstin Forsberg | LDSV2016, April 26 2016AZIT | R&D Information

5

6Kerstin Forsberg | WHO UMC, Jan 21 2015AZIT | R&D InformationCDISC in RDFFrom Human Readable to Machine Processable

RDF triples describing one variable/data elementand linking to related standard parts

6

MeSH in RDF

Example http://id.nlm.nih.gov/mesh/D015242for Ofloxacin in MeSH

ICD-11 in OWLiCAT tool, but Excel spreadsheets still rules :-(8Author | 00 Month YearSet area descriptor | Sub level 1

Pushing back to get MedDRA in RDFAZ Vocabulary Management team shared this with MedDRA MSSO9Courtland Yockey, Informatics AnalystAstraZeneca R&D Information, USA

A very simple SKOS-rendering of MedDRA term skos:Concept hierarchy level skos:ConceptScheme SMQ skos:Collection

Approach should be augmented with VoID representation of MedDRA versions and term properties distinguishing active from inactive terms.

Skos:Collection is likely not sufficient to support SMQ versioning nor context of terms in an SMQ (e.g. weight)

Kerstin Forsberg | LDSV2016, April 26 2016AZIT | R&D Information

9

Pushing back to get ATC codes in RDFAZ Vocabulary Management team created a RDF representation of ATC codes using the SKOS Schema 10Courtland Yockey, Informatics AnalystAstraZeneca R&D Information, USA

4 example RDF Triplesrepresenting part of a ATC code

Kerstin Forsberg | LDSV2016, April 26 2016AZIT | R&D Information

10

Standardized the StandardsObservationsPushing back to traditional standard organizations requires knowledge awareness and community buildingNew cross-functional communities e.g. Yosemite project and PhUSEMany use githubExcel spreadsheets still rules :-(

11Kerstin Forsberg | LDSV2016, April 26 2016AZIT | R&D Information

Semantic WebStandardsA stack of standards to represent data and semantics based on Resource Description Framework (RDF). RDF is a framework for creating statements in a form of so-called triplesOWL and SKOS: RDF-based standards to represent vocabularies of terms representing identified entities and conceptsSPARQL: query language for RDF triples

Building Linked Data Applications

Use of Semantic Web standards and Linked Data principles enabling us to ask questions and solve business problems across a heterogeneous information landscape across open and closed sources

Capture Business Questions and SourcesDomain Expert Concept MapBuild Formal Ontolog!Challenge with Linked Open DataModel Business Questions (SPARQL)Interact with RDF answer in a Faceted BrowserWeb of DataOpen and ClosedOpen data sources applying the Linked Data principles and semantic web standards as a Web of DataCentral is the Wikipedias structured content via DBpedia used by e.g. Googles KnowledgeGraph and IBMs Watson.Closed data sources now also form internal Webs of Data

Linked DataPrinciplesUse URIs (Uniform Resource Identifiers) as names for things.Use HTTP URIs so that people can look up (dereference) those names.When someone looks up a URI, provide useful information.Include links to other URIs so that they can discover more things

Linked Data in One slideKerstin Forsberg | LDSV2016, April 26 2016AZIT | R&D Information