Social Pharmacy and Pharmacoepidemiology Lister Hill National Center for Biomedical Communications Text-based Discovery in Biomedicine The Architecture.

Social Pharmacy andPharmacoepidemiology

Lister Hill National Center forBiomedical Communications

Text-based Discovery in Biomedicine

The Architecture of the DAD-system

Marc Weeber1,2, Henny Klein1,Alan R. Aronson2, Jim G. Mork2,

Lolkje T. W. de Jong - van den Berg1, Rein Vos1,3

1Department of Social Pharmacy and Pharmacoepidemiology, Groningen University Institute for Drug Exploration, The Netherlands

2Lister Hill National Center for Biomedical Communication, National Library of Medicine, Bethesda, MD

3Health Ethics and Philosophy, Faculty of Health Sciences, University of Maastricht, The Netherlands



Introduction• Goal:

Finding new biomedical knowledge through the combination of existing knowledge as represented in the medical literature

• Motivation:

Prevention of re-inventing the wheel, re-usage of specific knowledge outside the original domain of discovery



Swanson

• AB: Raynaud’s disease is characterized by high blood viscosity and high platelet aggregation

• BC: Fish oil is known to reduce blood viscosity and platelet aggregation

A CB?



Vos and Rikken

• Drugs instead of diet factors

• Intermediate (B) terms are adverse drug reactions

• Drug – Adverse drug reactions – Disease: The DAD-system

• Vos (1991) Drugs looking for diseases



Existing Techniques

• Swanson & Smalheiser:• Single words/multi word terms• MEDLINE titles• No statistics

• Gordon & Lindsay:• Single words/multi word terms• Information Retrieval statistics• Replication of Swanson’s discoveries



New Techniques

• Use of UMLS concepts

• PubMed

• MetaMap: mapping free text (MEDLINE titles and abstracts) to concepts

• Interactive web interface



Two-step Approach

• Open discovery, generating a hypothesis

A ??

• Closed discovery, testing a hypothesis

A C?



Why UMLS Concepts?

• Use of only biomedically relevant information

• Useful transition from single word to multi word term

• Semantic information (semantic types) for filtering (e.g. select only Disease or Syndrome)



DAD-system

Meta-thesaurus

SpecialistLexicon

PubMed SemanticNetwork

MetaMapKS



DAD-system

Meta-thesaurus

MySQLDatabase

SpecialistLexicon


MetaMap

FilterTxt2ConQuery ShowSelect

KS



DAD-system

Meta-thesaurus

MySQLDatabase

SpecialistLexicon


MetaMap

FilterTxt2ConQuery ShowSelect

KS



A

Open Discovery

•Query (user input):

raynaud’s disease



A

Open Discovery

•Mapping text to concept through MetaMap:

Raynaud's Disease [Disease or Syndrome]



A

Open Discovery

•Synonym lookup:

Raynaud's syndrome Raynaud's disease /phenomenon

•Variant generation:

e.g. syndrome / syndromes



A

Open Discovery

•PubMed query:

raynaud OR raynauds

•Processing: query in titles and abstracts

•Result: 1,246 MEDLINE citations



A

Open Discovery

•Text to concept mapping of all citations

•Sentences with Raynaud’s disease

•Result: 1,278 UMLS concepts



A

Open Discovery

•Select functional/physiological concepts•Semantic types in filter:

Body Location or RegionBiologic FunctionCell FunctionPhenomenon or ProcessPhysiologic FunctionTissue



A B

Open Discovery

•Result: 57 Concepts

•Frequency range:

1- 18



A B

Open Discovery

•Selected B-concepts:

Plasma Viscosity LevelBlood ViscosityPlatelet AdhesivenessPlatelet AggregationEffects, Blood

Coagulation



A B

Open Discovery

•Variants:

plasma, plasmasviscosity, viscous,aggregation, aggregations,

aggregatingcoagulation, coagulating



A B

Open Discovery

•PubMed query:

blood coagulation OR blood viscosity OR plasma viscosity OR platelet

adhesiveness OR platelet aggregation

•Result: 10,611 MEDLINE citations



A B

Open Discovery

•Concepts in sentences with B-concepts:

7,702

•Concepts not in Raynaud sentences:

6,747



A B

Open Discovery

•Filter for dietary related concepts

•Semantic types in filter:

VitaminLipidElement, Ion, or Isotope



A B C

Open Discovery

Eicosapentaenoic AcidFish OilFatty Acids, Omega 3MAXEPAOmega-3

PolyunsaturatedFatty Acid

Cod Liver OilSalmon Oil

•Result: 206 Concepts

•Rank order on relations

•Fish oil related concepts:



A C

Closed Discovery

Eicosapentaenoic AcidFish OilFatty Acids, Omega 3MAXEPAOmega-3

PolyunsaturatedFatty Acid

Cod Liver OilSalmon Oil

Raynaud’s Disease



A C

Closed Discovery

1,246 citations1,278

concepts

479 common concepts

463 citations1,795

concepts



A C

Closed Discovery

Functional / Physiological Filter

45 B-concepts



A C

Closed Discovery

B

•Known concepts:

Plasma viscosity level

Blood ViscosityPlatelet

AdhesivenessPlatelet AggregationEffects, Blood

Coagulation

•New concepts:

VasodilatationVeins, CapillariesDinoprostoneFibrinolysisDeformabilityRheology



Juxtaposition



Success / Failure +Simulation of Raynaud’s disease – fish

oil and migraine – magnesium

+Discovery of new therapeutic applications for thalidomide

- Mapping (Mg = milligram / magnesium)

- Association defined by co-occurrence



Future

• Better semantic analysis:increase(A,B) and decrease(B,C)

• Better user interface

• More databasese.g. finding genetic bases for diseases

Social Pharmacy and Pharmacoepidemiology Lister Hill National Center for Biomedical Communications Text-based Discovery in Biomedicine The Architecture.

Documents

biomedical communications

department of social

netherlands slide

new biomedical knowledge

syndrome slide

national library of

dadsystem vos

dadsystem marc weeber